NATIONAL OPEN UNIVERSITY OF NIGERIA

SCHOOL OF BUSINESS AND HUMAN RESOURCES

COURSE CODE:MBA 757

COURSE TITLE:DECISION SUPPORT SYSTEMS (DSS)

MBA 757 DECISION SUPPORT SYSTEM

COURSE
GUIDE

MBA 757
DECISION SUPPORT SYSTEMS (DSS)

Course Team Gerald C. Okereke (Developer/Writer) - ICT

NATIONAL OPEN UNIVERSITY OF NIGERIA

ii
MBA 757 DECISION SUPPORT SYSTEM

National Open University of Nigeria

Headquarters
14/16 Ahmadu Bello Way
Victoria Island
Lagos

Abuja Office
No. 5 Dar es Salaam Street
Off Aminu Kano Crescent
Wuse II, Abuja
Nigeria

e-mail: [email protected]
URL: www.nou.edu.ng

Published By:
National Open University of Nigeria

First Printed 2010

ISBN: 978-058-907-4

All Rights Reserved

CONTENTS PAGE

iii
MBA 757 DECISION SUPPORT SYSTEM

Course Aim…………………………………………..………….. 1
Course Objectives………………………………………………… 1
Credit Units………………………………….…………………….. 2
Study Units…………………………………….………………….. 2
Course Assessment…………………………….………………….. 2

Course Aim

This course is designed for information systems experts and business

managers, generally to understand the application of decision support
systems in making timely and accurate business decisions. It is further
aimed at giving a correct trend and perspective of DSS in the evolution
of information systems. Also, it serves to encourage the usage of
decision support systems by business managers. Supportive information
systems are also examined from comparative and complimentary
perspectives.

iv
 MBA 757 DECISION SUPPORT SYSTEM

Course Objectives

The following are the major objectives of this course.

1. explain the different meanings of information systems

2. explain the concept of information systems and its evolution
1. classify DSS into various forms
2. identify the fields in which DSS are used
• identify different types of decision theory
• describe the applications of the different types of DSS
• compare and contrast the forms of DSS
1. distinguish the concept of e-business and decision support systems
3. describe the major e-business decision support applications that are
being customised, personalised, and web-enabled for use in e-
business and e-commerce
4. list different ways of applying predictive analysis in decision making
in life and business
• identify the applications of spreadsheets as decision making tools
• define the concept of executive information system (EIS)
5. describe the various applications of EIS in sectors of business
6. explain the major indices to identify an effective EIS implementation
in organisation
*0identify the major components of GIS
*1outline the steps to take in developing an effective GIS
6.0 define and understand the concept of expert systems
7.0 identify the advantages and disadvantages associated with expert
systems
1. define the concept of artificial intelligence
7. identify AI characteristics that are appealing to business functions

Credit Units

This course attracts 3 credit units.

Study Units

The study units of this course are as follows:

Module 1

Unit 1 Introduction to Information Systems

Unit 2 Overview of Decision Support System
Unit 3 Decision Theory and Decision Making

v
MBA 757 DECISION SUPPORT SYSTEM

Unit 4 Types of DSS

Unit 5 Decision Support in E-Business

Module 2

Unit 1 Online Analytic Processing, Online Transaction

Processing and Business Analytics
Unit 2 Predictive Analytics
Unit 3 Spreadsheet
Unit 4 Executive Information System 1
Unit 5 Implementing Executive Information System

Module 3

Unit 1 Geographic Information System

Unit 2 Expert Systems
Unit 3 Artificial Intelligence

Course Assessment

• Assignments = 30 %
• Examination = 70%

vi
MBA 757 DECISION SUPPORT SYSTEM

Course Code MBA 757

Course Title Decision Support Systems (DSS)

Course Gerald C. Okereke (Developer/Writer)

NATIONAL OPEN UNIVERSITY OF NIGERIA

vii
MBA 757 DECISION SUPPORT SYSTEM

National Open University of Nigeria

Headquarters
14/16 Ahmadu Bello Way
Victoria Island
Lagos

Abuja Office
No. 5 Dar es Salaam Street
Off Aminu Kano Crescent
Wuse II, Abuja
Nigeria

e-mail: [email protected]
URL: www.nou.edu.ng

Published By:
National Open University of Nigeria

First Printed 2010

ISBN: 978-058-907-4

All Rights Reserved

viii
MBA 757 DECISION SUPPORT SYSTEM

CONTENTS PAGE

Module 1 ………………………………………………………… 1

Unit 1 Introduction to Information Systems……………... 1

Unit 2 Overview of Decision Support System…………... 11
Unit 3 Decision Theory and Decision Making…………... 24
Unit 4 Types of DSS…………………………………….. 37
Unit 5 Decision Support in E-Business………………….. 49

Module 2 ………………………………………………………... 62

Unit 1 Online Analytic Processing, Online Transaction

Processing and Business Analytics………………. 62
Unit 2 Predictive Analytics……………………………… 76
Unit 3 Spreadsheet………………………………………. 91
Unit 4 Executive Information System…………………… 107
Unit 5 Implementing Executive Information System……. 116

Module 3 ………………………………………………………... 134

Unit 1 Geographic Information System…………………. 134

Unit 2 Expert Systems…………………………………… 149
Unit 3 Artificial Intelligence…………………………….. 162

ix
MBA 757 DECISION SUPPORT SYSTEM

MODULE 1

Unit 1 Introduction to Information Systems

Unit 2 Overview of Decision Support System
Unit 3 Decision Theory and Decision Making
Unit 4 Types of DSS
Unit 5 Decision Support in E-Business

UNIT 1 INTRODUCTION TO INFORMATION

SYSTEMS

CONTENTS

1.0 Introduction
2.0 Objectives
3.0 Main Content
3.1 History of Information Systems
3.2 The Evolution of the Concept of Strategic Information
Systems
3.3 The Structure of Information System
3.4 Types of Information Systems
3.5 Relationship of Systems to One Another
4.0 Conclusion
5.0 Summary
6.0 Tutor-Marked Assignment
7.0 References/Further Reading

1.0 INTRODUCTION

The term Information System (IS) sometimes refers to a system of

persons, data records and activities that process the data and information
in an organisation, and it includes the organisation's manual and
automated processes. Computer-based information systems are the field
of study for information technology, elements of which are sometimes
called an "information system" as well, a usage some consider to be
incorrect.

In this way, the term "information system" has different meanings:

• In computer security, an information system is described by three

objects (Aceituno, 2004):

1
MBA 757 DECISION SUPPORT SYSTEM

Structure

• Repositories, which hold data permanently or temporarily, such as

buffers, RAM, hard disks, cache, etc.
• Interfaces, which exchange information with the non-digital world,
such as keyboards, speakers, scanners, printers, etc.

Channels

• Which connect repositories, such as buses, cables, wireless links, etc.

A Network is a set of logical or physical channels.

Behaviour

• Services, which provide value to users or to other services via

messages interchange.
• Messages, which carry a meaning to users or services.

• In geography and cartography, a Geographic Information System

(GIS) is used to integrate, store, edit, analyse, share, and display geo-
referenced information. There are many applications of GIS, ranging
from ecology and geology, to the social sciences.
• In knowledge representation, an information system consists of three
components: human, technology, and organisation. In this view,
information is defined in terms of the three levels of semiotics. Data
which can be automatically processed by the application system
corresponds to the syntax-level. In the context of an individual who
interprets the data they become information, which correspond to the
semantic-level. Information becomes knowledge when an individual
knows (understands) and evaluates the information (e.g., for a
specific task). This corresponds to the pragmatic-level.
• In Mathematics, in the area of domain theory, a Scott information
system (after its inventor Dana Scott) is a mathematical 'structure'
that provides an alternative representation of Scott domains and, as a
special case, algebraic lattices.
• In Mathematics rough set theory, an information system is an
attribute-value system.
• In sociology information systems are also social systems whose
behaviour is heavily influenced by the goals, values and beliefs of
individuals and groups, as well as the performance of the technology.
• In systems theory, an information system is a system, automated or
manual, that comprises people, machines, and/or methods organised
to collect, process, transmit, and disseminate data that represent user
information.
• In telecommunications, an information system is any
telecommunications and/or computer related equipment or

2
MBA 757 DECISION SUPPORT SYSTEM

interconnected system or subsystems of equipment that is used in the

acquisition, storage, manipulation, management, movement, control,
display, switching, interchange, transmission, or reception of voice
and/or data, and includes software, firmware, and hardware.
• In organisational informatics, an information system is a system of
communication between people. Information systems are systems
involved in the gathering, processing, distribution and use of
information and as such support human activity systems.
• The most common view of an information system is one of Input-
Process-Output.

2.0 OBJECTIVES

At the end of this unit, you should be able to:

• define the different meanings of information systems

• describe the concept of information systems and its evolution
• outline the basic structure of information systems
• differentiate the different types of information systems and how they
relate to themselves.

3.0 MAIN CONTENT

3.1 History of Information Systems

The study of information systems, originated as a sub-discipline of

computer science, in an attempt to understand and rationalise the
management of technology within organisations. It has matured into a
major field of management that is increasingly being emphasised as an

3
MBA 757 DECISION SUPPORT SYSTEM

important area of research in management studies, and is taught at all

major universities and business schools in the world.

Information technology is a very important malleable resource available

to executives. Many companies have created a position of Chief
Information Officer (CIO) that sits on the executive board with the
Chief Executive Officer (CEO), Chief Financial Officer (CFO), Chief
Operating Officer (COO) and Chief Technical Officer (CTO).The CTO
may also serve as CIO, and vice versa.

3.2 The Evolution of the Concept of Strategic Information

Systems

Since the 1950's, the concept of information systems has evolved from
electronic accounting machines speeding paperwork and bureaucracy, to
providing general information support in functional areas through the
generation of routine performance reports in the 1960's (early
Management Information Systems). In the 1970's and beginning of the
80's systems that provided customised information to improve decision
making emerged (DSS and ESS). Since the mid-eighties, the role of
information systems has taken a different turn. Computing power and
networks have placed information systems at the heart of the business.
The concept of Strategic Information Systems has gained acceptance,
emphasising the fact that information is a strategic resource.

You must not confuse strategic information systems with strategic-level

systems like ESS. Strategic information systems can be at any level.
They are systems that fundamentally change the organisation itself. So
viewed from this perspective, each of the six types of systems,
Transaction Processing Systems (TPS), Knowledge Work Systems
(KWS), Office Automation Systems (OAS), Management Information
Systems (MIS), Decision Support Systems (DSS), and Executive
Support System (ESS) can potentially be regarded as strategic
information systems if their impact transforms the goals, business
processes, products and external relations of the company to produce
competitive advantage. In fact strategic information systems can change
the very nature of the business. In the next section we will see
applications of strategic information systems at the business level, firm
level and industry level.

3.3 The Structure of Information System

The structure of an information system may be visualised as

infrastructure plus applications. The applications have a conceptual
structure based on the purpose or needs being met and the functions of
the organisations that employ them. The three infrastructures that

4
MBA 757 DECISION SUPPORT SYSTEM

provide the general capabilities and capacity for information access and
processing are technology, data and personnel. The infrastructures
enable specific applications and activities.

2. The Technology Infrastructure consists of computer and

communication hardware, software, and general purpose software
systems. The computer hardware consists of computer and related
storage, input and output devices. The communication hardware
contains devices to control the flow of communications within
internal networks and with external network providers. Computer
hardware is made operational through system software and provides
generalised functions necessary for applications. Computer operating
systems, communication software, and network software is not
specific to a single application but provides facilities for many
different applications. An example is database management systems
to manage databases and perform access and retrieval function for a
variety of applications and users.

Figure 2: The components and structure of an information system.

3. The Database Infrastructure. The database forms a data

infrastructure. They provide for storage of data needed for one or
more organisational functions and one or more activities. There will
be a number of databases based on organisational activities. Planning
of the database infrastructures involves determining what should be
stored, what relationships should be maintained among stored data,

5
MBA 757 DECISION SUPPORT SYSTEM

and what restrictions should be placed on access. The result of

database planning and implementation with database management
system is a capacity to provide data both for application and ad hoc
needs. Comprehensive databases designed for ad hoc use may be
termed data warehouses.

4. Personnel. The information systems personnel can be viewed as a

third infrastructure, which includes all personnel required to establish
and maintain the technology, and the database infrastructures and the
capacity to perform user support, development, implementation,
operation and maintenance activities. The personnel may be divided
between an MIS function and functional areas. There may be , for
example, general purpose user support personnel in the MIS function
and functional information management support personnel in the
functional areas of the organisation.

All information systems use people, hardware, software, data, and

network resources to perform input, processing, output, storage, and
control activities that transform data resources into information
products.

3.4 Types of Information Systems

Different Kinds of Systems

Information systems support different types of decisions at different

levels of the organisational hierarchy. While operational managers
mostly make structured decisions, senior managers deal with
unstructured decisions; middle managers are often faced with semi-
structured decisions.

For each functional area in the organisation, three or four levels of

organisational hierarchy depending on the author, can be identified: the
operational level, knowledge level, management level and strategic
level. Each of these levels is served by different types of information
systems.

Major Types of Systems

Transaction Processing Systems (TPS) record daily routine

transactions such as sales orders from customers, or bank deposits and
withdrawals. TPS are vital for the organisation, as they gather all the
input necessary for other types of systems. Think about how one could
generate a monthly sales report for middle management or critical
marketing information to senior managers without TPS. TPS provide the
basic input to the company's database. A failure in the TPS often means

6
MBA 757 DECISION SUPPORT SYSTEM

disaster for the organisation. Imagine what happens when the

reservation system at Turkish Airlines fails: all operations stop, no
transactions can be carried out until the system is up again. Long queues
form in front of ATMs and tellers when a bank's TPS crashes.

Knowledge Work Systems (KWS) support highly skilled knowledge

workers in the creation and integration of new knowledge into the
company. Computer Aided Design (CAD) systems used by product
designers not only allow them to easily make modifications without
having to redraw the entire object (just like word processors for
documents), but also enable them to test the product without having to
build physical prototypes. Three dimensional graphical simulation
systems like GRASP (Graphical Robotics Applications Simulation
Package) are used by British Aerospace and Rolls Royce for evaluating
and programming industrial robots. Architects use CAD software to
create, modify, evaluate and test their designs; such systems can
generate photo realistic pictures, simulating the lighting in rooms at
different times of the day, perform calculations, for instance on the
amount of paint required. Surgeons use sophisticated CAD systems to
design operations.

Financial institutions are using knowledge work systems to support

trading and portfolio management with powerful high-end PC's. These
allow managers to get instantaneous analysed results on huge amounts
of financial data and provide access to external databases.

Office Automation Systems (OAS) support general office work for

handling and managing documents and facilitating communication. Text
and image processing systems evolved from word processors to desktop
publishing, enabling the creation of professional documents with
graphics and special layout features. Spreadsheets, presentation
packages like PowerPoint, personal database systems and note-taking
systems (appointment book, notepad, cardfile) are part of OAS.

In addition OAS includes communication systems for transmitting

messages and documents (e-mail) and teleconferencing capabilities.

Management Information Systems (MIS) generate information for

monitoring performance (e.g. productivity information) and maintaining
coordination (e.g. between purchasing and accounts payable).

MIS extract process and summarise data from the TPS and provide
periodic (weekly, monthly, quarterly) reports to managers.
Today MIS are becoming more flexible by providing access to
information whenever needed (rather than pre-specified reports on a
periodic basis). Users can often generate more customised reports by

7
MBA 757 DECISION SUPPORT SYSTEM

selecting subsets of data (such as listing the products with 2% increase

in sales over the past month), using different sorting options (by sales
region, by salesperson, by highest volume of sales) and different display
choices (graphical, tabular).

Decision Support Systems (DSS) support analytical work in semi-

structured or unstructured situations. They enable managers to answer
"What if?" questions by providing powerful models and tools
(simulation, optimisation) to evaluate alternatives (e.g. evaluating
alternative marketing plans).

DSS are user-friendly and highly interactive. Although they use data
from the TPS and MIS, they also allow the inclusion of new data, often
from external sources, such as current share prices or prices of
competitors.

Executive Support Systems (ESS) or Executive Information Systems

(EIS) provide a generalised computing and communication environment
to senior managers to support strategic decisions. They draw data from
the MIS and allow communication with external sources of information.
But unlike DSS, they are not designed to use analytical models for
specific problem solving. ESS are designed to facilitate senior managers'
access to information quickly and effectively.

ESS have menu driven user friendly interfaces, interactive graphics to

help visualisation of the situation, and communication capabilities that
link the senior executive to the external databases he requires (e.g. Dow
Jones News/Retrieval, or the Gallop Poll).

Figure 3: Operations and management classifications of information systems.

3.5 Relationship of Systems to One Another

8
MBA 757 DECISION SUPPORT SYSTEM

Different types of systems exist in organisations. Not all organisations

have all of the types of systems described here. Many organisations may
not have knowledge work systems, executive support systems or
decision support systems. But today most organisations make use of
office automation systems and have a portfolio of information system
applications based on TPS and MIS (marketing systems, manufacturing
systems, human resources systems). Some organisations have hybrid
information systems that contain some of the characteristics of different
types of systems.

The field of information systems is moving so quickly that the features

of one particular type of system are integrated to other types (e.g. MIS
having many of the features of ESS). System characteristics evolve and
new types of systems emerge. Yet the classification of information
systems into these different types is useful because each type of system
has certain features that are relevant in particular situations.

4.0 CONCLUSION

Though there are different perspectives to the definition of information

system, there are basic elements associated with each definition. Also,
even as the different types of information systems keep emerging as new
technologies emerge by the day, information systems are still basically
responsible for making business operations to be effective and
productive.

5.0 SUMMARY

This unit is summarised as follows:

• The term Information System (IS) sometimes refers to a system of

persons, data records and activities that process the data and
information in an organisation, and it includes the organisation's
manual and automated processes.
• Since the 1950's, the concept of information systems has evolved
from electronic accounting machines, speeding paperwork and
bureaucracy, to providing general information support in functional
areas through the generation of routine performance reports in the
1960's (early Management Information Systems).
• The structure of an information system may be visualised as
infrastructure plus applications. The applications have a conceptual
structure based on the purpose or needs being met and the functions
of the organisation that employ them.
• Information systems support different types of decisions at different
levels of the organisational hierarchy. While operational managers
mostly make structured decisions, senior managers deal with

9
MBA 757 DECISION SUPPORT SYSTEM

unstructured decisions; middle managers are often faced with semi-

structured decisions.
• Different types of systems exist in organisations. Not all
organisations have all of the types of systems described here. Many
organisations may not have knowledge work systems, executive
support systems or decision support systems.

6.0 TUTOR-MARKED ASSIGNMENT

1. Identify the basic components of information systems

2. Briefly discuss the database infrastructure of information systems

7.0REFERENCES/FURTHER READING

Angell, I.O. and Smithson S. (1991). Information Systems Management:

Opportunities and Risks.

Beynon-Davies P. (2002). Information Systems: An Introduction to

Informatics in Organisations.Palgrave, Basingstoke, UK. ISBN:
0-333-96390-3.

Federal Standard 1037C, MIL-STD-188, and National Information

Systems Security Glossary.

ION 501; Introduction to Information Systems.

O’Brien J.A.; Introduction to Information Systems, 8th Edition, ISBN:

0-256-20937-5.

Rockart et. al (1996). Eight Imperatives for the New IT Organisation

Sloan Management Review.

Sloan Career Cornerstone Center. (2008). Information Systems. Alfred

P. Sloan Foundation.

Langefors, Börje (1973). Theoretical Analysis of Information Systems,

Auerbach. ISBN 0-87769-151-7.

Ciborra, C. (2002) Labyrinths of Information. Oxford: Oxford

University Press.

Master of Science in Information Systems at the University of Münster .

UNIT 2 OVERVIEW OF DECISION SUPPORT SYSTEM

CONTENTS

10
MBA 757 DECISION SUPPORT SYSTEM

1.0 Introduction
2.0 Objectives
3.0 Main Content
3.1 What is a Decision Support System?
3.2 A Brief History
3.3 Taxonomies
3.4 Architectures
3.5 Development Frameworks
3.6 Classifying DSS
3.7 Applications
3.8 Benefits of DSS
3.9 Decision Support System versus Management Information
System
4.0 Conclusion
5.0 Summary
6.0 Tutor-Marked Assignment
7.0 References/Further Reading

1.0 INTRODUCTION

Decision Support Systems constitute a class of computer-based

information systems including knowledge-based systems that support
decision-making activities.

Decision Support Systems (DSS) are a specific class of computerised

information system that supports business and organisational decision-
making activities. A properly-designed DSS is an interactive software-
based system intended to help decision makers compile useful
information from raw data, documents, personal knowledge, and/or
business models to identify and solve problems and make decisions.

Typical information that a decision support application might gather and

present would be:

• an inventory of all of your current information assets (including

legacy and relational data sources, cubes, data warehouses, and data
marts),
• comparative sales figures between one week and the next,
• projected revenue figures based on new product sales assumptions;
• the consequences of different decision alternatives, given past
experience in a context that is described.
2.0 OBJECTIVES

At the end of this unit, you should be able to:

11
MBA 757 DECISION SUPPORT SYSTEM

• define decision support system (DSS)

• outline the history and the development process of DSS
• explain what constitutes the architecture of a typical DSS
• classify DSS into various forms
• identify the fields in which DSS are used
• state the benefits associated with the use of DSS
• compare and contrast DSS and MIS

3.0 MAIN CONTENT

3.1 What is a Decision Support System?

A decision support system is a way to model data and make quality
decisions based upon it. Making the right decision in business is usually
based on the quality of your data and your ability to sift through and
analyse the data to find trends in which you can create solutions and
strategies for. DSS or decision support systems are usually computer
applications along with a human component that can sift through large
amounts of data and pick between the many choices.

While many people think of decision support systems as a specialised

part of a business, most companies have actually integrated this system
into their day to day operating activities. For instance, many companies
constantly download and analyse sales data, budget sheets and forecasts
and they update their strategy once they analyse and evaluate the current
results. Decision support systems have a definite structure in businesses,
but in reality, the data and decisions that are based on it are fluid and
constantly changing.
The key to decision support systems is to collect data, analyse and shape
the data that is collected and then try to make sound decisions or
construct strategies from analysis. Whether computers, databases or
people are involved usually doesn't matter, however it is this process of
taking raw or unstructured data, containing and collecting it and then
using it to aid decision making.

Although computers and artificial intelligence are at work or at play

with data, it is ultimately up to humans to execute these strategies or
comprehend the data into a usable hypothesis.

It is important to note that the field of DSS does not have a universally
accepted model, meaning that there are many theories vying for
supremacy in this broad field. Because there are many working theories
on the topic of DSS, there are many ways to classify DSS.

For instance, one of the DSS models available is with the relationship of
the user in mind. This model takes into consideration passive, active and

12
MBA 757 DECISION SUPPORT SYSTEM

co-operative DSS models.

Decision support systems that just collect data and organise them
effectively are usually called passive models, they do not suggest a
specific decision, and they only reveal the data. An active decision
support system actually processes data and explicitly shows solutions
based upon that data. While there are many systems that are able to be
active, many organisations would be hard pressed to put all their faith
into a computer model without any human intervention.

A co-operative decision support system is when data is collected,

analysed and then provided with a human component which helps the
system revise or refine it. It means that both a human component and
computer component work together to come up with the best solution.

While the above DSS model takes the relationship of the user in mind,
another popular DSS model takes into consideration the mode of
assistance as the underlying basis of the DSS model. This includes the
Model Driven DSS, Communications Driven DSS, Data Driven DSS,
Document Driven DSS, and Knowledge Driven DSS.

Model Driven DSS is when decision makers use statistical, simulations

or financial models to come up with a solution or strategy. Keep in mind
that these decisions are based on models; however they do not have to
be overwhelmingly data intensive.

A Communications Driven DSS model is when many collaborators

work together to come up with a series of decisions to set in motion a
solution or strategy. This communications driven DSS model can be in
an office environment or on the web.

A Data Driven DSS model puts its emphasis on collected data that is
then manipulated to fit the decision maker's needs. This data can be
internal, external and in a variety of formats. It is important that usually
data is collected and categorised as a time series which is a collection of
data that forms a sequence, such as daily sales, operating budgets from
one quarter to the next, inventory levels over the previous year, etc.

A Document Driven DSS model uses documents in a variety of data

types such as text documents, spreadsheets and database records to
come up with decisions as well as further manipulate the information to
refine strategies.

A Knowledge Driven DSS model uses special rules stored in a

computer or used by a human to determine whether a decision should be
made. For instance, for many days, traders stop loss limit can be seen as
a knowledge driven DSS model. These rules or facts are used in order to
make a decision.

13
MBA 757 DECISION SUPPORT SYSTEM

You can also look at the scope in which decisions are made as a model
of DSS. For instance, an organisational wide decision, department
decision or single user decision, can be seen in the scope wide model.

3.2 A Brief History

In the absence of an all-inclusive definition, we focus on the history of

DSS. According to Keen, the concept of decision support has evolved
from two main areas of research: the theoretical studies of organisational
decision making done at the Carnegie Institute of Technology during the
late 1950s and early 1960s, and the technical work on interactive
computer systems, mainly carried out at the Massachusetts Institute of
Technology in the 1960s. It is considered that the concept of DSS
became an area of research of its own in the middle of the 1970s, before
gaining in intensity during the 1980s. In the middle and late 1980s,
executive information systems (EIS), group decision support systems
(GDSS), and organisational decision support systems (ODSS) evolved
from the single user and model-oriented DSS. Beginning in about 1990,
data warehousing and on-line analytical processing (OLAP) began
broadening the realm of DSS. As the turn of the millennium approached,
new Web-based analytical applications were introduced.

It is clear that DSS belong to an environment with multidisciplinary

foundations, including (but not exclusively) database research, artificial
intelligence, human-computer interaction, simulation methods, software
engineering, and telecommunications.

DSS also have a weak connection to the user interface paradigm of

hypertext. Both the University of Vermont PROMIS system (for
medical decision making) and the Carnegie Mellon ZOG/KMS system
(for military and business decision making) were decision support
systems which also were major breakthroughs in user interface research.
Furthermore, although hypertext researchers have generally been
concerned with information overload, certain researchers, notably
Douglas Engelbart, have been focused on decision makers in particular.

3.3 Taxonomies

As with the definition, there is no universally-accepted taxonomy of

DSS either. Different authors propose different classifications. Using the
relationship with the user as the criterion, Haettenschwiler differentiates
passive, active, and co-operative DSS. A passive DSS is a system that
aids the process of decision making, but that cannot bring out explicit
decision suggestions or solutions. An active DSS can bring out such
decision suggestions or solutions. A co-operative DSS allows the

14
MBA 757 DECISION SUPPORT SYSTEM

decision maker (or its advisor) to modify, complete, or refine the

decision suggestions provided by the system, before sending them back
to the system for validation. The system again improves, completes, and
refines the suggestions of the decision maker and sends them back to her
for validation. The whole process then starts again, until a consolidated
solution is generated.

Using the mode of assistance as the criterion, Power differentiates

communication-driven DSS, data-driven DSS, document-driven DSS,
knowledge-driven DSS, and model-driven DSS.

• A model-driven DSS emphasises access to and manipulation of a

statistical, financial, optimisation, or simulation model. Model-
driven DSS use data and parameters provided by users to assist
decision makers in analysing a situation; they are not necessarily
data-intensive. Dicodess is an example of an open source model-
driven DSS generator.
• A communication-driven DSS supports more than one person
working on a shared task; examples include integrated tools like
Microsoft's NetMeeting or Groove.
• A data-driven DSS or data-oriented DSS emphasises access to and
manipulation of a time series of internal company data and,
sometimes, external data.
• A document-driven DSS manages, retrieves, and manipulates
unstructured information in a variety of electronic formats.
• A knowledge-driven DSS provides specialised problem-solving
expertise stored as facts, rules, procedures, or in similar structures.

Using scope as the criterion, Power differentiates enterprise-wide DSS

and desktop DSS. An enterprise-wide DSS is linked to large data
warehouses and serves many managers in the company. A desktop,
single-user DSS is a small system that runs on an individual manager's
PC.

3.4 Architectures

Once again, different authors identify different components in a DSS.

For example, Sprague and Carlson identify three fundamental
components of DSS: (a) the database management system (DBMS), (b)
the model-base management system (MBMS), and (c) the dialogue
generation and management system (DGMS).

• Haag et al. describe these three components in more detail:

The Data Management Component stores information (which can be

further subdivided into that derived from an organisation's traditional

15
MBA 757 DECISION SUPPORT SYSTEM

data repositories, from external sources such as the Internet, or from the
personal insights and experiences of individual users); the Model
Management Component handles representations of events, facts, or
situations (using various kinds of models, two examples being
optimisation models and goal-seeking models); and the User Interface
Management Component is, of course, the component that allows a user
to interact with the system.

• According to Power , academics and practitioners have discussed

building DSS in terms of four major components: (a) the user
interface, (b) the database, (c) the model and analytical tools, and (d)
the DSS architecture and network.
• Hättenschwiler identifies five components of DSS:

(a) users with different roles or functions in the decision making

process (decision maker, advisors, domain experts, system
experts, data collectors),
(b) a specific and definable decision context,
(c) a target system describing the majority of the preferences,
(d) a knowledge base made of external data sources, knowledge
databases, working databases, data warehouses and meta-
databases, mathematical models and methods, procedures,
inference and search engines, administrative programs, and
reporting systems, and
(e) a working environment for the preparation, analysis, and
documentation of decision alternatives.

• Arakas proposes a generalised architecture made of five distinct

parts:

(a) the data management system,

(b) the model management system,
(c) the knowledge engine,
(d) the user interface, and
(e) the user(s).

3.5 Development Frameworks

DSS systems are not entirely different from other systems and require a
structured approach. A framework was provided by Sprague and Watson
(1993). The framework has three main levels:
1). Technology levels
2). People involved

16
MBA 757 DECISION SUPPORT SYSTEM

3). The developmental approach

1. Technology Levels

Sprague has suggested that there are three levels of hardware and
software that has been proposed for DSS.

a) Level 1 – Specific DSS

This is the actual application that will be used by the user. This is the
part of the application that allows the decision maker to make decisions
in a particular problem area. The user can act upon that particular
problem.

b) Level 2 – DSS Generator

This level contains hardware/software environment that allows people to

easily develop specific DSS applications. This level makes use of case
tools or systems such as Crystal, AIMMS, iThink and Clementine.

c) Level 3 – DSS Tools

Contains lower level hardware/software. DSS generators including

special languages, function libraries and linking modules .

2. People Involved

Sprague suggests that there are 5 roles involved in a typical DSS

development cycle.

a) The end user

b) An intermediary
c) DSS developer
d) Technical supporter
e) Systems expert

3. The Developmental Approach

The developmental approach for a DSS system should be strongly

interactive. This will allow for the application to be changed and
redesigned at various intervals. The initial problem is used to design the
system and then tested and revised to ensure the desired outcome is
achieved.

17
MBA 757 DECISION SUPPORT SYSTEM

3.6 Classifying DSS

There are several ways to classify DSS applications. Not every DSS fits
neatly into one category, but a mix of two or more architecture in one.

Holsapple and Whinston classify DSS into the following six

frameworks: Text-oriented DSS, Database-oriented DSS, Spreadsheet-
oriented DSS, Solver-oriented DSS, Rule-oriented DSS, and Compound
DSS.

A compound DSS is the most popular classification for a DSS. It is a

hybrid system that includes two or more of the five basic structures
described by Holsapple and Whinston .
The support given by DSS can be separated into three distinct,
interrelated categories:

Personal Support,
Group Support, and
Organisational Support

Additionally, the build up of a DSS is also classified into a few

characteristics.

1) Inputs: This is used so the DSS can have factors, numbers, and
characteristics to analyse.
2) User knowledge and Expertise: This allows the system to
decide how much it is relied on, and exactly what inputs must be
analysed with or without the user.
3) Outputs: This is used so the user of the system can analyse the
decisions that may be made and then potentially.
4) Make a Decision: This decision making is made by the DSS,
however, it is ultimately made by the user in order to decide on
which criteria it should use.

DSS which perform selected cognitive decision-making functions and

are based on artificial intelligence or intelligent agents’ technologies are
called Intelligent Decision Support Systems (IDSS)

3.7 Applications

As mentioned above, there are theoretical possibilities of building such

systems in any knowledge domain.

18
MBA 757 DECISION SUPPORT SYSTEM

One example is the Clinical decision support system for medical

diagnosis. Other examples include a bank loan officer verifying the
credit of a loan applicant or an engineering firm that has bids on several
projects and wants to know if they can be competitive with their costs.

DSS is extensively used in business and management. Executive

dashboard and other business performance software allow faster
decision making, identification of negative trends, and better allocation
of business resources.

A growing area of DSS application, concepts, principles, and techniques

is in agricultural production, marketing for sustainable development. For
example, the DSSAT4 package, developed through financial support of
USAID during the 80's and 90's, has allowed rapid assessment of several
agricultural production systems around the world to facilitate decision-
making at the farm and policy levels. There are, however, many
constraints to the successful adoption on DSS in agriculture.

A specific example concerns the Canadian National Railway system,

which tests its equipment on a regular basis using a decision support
system. A problem faced by any railroad is worn-out or defective rails,
which can result in hundreds of derailments per year. Under a DSS, CN
managed to decrease the incidence of derailments at the same time other
companies were experiencing an increase.

DSS has many applications that have already been spoken about.
However, it can be used in any field where organisation is necessary.
Additionally, a DSS can be designed to help make decisions on the
stock market, or deciding which area or segment to market a product
toward.

3.8 Benefits of DSS

1. Improves personal efficiency

2. Expedites problem solving
3. Facilitates interpersonal communication
4. Promotes learning or training
5. Increases organisational control
6. Generates new evidence in support of a decision
7. Creates a competitive advantage over competition
8. Encourages exploration and discovery on the part of the decision
maker
9. Reveals new approaches to thinking about the problem space

3.9 Decision Support System versus Management

19
MBA 757 DECISION SUPPORT SYSTEM

Information System

Sales managers typically rely on management information systems

(MIS) to produce sales analytic reports. These reports contain sales
performance figure by products line, sales person, sales region, and so
on. A decision support system (DSS), on the other hand, would also
interactively show a sales manager the effects on sales performance of
changes in a variety of factors (such as promotion expenses and sales
compensation). The DSS could then use several criteria (such as
expected gross margin and market share) to evaluate and rank several
alternative combinations of sales performance factors.

MIS DSS
DecisionSupport Provide information
Provide information
Provided about the performance of and decision support
the organisation techniques to analyse
specific problem or
opportunities
Information form Periodic, exception, Interactive enquiries
and Frequency demand, and push reports and responses
and responses
Information Pre-specified, fixed Ad hoc, flexible and
Format format adaptable format
Information Information provided by Information produced
Processing extraction and by analytic and
Methodology manipulation of business modeling of business
data. data
Figure 1: Comparing DSS and MIS

Using DSS involves an interactive modeling process. For example,

using a DSS software package for decision support may result in a series
of displays in response to alternative what-if changes entered by a
manager. This differs from the demand response of MIS, since decision
makers are not demanding pre-specified information. Rather, they are
exploring possible alternatives. Thus, they do not have to specify their
information need in advance. Instead they use a DSS to find the
information they need to help make a decision. That is the essence of
DSS concept.

4.0 CONCLUSION

Decision support systems are a form of management information

systems used by management to aid decision making process. The

20
MBA 757 DECISION SUPPORT SYSTEM

complex problems that DSS are out to solve are often very poorly
defined with a high level of uncertainty about the true nature of the
problem, the various responses which the management could undertake
or the likely impact of those actions. Many decision support systems
have been developed so that they support implementation on a wide
range of hardware.

5.0 SUMMARY

• Decision Support Systems constitute a class of computer-based

information systems including knowledge-based systems that
support decision-making activities.
• A decision support system is a way to model data and make quality
decisions based upon it. Making the right decision in business is
usually based on the quality of your data and your ability to sift
through and analyse the data to find trends in which you can create
solutions and strategies for growth.
• According to Keen, the concept of decision support has evolved
from two main areas of research: the theoretical studies of
organisational decision making done at the Carnegie Institute of
Technology during the late 1950s and early 1960s, and the technical
work on interactive computer systems, mainly carried out at the
Massachusetts Institute of Technology in the 1960s.
• As with the definition, there is no universally-accepted taxonomy of
DSS either. Different authors propose different classifications.
• Also, different authors identify different components in a DSS.
• DSS systems are not entirely different from other systems and
require a structured approach.
• There are several ways to classify DSS applications. Not every DSS
fits neatly into one category, but a mix of two or more architecture in
one.
• DSS is extensively used in business and management. Executive
dashboard and other business performance software allow faster
decision making, identification of negative trends, and better
allocation of business resources.
• Sales managers typically rely on management information systems
(MIS) to produce sales analytic reports.

6.0 TUTOR-MARKED ASSIGNMENT

1. By taxonomy, list the models of decision support system

21
MBA 757 DECISION SUPPORT SYSTEM

2. Mention 5 benefits of decision support systems

7.0 REFERENCES/FURTHER READING

Power, D. J. A May 31, (2003). Brief History of Decision Support

Systems, DSSResources.COM, World Wide Web, version 2.8.

Keen, P. G. W. (1978). Decision Support Systems: An Organisational

Perspective. Reading, Mass.: Addison-Wesley Pub. Co. ISBN
0-201-03667-3.

Haettenschwiler, P. (1999). Neues anwenderfreundliches Konzept der

Entscheidungsunterstützung. Gutes Entscheiden in Wirtschaft,
Politik und Gesellschaft. Zurich, vdf Hochschulverlag AG:
189-208.

Power, D. J. (2002). Decision Support Systems: Concepts and

Resources for Managers. Westport, Conn.: Quorum Books.

Gachet, A. (2004). Building Model-Driven Decision Support Systems

with Dicodess, Zurich, VDF.

Sprague, R. H. and E. D. Carlson (1982). Building Effective Decision

Support Systems. Englewood Cliffs: N.J., Prentice-Hall. ISBN
0-130-86215-0.

Haag, Cummings, McCubbrey, Pinsonneault, Donovan (2000).

Management Information Systems for the Information Age.
McGraw-Hill Ryerson Limited: 136-140. ISBN 0-072-81947-2.

Marakas, G. M. (1999). Decision Support Systems In The Twenty-First

Century. Upper Saddle River, N.J.: Prentice Hall.

Holsapple, C.W.; A. B. Whinston (1996). Decision Support Systems: A

Knowledge-Based Approach. St. Paul: West Publishing. ISBN:
0-324-03578-0.

Hackathorn, R. D.; P. G. W. Keen (1981, September). "Organisational

Strategies for Personal Computing in Decision Support Systems,"
MIS Quarterly, Vol. 5, No. 3.

Gadomski A. M. et al. (1998). Integrated Parallel Bottom-up and Top-

Down Approach to the Development of Agent-Based Intelligent
DSSs for Emergency Management, TIEMS98. Washington:
CiteSeerx – alfa.

22
MBA 757 DECISION SUPPORT SYSTEM

DSSAT4 (pdf) The Decision Support System for Agrotechnology

Transfer.

Stephens, W. and Middleton, T. (2002). Why has the uptake of Decision

Support Systems been so poor? In: Crop-Soil Simulation Models
in Developing Countries.

UNIT 3 DECISION THEORY AND DECISION MAKING

23
MBA 757 DECISION SUPPORT SYSTEM

CONTENTS

1.0 Introduction
2.0 Objectives
3.0 Main Content
3.1 Normative and Descriptive Decision Theory
3.2 What kinds of decisions need a theory?
3.3 Paradox of Choice
3.4 Statistical Decision Theory
3.5 Alternatives to Probability Theory
3.6 Decision Making
3.7 Overview of Decision Making
3.8 Decision Making Processes Topics
3.9 Cognitive and Personal Biases
3.10 Neuroscience Perspective
3.11 Styles and Methods of Decision Making
4.0 Conclusion
5.0 Summary
6.0 Tutor-Marked Assignment
7.0 References/Further Reading

1.0 INTRODUCTION

Decision Theory in mathematics and statistics is concerned with

identifying the values, uncertainties and other issues relevant in a given
decision and the resulting optimal decision.

2.0 OBJECTIVES

At the end of this unit, the students should be able to:

• define decision support theory

• identify different types of decision theory
• describe and differentiate normative and descriptive decision theory
• compare and contrast the two major forms of decision theory
• answer the question of what type of decision needs a theory to back
it up
• categorise styles and methods of decision making
• explain cognitive and personal biases in decision making.

3.0 MAIN CONTENT

3.1 Normative and Descriptive Decision Theory

24
MBA 757 DECISION SUPPORT SYSTEM

Most of decision theory is normative or prescriptive, i.e. it is concerned

with identifying the best decision to take, assuming an ideal decision
maker who is fully informed, able to compute with perfect accuracy, and
fully rational. The practical application of this prescriptive approach
(how people should make decisions) is called decision analysis, and
aimed at finding tools, methodologies and software to help people make
better decisions. The most systematic and comprehensive software tools
developed in this way are called decision support systems.

Since it is obvious that people do not typically behave in optimal ways,

there is also a related area of study, which is a positive or descriptive
discipline, attempting to describe what people will actually do. Since the
normative, optimal decision often creates hypotheses for testing against
actual behaviour, the two fields are closely linked. Furthermore it is
possible to relax the assumptions of perfect information, rationality and
so forth in various ways, and produce a series of different prescriptions
or predictions about behaviour, allowing for further tests of the kind of
decision-making that occurs in practice.

3.2 What Kinds of Decisions Need a Theory?

1. Choice between incommensurable commodities

2. Choice under uncertainty

This area represents the heart of decision theory. The procedure now
referred to as expected value was known from the 17th century. Blaise
Pascal invoked it in his famous wager (see below), which is contained in
his Pensées, published in 1670. The idea of expected value is that, when
faced with a number of actions, each of which could give rise to more
than one possible outcome with different probabilities, the rational
procedure is to identify all possible outcomes, determine their values
(positive or negative) and the probabilities that will result from each
course of action, and multiply the two to give an expected value. The
action to be chosen should be the one that gives rise to the highest total
expected value. In 1738, Daniel Bernoulli published an influential paper
entitled Exposition of a New Theory on the Measurement of Risk, in
which he uses the St. Petersburg paradox to show that expected value
theory must be normatively wrong. He also gives an example in which a
Dutch merchant is trying to decide whether to insure a cargo being sent
from Amsterdam to St Petersburg in winter, when it is known that there
is a 5% chance that the ship and cargo will be lost. In his solution, he
defines a utility function and computes expected utility rather than
expected financial value.

25
MBA 757 DECISION SUPPORT SYSTEM

In the 20th century, interest was reignited by Abraham Wald's 1939

paper pointing out that the two central concerns of orthodox statistical
theory at that time, namely statistical hypothesis testing and statistical
estimation theory, could both be regarded as particular special cases of
the more general decision problem. This paper introduced much of the
mental landscape of modern decision theory, including loss functions,
risk functions, admissible decision rules, a priori distributions, Bayes
decision rules, and minimax decision rules. The phrase "decision theory"
itself was first used in 1950 by E. L. Lehmann.

The rise of subjective probability theory, from the work of Frank

Ramsey, Bruno de Finetti, Leonard Savage and others, extended the
scope of expected utility theory to situations where only subjective
probabilities are available. At this time it was generally assumed in
economics that people behave as rational agents and thus expected
utility theory also provided a theory of actual human decision-making
behaviour under risk. The work of Maurice Allais and Daniel Ellsberg
showed that this was clearly not so. The prospect theory of Daniel
Kahneman and Amos Tversky placed behavioural economics on a more
evidence-based footing. It emphasised that in actual human (as opposed
to normatively correct) decision-making "losses loom larger than gains",
people are more focused on changes in their utility states than the states
themselves and estimation of subjective probabilities is severely biased
by anchoring.

Castagnoli and LiCalzi (1996), Bordley and LiCalzi (2000) recently

showed that maximising expected utility is mathematically equivalent to
maximising the probability that the uncertain consequences of a decision
are preferable to an uncertain benchmark (e.g., the probability that a
mutual fund strategy outperforms the S&P 500 or that a firm
outperforms the uncertain future performance of a major competitor.).
This reinterpretation relates to psychological work suggesting that
individuals have fuzzy aspiration levels (Lopes & Oden), which may
vary from choice context to choice context. Hence it shifts the focus
from utility to the individual's uncertain reference point.

Pascal's Wager is a classic example of a choice under uncertainty. The

uncertainty, according to Pascal, is whether or not God exists. Belief or
non-belief in God is the choice to be made. However, the reward for
belief in God if God actually does exist is infinite. Therefore, however
small the probability of God's existence, the expected value of belief
exceeds that of non-belief, so it is better to believe in God. (There are
several criticisms of the argument.)
Inter-Temporal Choice

26
MBA 757 DECISION SUPPORT SYSTEM

This area is concerned with the kind of choice where different actions
lead to outcomes that are realised at different points in time. If someone
received a windfall of several thousand dollars, they could spend it on
an expensive holiday, giving them immediate pleasure, or they could
invest it in a pension scheme, giving them an income at some time in the
future. What is the optimal thing to do? The answer depends partly on
factors such as the expected rates of interest and inflation, the person's
life expectancy, and their confidence in the pensions industry. However
even with all those factors taken into account, human behaviour again
deviates greatly from the predictions of prescriptive decision theory,
leading to alternative models in which, for example, objective interest
rates are replaced by subjective discount rates.

Competing Decision Makers

Some decisions are difficult because of the need to take into account
how other people in the situation will respond to the decision that is
taken. The analysis of such social decisions is the business of game
theory, and is not normally considered part of decision theory, though it
is closely related. In the emerging socio-cognitive engineering the
research is especially focused on the different types of distributed
decision-making in human organisations, in normal and
abnormal/emergency/crisis situations. The signal detection theory is
based on the Decision theory.

Complex Decisions

Other areas of decision theory are concerned with decisions that are
difficult simply because of their complexity, or the complexity of the
organisation that has to make them. In such cases the issue is not the
deviation between real and optimal behaviour, but the difficulty of
determining the optimal behaviour in the first place. The Club of Rome,
for example, developed a model of economic growth and resource usage
that helps politicians make real-life decisions in complex situations.

3.3 Paradox of Choice

Observed in many cases is the paradox that more choices may lead to a
poorer decision or a failure to make a decision at all. It is sometimes
theorised to be caused by analysis paralysis, real or perceived, or
perhaps from rational ignorance. A number of researchers including
Sheena S. Iyengar and Mark R. Lepper have published studies on this
phenomenon. A popularisation of this analysis was done by Barry
Schwartz in his 2004 book, The Paradox of Choice.
3.4 Statistical Decision Theory

27
MBA 757 DECISION SUPPORT SYSTEM

Several statistical tools and methods are available to organise evidence,

evaluate risks, and aid in decision making. The risks of type I and type II
errors can be quantified (estimated probability, cost, expected value, etc)
and rational decision making is improved.

One example shows a structure for deciding guilt in a criminal trial:

Actual condition
Guilty Not guilty
False Positive
(i.e. guilt
Verdict of
True Positive reported
'guilty'
unfairly)
Decision Type I error
False Negative
Verdict of (i.e. guilt
True Negative
'not guilty' not detected)
Type II error

3.5 Alternatives to Probability Theory

A highly controversial issue is whether one can replace the use of

probability in decision theory by other alternatives. The proponents of
fuzzy logic, possibility theory, Dempster-Shafer theory and info-gap
decision theory maintain that probability is only one of many
alternatives and point to many examples where non-standard alternatives
have been implemented with apparent success. Work by Yousef and
others advocate exotic probability theories using complex-valued
functions based on the probability amplitudes developed and validated
by Birkhoff and Von Neumann in quantum physics.

Advocates of probability theory point to:

• the work of Richard Threlkeld Cox for justification of the probability

axioms,
• the Dutch book paradoxes of Bruno de Finetti as illustrative of the
theoretical difficulties that can arise from departures from the
probability axioms, and
• the complete class theorems which show that all admissible decision
rules are equivalent to a Bayesian decision rule with some prior
distribution (possibly improper) and some utility function. Thus, for
any decision rule generated by non-probabilistic methods, either

28
MBA 757 DECISION SUPPORT SYSTEM

there is an equivalent rule derivable by Bayesian means, or there is a

rule derivable by Bayesian means which is never worse and (at least)
sometimes better.

3.6 Decision Making

Decision Making can be regarded as an outcome of mental processes

(cognitive process) leading to the selection of a course of action among
several alternatives. Every decision making process produces a final
choice. The output can be an action or an opinion of choice.

3.7 Overview of Decision Making

Human performance in decision making terms has been subject of active

research from several perspectives. From a psychological perspective, it
is necessary to examine individual decisions in the context of a set of
needs, preferences an individual has and values he/she seeks. From a
cognitive perspective, the decision making process must be regarded as
a continuous process integrated in the interaction with the environment.
From a normative perspective, the analysis of individual decisions is
concerned with the logic of decision making and rationality and the
invariant choice it leads to.

Yet, at another level, it might be regarded as a problem solving activity

which is terminated when a satisfactory solution is found. Therefore,
decision making is a reasoning or emotional process which can be
rational or irrational, can be based on explicit assumptions or tacit
assumptions.

Logical decision making is an important part of all science-based

professions, where specialists apply their knowledge in a given area to
making informed decisions. For example, medical decision making
often involves making a diagnosis and selecting an appropriate
treatment. Some research using naturalistic methods shows, however,
that in situations with higher time pressure, higher stakes, or increased
ambiguities, experts use intuitive decision making rather than structured
approaches, following a recognition primed decision approach to fit a
set of indicators into the expert's experience and immediately arrive at a
satisfactory course of action without weighing alternatives. Also, recent
robust decision efforts have formally integrated uncertainty into the
decision making process.

29
MBA 757 DECISION SUPPORT SYSTEM

3.8 Decision Making Processes Topics

According to behaviouralist Isabel Briggs Myers, a person's decision

making process depends on a significant degree on their cognitive style.
Myers developed a set of four bi-polar dimensions, called the Myers-
Briggs Type Indicator (MBTI). The terminal points on these dimensions
are: thinking and feeling; extroversion and introversion; judgment and
perception; and sensing and intuition. She claimed that a person's
decision making style is based largely on how they score on these four
dimensions. For example, someone who scored near the thinking,
extroversion, sensing, and judgment ends of the dimensions would tend
to have a logical, analytical, objective, critical, and empirical decision
making style.

Other studies suggest that national or cross-cultural differences exist

across entire societies. For example, Maris Martinsons has found that
American, Japanese and Chinese business leaders each exhibit a
distinctive national style of decision making.

3.9 Cognitive and Personal Biases

Some of the decision making techniques that we use in everyday life

include:

• listing the advantages and disadvantages of each option, popularised

by Plato and Benjamin Franklin
• flipping a coin, cutting a deck of playing cards, and other random or
coincidence methods
• accepting the first option that seems like it might achieve the desired
result
• prayer, tarot cards, astrology, augurs, revelation, or other forms of
divination
• acquiesce to a person in authority or an "expert"
• calculating the expected value or utility for each option.

For example, a person is considering two jobs. At the first job option the
person has a 60% chance of getting a 30% raise in the first year. And at
the second job option the person has an 80% chance of getting a 10%
raise in the first year. The decision maker would calculate the expected
value of each option, calculating the probability multiplied by the
increase of value. (0.60*0.30=0.18 [option a] 0.80*0.10=0.08 [option
b]). The person deciding on the job would choose the option with the
highest expected value, in this example option number one. An
alternative may be to apply one of the processes described below, in
particular in the Business and Management section.

30
MBA 757 DECISION SUPPORT SYSTEM

Biases can creep into our decision making processes. Many different
people have made a decision about the same question (e.g. "Should I
have a doctor look at this troubling breast cancer symptom I've
discovered?" "Why did I ignore the evidence that the project was going
over budget?") and then craft potential cognitive interventions aimed at
improving decision making outcomes.

Below is a list of some of the more commonly debated cognitive biases.

• Selective search for evidence (a.k.a. Confirmation bias in

psychology) (Scott Plous, 1993) - We tend to be willing to gather
facts that support certain conclusions but disregard other facts that
support different conclusions.
• Premature termination of search for evidence - We tend to accept the
first alternative that looks like it might work.
• Inertia - Unwillingness to change thought patterns that we have used
in the past in the face of new circumstances.
• Selective perception - We actively screen-out information that we do
not think is salient.
• Wishful thinking or optimism bias - We tend to want to see things in
a positive light and this can distort our perception and thinking.
• Choice-supportive bias occurs when we distort our memories of
chosen and rejected options to make the chosen options seem
relatively more attractive.
• Recency - We tend to place more attention on more recent
information and either ignore or forget more distant information. The
opposite effect in the first set of data or other information is termed
Primacy effect (Plous, 1993).
• Repetition bias - A willingness to believe what we have been told
most often and by the greatest number of different sources.
• Anchoring and adjustment -Decisions are unduly influenced by
initial information that shapes our view of subsequent information.
• Group thinks - Peer pressure to conform to the opinions held by the
group.
• Source credibility bias - We reject something if we have a bias
against the person, organisation, or group to which the person
belongs: We are inclined to accept a statement by someone we like.
• Incremental decision making and escalating commitment - We look
at a decision as a small step in a process and this tends to perpetuate
a series of similar decisions. This can be contrasted with zero-based
decision making.
• Attribution asymmetry - We tend to attribute our success to our
abilities and talents, but we attribute our failures to bad luck and
external factors. We attribute other's success to good luck, and their
failures to their mistakes.

31
MBA 757 DECISION SUPPORT SYSTEM

• Role fulfillment (Self Fulfilling Prophecy) - We conform to the

decision making expectations that others have of someone in our
position.
• Underestimating uncertainty and the illusion of control - We tend to
underestimate future uncertainty because we tend to believe we have
more control over events than we really do. We believe we have
control to minimise potential problems in our decisions.

3.10 Neuroscience Perspective

The anterior cingulate cortex (ACC) and orbitofrontal cortex are brain
regions involved in decision making processes. A recent neuro-imaging
study, Interactions between decision making and performance
monitoring within prefrontal cortex, found distinctive patterns of neural
activation in these regions depending on whether decisions were made
on the basis of personal volition or following directions from someone
else.

Another recent study by Kennerly, et al. (2006) found that lesions to the
ACC in the macaque resulted in impaired decision making in the long
run of reinforcement guided tasks suggesting that the ACC is
responsible for evaluating past reinforcement information and guiding
future action.

Emotion appears to aid the decision making process:

• Decision making often occurs in the face of uncertainty about

whether one's choices will lead to benefit or harm (see also Risk).
The somatic-marker hypothesis is a neurobiological theory of how
decisions are made in the face of uncertain outcome. This theory
holds that such decisions are aided by emotions, in the form of
bodily states, that are elicited during the deliberation of future
consequences and that mark different options for behaviour as being
advantageous or disadvantageous. This process involves an interplay
between neural systems that elicit emotional/bodily states and neural
systems that map these emotional/bodily states.

3.11 Styles and Methods of Decision Making

Styles and methods of decision making were elaborated by the founder

of Predispositioning Theory, Aron Katsenelinboigen. In his analysis on
styles and methods Katsenelinboigen referred to the game of chess,
saying that “chess does disclose various methods of operation, notably
the creation of predisposition—methods which may be applicable to
other, more complex systems.”[

32
MBA 757 DECISION SUPPORT SYSTEM

In his book Katsenelinboigen states that apart from the methods

(reactive and selective) and sub-methods (randomisation,
predispositioning, programming), there are two major styles – positional
and combinational. Both styles are utilised in the game of chess.
According to Katsenelinboigen, the two styles reflect two basic
approaches to the uncertainty: deterministic (combinational style) and
indeterministic (positional style). Katsenelinboigen’s definition of the
two styles are the following.

The combinational style is charaterised by:

• a very narrow, clearly defined, primarily material goal, and

• a program that links the initial position with the final outcome.

In defining the combinational style in chess, Katsenelinboigen writes:

The combinational style features a clearly formulated

limited objective, namely the capture of material (the
main constituent element of a chess position). The
objective is implemented via a well defined and in some
cases in a unique sequence of moves aimed at reaching
the set goal. As a rule, this sequence leaves no options for
the opponent. Finding a combinational objective allows
the player to focus all his energies on efficient execution,
that is, the player’s analysis may be limited to the pieces
directly partaking in the combination. This approach is
the crux of the combination and the combinational style of
play.

The positional style is distinguished by:

• a positional goal and

• a formation of semi-complete linkages between the initial step and
final outcome.

Unlike the combinational player, the positional player is

occupied, first and foremost, with the elaboration of the
position that will allow him to develop in the unknown
future. In playing the positional style, the player must
evaluate relational and material parameters as
independent variables. ( … ) The positional style gives the
player the opportunity to develop a position until it
becomes pregnant with a combination. However, the
combination is not the final goal of the positional player
—it helps him to achieve the desirable, keeping in mind a
predisposition for the future development. The Pyrrhic

33
MBA 757 DECISION SUPPORT SYSTEM

victory is the best example of one’s inability to think

positionally.

The positional style serves to:

a) create a predisposition to the future development of the position;

b) induce the environment in a certain way;
c) absorb an unexpected outcome in one’s favor;
d) avoid the negative aspects of unexpected outcomes.

The positional style gives the player the opportunity to develop a

position until it becomes pregnant with a combination. Katsenelinboigen
writes:

As the game progressed and defense became more

sophisticated the combinational style of play declined. . . .
The positional style of chess does not eliminate the
combinational one with its attempt to see the entire
program of action in advance. The positional style merely
prepares the transformation to a combination when the
latter becomes feasible.

4.0 CONCLUSION
Decision support systems do not make decisions. The objective is to
allow the manager to consider a number of alternatives and evaluate
them under a variety of potential conditions. And there are several
theories in decision making. Though these theories vary in approach to
decision making, they all have and share the same basic objective of
assisting managers to make more effective decision.

5.0 SUMMARY
• Decision Theory in mathematics and statistics is concerned with
identifying the values, uncertainties and other issues relevant in a
given decision and the resulting optimal decision.
• Most of decision theory is normative or prescriptive, i.e. it is
concerned with identifying the best decision to take, assuming an
ideal decision maker who is fully informed, able to compute with
perfect accuracy, and fully rational.
• Several statistical tools and methods are available to organise
evidence, evaluate risks, and aid in decision making.
• A highly controversial issue is whether one can replace the use of
probability in decision theory by other alternatives.

34
MBA 757 DECISION SUPPORT SYSTEM

• Decision Making can be regarded as an outcome of mental

processes (cognitive process) leading to the selection of a course of
action among several alternatives.
• Human performance in decision making terms has been subject of
active research from several perspectives. From a psychological
perspective, it is necessary to examine individual decisions in the
context of a set of needs, preferences an individual has and values
he/she seeks.
• According to behaviouralist Isabel Briggs Myers, a person's decision
making process depends on a significant degree on their cognitive
style.
• The anterior cingulate cortex (ACC) and orbitofrontal cortex are
brain regions involved in decision making processes.
• Styles and methods of decision making were elaborated by the
founder of Predispositioning Theory, Aron Katsenelinboigen.

8.0 TUTOR-MARKED ASSIGNMENT

1. Briefly discuss the Inter-temporal Choice as a kind of decision that
needs theory
2. Mention 5 decision-making techniques used in every day life

9.0 REFERENCES/FURTHER READING

James Reason (1990). Human Error. Ashgate. ISBN 1840141042.
Daniel Kahneman, Amos Tversky (2000). Choice, Values, Frames. The
Cambridge University Press. ISBN:0521621720.
Isabel Briggs Myers|Myers, I. (1962). Introduction to Type: A
Description of The Theory and Applications of the Myers-Briggs
Type Indicator, Palo Alto Ca: Consulting Psychologists Press.

Martinsons, Maris G. (August 2001). Comparing the Decision Styles of

American, Chinese and Japanese Business Leaders. Best Paper
Proceedings of Academy of Management Meetings, Washington,
DC.

Katsenelinboigen, Aron. (1997). The Concept of Indeterminism and Its

Applications: Economics, Social Systems, Ethics, Artificial
Intelligence, and Aesthetics. Praeger: Westport, Connecticut, p.6

Ulea, V. (2002). The Concept of Dramatic Genre and the Comedy of a

New Type. Chess, Literature, and Film. Southern Illinois
University Press, p.p.17-18].

35
MBA 757 DECISION SUPPORT SYSTEM

Selected Topics in Indeterministic Systems Intersystems Publications:

California, 1989, p. 21.

A New Formula for the Index of Cost of Living, 1939, in Econometrica.

Goode, Erica. (2001). In Weird Math of Choices, 6 Choices Can Beat

600. The New York Times.

36
MBA 757 DECISION SUPPORT SYSTEM

UNIT 4 TYPES OF DSS

CONTENTS

1.0 Introduction
2.0 Objectives
3.0 Main Content
3.1 Group Decision Support System
3.2 Business Intelligence
3.3 Land Allocation Decision Support System
3.4 Spatial Decision Support System
3.5 Self Service Software
3.6 Dashboards (Management Information Systems)
4.0 Conclusion
5.0 Summary
6.0 Tutor-Marked Assignment
7.0 References/Further Reading

1.0 INTRODUCTION

There are several types of decision support systems and many more are
emerging. This goes to show the dynamic nature of the concept of
decision support systems. In this unit we shall examine the various types
of decision support systems and their applications.

2.0 OBJECTIVES

At the end of this unit, the students should be able to:

• identify and define the major types of decision support system (DSS)
• understand the applications of the different types of DSS
• compare and contrast the forms of DSS
• understand the concept behind each type of DSS
• appreciate the workings of some of the DSS such as the spatial
Decision Support System
• trace the history and development processes of some of the DSS.

3.0 MAIN CONTENT

3.1 Group Decision Support System

This is an interactive computer-based system that facilitates users

finding (partial) solutions to semi-structured problems. A GDSS uses a
set of decision makers working together as a group.

37
MBA 757 DECISION SUPPORT SYSTEM

Technical developments in electronic communication, computing, and

decision support, coupled with new interest on the part of organisations
to improve meeting effectiveness, are spurring research in the area of
group decision support systems (GDSS). A GDSS combines
communication, computing, and decision support technologies to
facilitate formulation and solution of unstructured problems by a group
of people. This unit presents a conceptual overview of GDSS based on
an information-exchange perspective of decision making. Three levels
of systems are described, representing varying degrees of intervention
into the decision process. Research on GDSS is conceived as evolving
over time from the study of simple "shell" systems, consisting of menus
of features, available for selection by a group, to consideration of
sophisticated rule-based systems that enable a group to pursue highly
structured and novel decision paths. A multi-dimensional taxonomy of
systems is proposed as an organizing frame- work for research in the
area. Three environmental contingencies are identified as critical to
GDSS design: group size, member proximity, and the task confronting
the group. Potential impacts of GDSS on group processes and outcomes
are discussed, and important constructs in need of study are identified.

Group Decision Support System Application

The first example or application for a groupware is GDSS, which stands

for Group Decision Support System. There is such a GDSS system
supported by the Faculty of Management at the University of Arizona.
This kind of same-time-same-place conference is oriented toward
business meetings and decision making.

The GDSS started originally from the Management Information System

at University of Arizona. Some kind of problems has always been
observed that are associated more with large meetings than with small
meetings. By large meetings we mean meetings with generally more
than 15 participants, but can go much beyond that, e.g. 40 or even 50.
Some of the identified problems are:

•time consuming;
•dominance over the meeting; and
•honesty and participation.

However, it is important to note that we are not trying to say that small
meetings do not have the above problems; these problems mentioned
exist in every kind of meetings, but we are just trying to stress that they
are more commonly found in large meetings. Small meetings tend to be
more easily controlled than large meetings.

38
MBA 757 DECISION SUPPORT SYSTEM

In a GDSS environment, there is usually a big room with something like

40 seats, which means that 40 people can be at the meeting at any one
time. There are not only 40 seats but also 40 microcomputers. This
enables every participant to have the use of one microcomputer during
the course of the meeting. The reason why each participant needs a
microcomputer depends on how GDSS works.

In the GDSS, with special computer software, the facilitator of each

meeting will first make the agenda of the meeting, which will be
projected on to a big screen that everyone can see. The participants will
type simultaneously their ideas of the topic of discussion on the
individual microcomputers next to them. The computer will then sort the
ideas, and the participants will then vote or comment on which ideas
they like or dislike. In the course of the whole meeting, GDSS stores,
categorises and prints out all the ideas, comments and vote tallies, so
that each of the meeting participants will get a summary of the meeting
when it ends.

What is so special about GDSS is that it enables meeting participants to

simultaneously "talk", when the computer sorts and sends ideas to each
of the terminal, all at the same time. That saves a tremendous amount of
time, because all these are done electronically instead of manually, and
the time saved will enable participants to spend more time manipulating
and expressing their ideas. This can consequently increase the
productivity and efficiency of the group. The time-saving benefit also
has an added bonus: when productivity and efficiency in meetings
increase, it is likely that the team spirit can be consolidated, resulting in
an increase of the strength of binding among team members.

Besides, under this GDSS, no one can dominate the meeting. This is
because of another feature of GDSS. GDSS provides an anonymous
scheme, so that whatever you type in the terminal (i.e. your opinion)
will be protected. Under this circumstance, no one really knows who is
typing what. Because of this, not a single person can dominate the
meetings. In the worst case, we might say "some ideas" are dominating
the meeting, but this is perfectly fine because this is as a matter of fact
an aim of the GDSS: to help meeting participants voice their opinions
from an idea-oriented mindset. For example, simply because you have a
prejudice against person A does not mean that you are going to reject
the idea being proposed in the meeting, because you do not know who is
proposing that idea!!

Besides, this anonymity scheme will also help those team members who
are shy to voice opinions. And with the anonymity, people are likely to
be more honest, just as you will say more, and more honestly on the
professor's evaluation form if you know whatever you write will not

39
MBA 757 DECISION SUPPORT SYSTEM

affect your final grade on the course. This, of course, is because you
know you do not have to worry about the consequences.

However, whether this anonymity is good or not can be very

controversial. The success of meetings supported by GDSS depends
largely on the conduct of the participants. If people are taking advantage
of the anonymity system by typing obscene words or foul languages,
this system may be banned for the good of the organisation.

3.2 Business Intelligence

Business Intelligence (BI) refers to technologies, applications and

practices for the collection, integration, analysis, and presentation of
business information and sometimes to the information itself. The
purpose of business intelligence--a term that dates at least to 1958--is to
support better business decision making. Thus, BI is also described as a
decision support system (DSS).

BI is sometimes used interchangeably with briefing books, report and

query tools and executive information systems. In general, business
intelligence systems are data-driven DSS.

BI systems provide historical, current, and predictive views of business

operations, most often using data that has been gathered into a data
warehouse or a data mart and occasionally working from operational
data. Software elements support the use of this information by assisting
in the extraction, analysis, and reporting of information. Applications
tackle sales, production, finance, and many other sources of business
data for purposes that include, notably, business performance
management. Information may be gathered on comparable companies to
produce benchmarks.

History

Prior to the start of the Information Age in the late 20th century,
businesses had to collect data from non-automated sources. Businesses
then lacked the computing resources necessary to properly analyse the
data, and as a result, companies often made business decisions primarily
on the basis of intuition.

As businesses automated systems the amount of data increased but its

collection remained difficult due to the inability of information to be
moved between or within systems. Analysis of information informed for
long-term decision making, but was slow and often required the use of
instinct or expertise to make short-term decisions. Business intelligence
was defined in 1958 by Hans Peter Luhn who wrote that, “business is a

40
MBA 757 DECISION SUPPORT SYSTEM

collection of activities carried on for whatever purpose, be it science,

technology, commerce, industry, law, government, defense, et cetera”.
The communication facility serving the conduct of a business (in the
broad sense) may be referred to as an intelligence system. The notion of
intelligence is also defined here, in a more general sense, as "the ability
to apprehend the interrelationships of presented facts in such a way as
to guide action towards a desired goal."

In 1989 Howard Dresner, later a Gartner Group analyst, popularised BI

as an umbrella term to describe "concepts and methods to improve
business decision making by using fact-based support systems." In
modern businesses the use of standards, automation and specialised
software, including analytical tools, allows large volumes of data to be
extracted, transformed, loaded and warehoused to greatly increase the
speed at which information becomes available for decision-making.

Key Intelligence Topics

Business intelligence often uses key performance indicators (KPIs) to

assess the present state of business and to prescribe a course of action.
Examples of KPIs are things such as lead conversion rate (in sales) and
inventory turnover (in inventory management). Prior to the widespread
adoption of computer and web applications, when information had to be
manually inputed and calculated, performance data was often not
available for weeks or months. Recently, banks have tried to make data
available at shorter intervals and have reduced delays. The KPI
methodology was further expanded with the Chief Performance Officer
methodology which incorporated KPIs and root cause analysis into a
single methodology.

Businesses that face higher operational/credit risk loading, such as credit

card companies and "wealth management" services, often make KPI-
related data available weekly. In some cases, companies may even offer
a daily analysis of data. This fast pace requires analysts to use IT
systems to process this large volume of data.

3.3 Land Allocation Decision Support System

LADSS or Land Allocation Decision Support System is an
agricultural land use planning tool being developed at The Macaulay
Institute.

LADSS is implemented using the programming language G2 from

Gensym alongside a Smallworld GIS application using the Magik
programming language and an Oracle database. LADSS models crops
using the CropSyst simulation model. LADSS also contains a livestock
model plus social, environmental and economic impact assessments.

41
MBA 757 DECISION SUPPORT SYSTEM

LADSS has recently been used to address climate change issues

affecting agriculture in Scotland and Italy. Part of this work has
involved the use of General Circulation Models (also known as Global
climate models) to predict future climate scenarios. Other recent work
has been a study into how Common Agricultural Policy reform will
affect the uplands of Scotland, an assessment of agricultural
sustainability and for rural development research within the AGRIGRID
project.

3.4 Spatial Decision Support System

Spatial Decision Support Systems (SDSS) developed in parallel with
the concept of Decision Support Systems (DSS).

An SDSS is an interactive, computer-based system designed to support a

user or group of users in achieving a higher effectiveness of decision
making while solving a semi-structured spatial problem. It is designed to
assist the spatial planner with guidance in making land use decisions.
For example, when deciding where to build a new airport many
contrasting criteria, such as noise pollution vs employment prospects or
the knock on effect on transportation links, which make the decision
difficult. A system which models decisions could be used to help
identify the most effective decision path.

An SDSS is sometimes referred to as a Policy Support System.

A spatial decision support system typically consists of the following
components.

1. A database management system - This system holds and handles the

geographical data. A standalone system for this is called a
Geographical Information System, (GIS).
2. A library of potential models that can be used to forecast the possible
outcomes of decisions.
3. An interface to aid the users’ interaction with the computer system
and to assist in analysis of outcomes.

This concept fits dialog, data and modelling concepts outlined by

Sprague and Watson as the DDM paradigm.

How does an SDSS work?

An SDSS usually exists in the form of a computer model or collection of

interlinked computer models, including a land use model. Although
various techniques are available to simulate land use dynamics, two
types are particularly suitable for SDSS. These are Cellular Automata
(CA) based models and Agent Based Models (ABM).

42
MBA 757 DECISION SUPPORT SYSTEM

An SDSS typically uses a variety of spatial and non-spatial information,

like data on land use, transportation, water management, demographics,
agriculture, climate or employment. By using two (or, better, more)
known points in history the models can be calibrated and then
projections into the future can be made to analyse different spatial
policy options. Using these techniques spatial planners can investigate
the effects of different scenarios, and provide information to make
informed decisions. To allow the user to easily adapt the system to deal
with possible intervention possibilities an interface allows for simple
modification to be made.

Examples where an SDSS has been used

Community Viz

Community Viz is a land-use planning SDSS that works as an extension

to ArcGIS Geographic Information System software produced by ESRI.
It uses a scenario planning approach and calculates economic,
environmental, social and visual impacts and indicators dynamically as
users explore alternatives. Interactive 3D models and various tools for
public participation and collaboration are also included. It has been
commercially available since 2001.

Environment Explorer

The Environment Explorer (LOV) is a spatial, dynamic model, in which

land use and the effects on social, economic and ecological indicators
are modelled in an integrated way. Its primary goal is to explore future
developments, combining autonomous developments with alternative
policy options, in relation to the quality of the environment in which
inhabitants of the Netherlands live, work and recreate. Various policy
options from governmental departments are translated into a spatial,
dynamic image of the Netherlands future with respect to issues such as:
economic activity, employment, social well-being, transportation and
accessibility, and the natural environment. The model covers the whole
of The Netherlands.

LUMOCAP

LUMOCAP aims at delivering an operational tool for assessing land use

changes and their impact on the rural landscape according to a Common
Agricultural Policy (CAP) orientation. It focuses on the relations
between the CAP and landscape changes and emphasises the spatio-
temporal dimension of the former. The core of the tool is a dynamic
Cellular Automata based land use model. Current usage areas - Poland
(2 areas), Germany / The Netherlands (1 cross border area)

43
MBA 757 DECISION SUPPORT SYSTEM

MOLAND

The aim of MOLAND is to provide a spatial planning tool that can be

used for assessing, monitoring and modelling the development of urban
and regional environments. The project was initiated in 1998 (under the
name of MURBANDY – Monitoring Urban Dynamics) with the
objective to monitor the developments of urban areas and identify trends
at the European scale. The work includes the computation of indicators
and the assessment of the impact of anthropogenic stress factors (with a
focus on expanding settlements, transport and tourism) in and around
urban areas, and along development corridors. Models now covering 23
European cities (map)

MURBANDY

The overall objective of MURBANDY is to provide datasets to study

past and current land uses, to develop an Earth Observation based
procedure to monitor the dynamics of European cities; to develop a
number of "urban" and "environmental" indicators that allow to
understand these dynamics and the impact these cities have on the
environment, and finally to elaborate scenarios of urban growth. Initially
this project covered 5 European cities, but the project has expanded into
the MOLAND project.

Zer0-M

Zer0-M aims at concepts and technologies to achieve optimized close-

loop usage of all water flows in small municipalities or settlements (e.g.
tourism facilities) not connected to a central wastewater treatment - the
Zero Outflow Municipality (Zer0-M).

3.5 Self Service Software

Self Service Software is a subset within the Knowledge Management

software category and which contains a range of software that
specialises in the way information, process rules and logic are collected,
framed within an organised taxonomy, and accessed through decision
support interviews. Self-service software allows people to secure
answers to their inquiries and/or needs through an automated interview
fashion instead of traditional search approaches.

Self Service Software Functionality

Self service software allows authors (typically subject matter experts) to

readily automate the deployment of, the timeliness of, and compliance

44
MBA 757 DECISION SUPPORT SYSTEM

around a variety of processes with which they are involved in

communicating without having to physically address the questions,
needs, and solicitations of end users who are inquiring about the
particular process being automated.

Self service software primarily addresses closed-loop inquiries whereby

the author emulates a variety of known (finite) questions and related
(known) responses on hand or required steps that must be addressed to
derive and deliver a final answer or directive. Often the author using
such software codifies such known processes and steps then generates
(publishes) end-user facing applications which can encompass a variety
of code bases and platforms.

Self service software is sometimes referred to as decision support

software and even expert systems. It is typically categorised as a sub-
topic within the knowledge management software category. Self service
software allows individuals and companies alike to tailor and address
customer support, technical support and employee support inquiries and
needs in an on-demand fashion where the person with a question (need)
can interface with the author's generated application via a computer, a
handheld device, a kiosk, register, or other machine type to secure their
answers as if they were directly interacting (talking to) with the author.

3.6 Dashboards (Management Information Systems)

In management information systems, a dashboard is an executive
information system user interface that (similar to an automobile's
dashboard) is designed to be easy to read. For example, a product might
obtain information from the local operating system in a computer, from
one or more applications that may be running, and from one or more
remote sites on the Web and present it as though it all came from the
same source.

Types of Dashboards

45
MBA 757 DECISION SUPPORT SYSTEM

Dashboard of Sustainability screen shot illustrating example dashboard

layout. (Sentence is hanging)

Digital dashboards may be laid out to track the flows inherent in the
business processes that they monitor. Graphically, users may see the
high-level processes and then drill down into low level data. This level
of detail is often buried deep within the corporate enterprise and
otherwise unavailable to the senior executives.

Three main types of digital dashboard dominate the market today: stand
alone software applications, web-browser based applications, and
desktop applications also known as desktop widgets. These latter would
be driven by a Widget engine.

Specialised dashboards may track all corporate functions. Examples

include human resources, recruiting, sales, operations, security,
information technology, project management, customer relationship
management and many more departmental dashboards.

Digital dashboard projects involve business units as the driver and the
information technology department as the enabler. The success of digital
dashboard projects often relies on the correct selection of metrics to
monitor. Key performance indicators, balanced scorecards, sales
performance figures — these are just some of the content appropriate on
business dashboards.

Interface Design Styles

To some extent, most graphical user interfaces (GUIs) resemble an

automobile dashboard. Although a computer dashboard is more likely to
be interactive than an automobile dashboard, some product developers
consciously employ this metaphor (and sometimes the term) in the
interface design so that the user instantly recognises the similarity. Some
products that aim to integrate information from multiple components

46
MBA 757 DECISION SUPPORT SYSTEM

into a unified display refer to themselves as dashboards. Based on the

metaphor of the instrument panel in a car, the computer, or "digital"
version of a dashboard provides a business manager with the input
necessary to "drive" the business. Highlights with colors similar to
traffic lights, alerts, drill-downs, summaries, and graphics such as bar
charts, pie charts, bullet graphs, sparklines and gauges are usually set in
a portal-like environment that is often role-driven and customisable.

History

Historically, the idea of digital dashboards follows the work in the 1970s
with the study of decision support systems. In the late 1990s with the
surge of the web, digital dashboards as we know them today began
appearing. Many systems were developed in-house by organisations to
consolidate and display data already being gathered in various
information systems throughout the organisation. Today, digital
dashboard technology is available "out-of-the-box" with many software
providers on the scene. Certain companies however still continue to do
in-house development and maintenance of dashboard applications. For
example, GE Aviation has developed a proprietary software/portal
called "Digital Cockpit" to monitor the trends in aircraft spare parts
business.

Benefits of Digital Dashboards

Most organisations have various departments all contributing to its

overall success and thus it is important to be able to assess the progress
of each department. Digital dashboards, which are a type of executive
information system, allow managers to do just that. To gauge exactly
how well an organisation is performing overall, digital dashboards allow
you to capture and report specific data points from each department
within the organisation, thus providing a "snapshot" of performance.

Some benefits of using digital dashboards include:

• visual presentation of performance measures

• ability to identify and correct negative trends.
• measures efficiencies/inefficiencies.
• ability to generate detailed reports showing new trends.
• increases productivity
• ability to make more informed decisions based on collected BI
(business intelligence)
• aligns strategies and organisational goals.
• saves time over running multiple reports
•

47
MBA 757 DECISION SUPPORT SYSTEM

4.0 CONCLUSION
As there are several field in human endeavour so are there likely to be
models and types of decision making systems. Aside from generalised
decision support systems applicable to all, there are very specific
decision support systems that address a particular subject or discipline.
These types and models commonly have their strengths and weaknesses,
but they all have the same concept of presenting a decision maker with
variety of decisions to choose from based on the individual need of the
managers.

48
MBA 757 DECISION SUPPORT SYSTEM

5.0 SUMMARY
• A GDSS is an interactive computer-based system that facilitates
users finding (partial) solutions to semi-structured problems. A
GDSS uses a set of decision makers working together as a group.
• Business Intelligence (BI) refers to technologies, applications and
practices for the collection, integration, analysis, and presentation of
business information and sometimes to the information itself.
• LADSS or Land Allocation Decision Support System is an
agricultural land use planning tool being developed at The Macaulay
Institute.
• Spatial Decision Support Systems (SDSS) is developed in parallel
with the concept of Decision Support Systems (DSS).An SDSS is an
interactive computer.
• Self Service Software (SSS) is a subset within the Knowledge
Management software category and which contains a range of
software that specialises in the way information, process rules and
logic are collected, framed within an organised taxonomy, and
accessed through decision support interviews.
• In management information systems, a dashboard is an executive
information system user interface that (similar to an automobile's
dashboard) is designed to be easy to read.

6.0 TUTOR-MARKED ASSIGNMENT

Mention 5 types of decision support systems.

7.0 REFERENCES/FURTHER READING

Bontis, N., Dragonetti, N., Jacobsen, K. and G. Roos. (1999). The

Knowledge Toolbox: A Review Of The Tools Available To
Measure And Manage Intangible Resources, European
Management Journal, 17, 4, 391-402. 1.

D. J. Power (2007-03-10). A Brief History of Decision Support Systems,

version 4.0. DSSResources.COM.

H. P. Luhn (October 1958). A Business Intelligence System (PDF). IBM

Journal.

Dictionary definition of dashboards, contributed by Matt Sorenson,

SearchCIO.com, 25 February 2002. Retrieved: 9 February 2008.

Few, Stephen (2006). Information Dashboard Design. O'Reilly. ISBN

978-0-596-10016-2.
UNIT 5 DECISION SUPPORT IN E-BUSINESS

49
MBA 757 DECISION SUPPORT SYSTEM

CONTENTS

1.0 Introduction
2.0 Objectives
3.0 Main Content
3.1 E-Business Decision Support Trend
3.2 Case Study: Target Corporation E-Business Decision
Support System
3.3 Information, Decisions and Management
3.4 Decision Structure
3.5 Using Decision Support System
3.6 Creating Effective Decision Support System
4.0 Conclusion
5.0 Summary
6.0 Tutor-Marked Assignment
7.0 References/Further Reading

1.0 INTRODUCTION

To succeed in e-business and e-commerce, companies need information

systems that can support the diverse information and decision-making
needs of the mangers and business professionals.

2.0 OBJECTIVES

At the end of this unit, the students should be able to:

• link the concept of e-business and decision support systems

• identify the major e-business decision support applications that are
being customised, personalised, and web-enabled for use in e-
business and e-commerce
• use a case study to illustrate the application of decision support
system on e-business
• identify the major structure and corresponding characteristic of
information
• use decision support system in e-business
• describe how to create an effective decision support system for e-
business
• explain the relationship between information, decision and
management.

3.0 MAIN CONTENT

50
 MBA 757 DECISION SUPPORT SYSTEM

3.1 E-Business Decision Support Trend

Using information systems to support business decision-making has

been one of the primary thrusts of the business use of information
technology. However, the e-commerce revolution spawned by the
Internet and the World Wide Web is expanding the information and
decision-support uses, and expectations of many companies’s
employees, managers, customers, suppliers and other business partners.
But these changes were noticed even earlier, as both academic
researchers and business practitioners began reporting that the
traditional managerial focus originating in classic MIS (1950s), DSS
(1970s) and EIS (1980s) was expanding. The fast pace of new
information technologies like personal computer hardware and software
suites, client/server networks and networked PC versions of DSS/EIS
software made decision support available to lower levels of management
as well as non-managerial individuals and self-directed teams of
business professionals.

This trend has accelerated with Internet and e-commerce revolutions,

and the dramatic growth in Intranets and Extranets that internetworked
e-business enterprises and their stakeholders. Figure 1 illustrates that all
e-commerce participants expect easy and instant access to information
and Web-enabled self-service data analysis. Internetworked e-business
enterprises are responding with a variety of personalised and proactive
Web-based analytic technologies to support the decision-making
requirement of all their stakeholders.

E-Commerce Value E-Business Decision

Requirement Support Response

Info at Your Finger Tips Personalised Proactive

Do-it-Yourself Decision Analysis and Web
Data Analysis Distribution

Figure 1: An E-Business Meeting the information and Data Needs

Source: Adapted from Ravi Kalakota and Marcia Robinson, E-Business
Roadmap for Success.

Note: An e-business enterprise must meet the information and data analysis
requirements of customers and companies in e-commerce with more
personalised and proactive Web-based decision support.

51
MBA 757 DECISION SUPPORT SYSTEM

Thus, the growth of corporate intranets, extranets, as well as the Web

has accelerated development and use of “economic class” information
delivery and decision support software tools by lower level of
management and by individuals and teams of business professionals. In
addition, the dramatic expansion of e-commerce has opened the door to
the use of e-business DSS tools by the suppliers, customers, and other
business stakeholders of many companies from customer relationship
management, supply and chain management and other e-business
applications.

Figure 2 highlights several of the major e-business Decision Support

applications that are being customised, personalised, and Web-enabled
for use in e-business and e-commerce

Figure 2: Examples of E-Business Decision Support Applications

available to managers, employees, customers, suppliers, and other
business partners of e-business enterprise.

Supply
Chain
Management
Enterprise
Customer Performance
Relations Monitoring
Management Employee/Manager/
Customer/Partner

Knowledge/Innovatio Simulation What-If

n Management Scenario Analysis

Source: Adapted from Ravi Kalakota and Marcia Robinson, E-

Business Roadmap for Success.

52
MBA 757 DECISION SUPPORT SYSTEM

3.2 Case Study: Target Corporation E-Business Decision

Support System

Target Corporation’s Decision Support System (DSS) is composed of

several applications known as Decision Maker’s Workbench, which use
Decision Suite and WebOLAP Software from Information Advantage.
The DSS and Target’s corporate intranet supports more than 1,700
active users creating more than 60,000 ad-hoc online processing
(OLAP) reports each month. During the Christmas seasons, more than
20,000 analytic OLAP reports are produced each day by integrating the
Web with its corporate data warehouse to monitor the sales and
performance of their own products via secure extranet links across the
Internet.

With the Target Store systems complete, the corporation has

standardised it as a model for the entire company. Already the
standardised warehouse has enabled Target Corporation to obtain more
accurate data on how items are performing across divisions, across the
company. This has improved vendor negotiations considerably by
enabling the different divisions to consolidate orders and receive a better
price. The standardised DSS applications also allow for cross
referencing of fashion trend across divisions, and they have helped
validate merchandizing hunches through analysis of cross-company
data.

3.3 Information, Decisions and Management

Figure 3 emphasises that the type of information required by decision

makers in a company is directly related to the level of management
decision-making and the amount of structure in the decision situation
they face. You should realise that the framework of the classic
managerial pyramid shown in figure 3 applies in even today’s
downsized organisations and flattened or non-hierarchical
organisational structures. Levels of management decision making still
exists, but their sizes, shape and participants continue to change as
today’s fluid organisational structure evolves. Thus the levels of
managerial decision making development that must be supported by
information technology in a successful organisation are:

• Strategic Management: Typically, a board of directors and an

executive committee of the CEO and top executives develop overall
original goals, strategies, policies and objectives as part of a strategic
planning process. They also monitor the strategic performance of the
organisation and its overall direction in the political, economic, and
competitive business environment.

53
MBA 757 DECISION SUPPORT SYSTEM

• Tactical Management: Increasingly, business professionals in self-

directed teams, as well as business unit’s managers develop their
short-based and medium-range plans, schedules, and budgets and
specify the policies, procedures, and business objectives for their
subunits of the company. They also allocate resources and monitor
the performance of their organisational sub units, including
departments, divisions, process teams, project teams, and other
workgroups.

• Operational Management: The members of self-directed teams or

operating managers develop short-range plans such as weekly
production schedules. They direct the use of resources and the
performance of the tasks according to the procedures and within
budgets and schedules they established for the team and other
workgroups of the organisation.

3.4 Decision Structure

Decisions made at the operational management level tend to more

structure, those at tactical level more semi-structured, and those at the
strategic management level more unstructured. Structured decisions
involve situations where the procedures to follow when a decision is
needed can be specified in advance. The inventory reorder decisions
faced by most business are a typical example. Unstructured decisions
involve decisions where it is not possible to specify in advance most of
the decisions and procedures to follow. At most, many decision
situations are semi-structured. That is, some decision procedures can be
pre-specified, but not enough to lead to a definite recommendation
decision. For example, decisions involved in the starting of a new line of
e-commerce services or making major changes to employee benefits
would probably range from unstructured to semi-structured. Figure 4
provides a variety of examples of business decisions by type of decision
structured and level of management.

54
MBA 757 DECISION SUPPORT SYSTEM

Figure 3: Information Requirement for Decision Makers

Therefore, information systems must be designed to produce a variety of

products to meet the changing needs of decision makers throughout an
organisation. For example, decision makers at the strategic management
levels require more summarised adhoc, unscheduled reports, forecasts,
and external intelligence to support their more unstructured planning
and policy-making responsibilities. Decision makers at the operational
management level, on the other hand, may require more pre-specified
internal reports emphasising detailed current and historical data
comparison that support their more structured responsibilities on day-to-
day operations.

55
MBA 757 DECISION SUPPORT SYSTEM

Decision Operational Tactical Strategic

Structure Management Management Management
Unstructured • Cash • Business • New e-commerce
Managemen Process initiative
t reengineering • Company
• Workgroup organisation
performance
analysis
Semi-Structured • Credit • Employee • Product Planning
Managemen performance • Merger &
t appraisal Acquisition
• Production • Capital • Site Location
Schedule Budgeting
• Daily Work • Program
Assignment Budgeting
Structured • Inventory • Program
Control Control
Figure 4 Examples of Business Decisions by Type of Decision

3.5 Using Decision Support System

Typically, the four major options used in decision support systems are:

1. Analytic models
2. Specialised Databases like data warehouse
3. Decision-Makers own insights and judgments
4. An Interactive Computer-based modelling process to support the
making of semi-structured and unstructured decisions.

Of the four major options above, using one of the option, that is, the
analytic modelling, also involves four basic activities:

• What-If Analysis
• Sensitivity Analysis
• Goal Seeking Analysis
• Optimisation Analysis

What-If Analysis

In What-if analysis, an end user makes changes to variables, or

relationships among variables, and observes the resulting changes in the
value of other variables. For example, if you are using a spreadsheet,
you might change a revenue amount (variable) or a tax rate formula (a
relationship among variables) in a simple financial spreadsheet model.
Then you could command the spreadsheet program to instantly
recalculate all affected variables in the spreadsheet. A managerial user

56
MBA 757 DECISION SUPPORT SYSTEM

would be very interested in observing and evaluating changes that

occurred to the value of the spreadsheet, especially to a variable such as
net profit after taxes. To many managers, net after tax is an example of
the bottom line, that is, a key factor in making many types of decisions.
This type of analysis would be repeated until the manager was satisfied
with what the results revealed about the effects of various possible
decisions.

Sensitivity Analysis

This is a special case of What-If Analysis. Typically the value of only

one variable is changed repeatedly, and the resulting changes on other
variables are observed. So sensitivity analysis is really a case of What-If
Analysis involving repeated changes to only one variable at a time.
Some DSS packages automatically make repeated changes to a variable
when asked to perform sensitivity analysis. Typically sensitivity
analysis is used when decision makers are uncertain about the
assumptions made in estimating the value of certain key variables.

Goal-Seeking Analysis

This reverses the direction of the analysis done in What-If and

sensitivity analysis. Instead of observing how changes in the variable
affect other variables, goal-seeking analysis (also called How Can
analysis) sets a target value (a goal) for a variable and then repeatedly
changes other variables until the target value is achieved. For example,
you could specify a target value (goal) of $2 million for net profit after
taxes from a business venture. Then you could repeatedly change the
value of revenue or expenses in a spreadsheet model until a result of $2
million is achieved. Thus, you would discover what amount of revenue
level or level of expenses the business venture needs to achieve in order
to reach the goal of $2 million in after tax profits. This form of
analytical modeling would help answer the questions: “How can we
achieve $2million in net profit after taxes?” instead of the question
“What happens if we change revenue or expenses?”. Thus goal-setting
analysis is another important method of decision support.

Optimisation Analysis

This is a more complex extension of goal seeking analysis instead of

setting a specific target value for a variable, the goal is to find the
optimisation value for one or more target variables, given certain
constraints. Then one or more other variables are changed repeatedly,
subject to the specific constraints, until the best value for the target
variables are discovered. For example, you could try to determine the
highest possible level of profit that could be achieved by varying the
values for selected revenue resources and expense categories. Changes

57
MBA 757 DECISION SUPPORT SYSTEM

to such variables could be subject to constraints such as limited capacity

of the production process or limits to variable financing. Optimisation
typically is accomplished by special-purpose software packages for
optimisation techniques such as linear programming or by advance
decision support system generators.

3.6 Creating Effective Decision Support System

The concept of an interactive computer-based system that helps
companies make better business decisions has been around since
computers came into widespread use.

The vision is deceptively simple. Companies take advantage of in-depth

reporting tools and predictive models to analyse data and learn what
happened in their business, why it happened and, eventually, what will
happen. This yields a deep, fact-based understanding that complements
experience and intuition and leads to exemplary decision-making and
dramatic competitive advantage.

Types of Analytic Examples and Activities

Modeling
What-If-Analysis Observing how changes to selected variables
affect other variables
Example: What if we cut advertising by 10%?
What would happen to sales
Sensitivity Analysis Observing how repeated changes to a single
variable affect other variables
Example: Let’s cut advertisement by $100
repeatedly so we can see its relationship to sales
Goal-Seeking Analysis Making repeated changes to selected variables
until a chosen variable reaches a target value
Example: Let’s try increases in advertisement
until sales reaches $1 million
Optimisation Analysis Finding an optimum value fro selected variables,
given certain constraints.
Example: What’s the best amount of
advertisement to have, given our budget and
choice of media.
Figure 5: Activities and Examples of the Major Types of Analytic
Modeling

While this sounds simple, in reality there are a number of pitfalls that
can complicate the implementation of a decision support system (DSS).
Nevertheless, a number of innovative companies have avoided the
pitfalls by understanding that creation of a successful data-driven DSS
requires three essential elements: first, a process that carefully gauges

58
MBA 757 DECISION SUPPORT SYSTEM

the short- and long-term decision support needs of the business and what
is required to meet those needs; second, a flexible, step-by-step plan for
growth; and, third, a centralised data warehouse that can deliver a single,
comprehensive, and up-to-date picture of the enterprise that all levels of
the organisation can access as needed.
Defining the Business Needs
The process begins with an analysis aimed at precisely defining the
business challenge(s) that your DSS will address both in the short- and
long-term.
After identifying all the areas that might benefit from improved decision
support, you must then prioritise. For example, you may recognise that
your marketing department has delivered solid results for its direct
marketing programmes. How can you maintain or boost the direct
marketing programme's success while lowering the cost? The data-
driven DSS enables you to cost effectively target customers that are
most likely to respond. It helps you more clearly understand the
customers you have been targeting, the customers you need to target
(perhaps broken down by geography and demographics), and what you
can change to improve the targeted mailings.
In another part of the company your customer service department has
been struggling to get accurate, up-to-date information on computer
screens at the call-in centre. Here, you are hoping the data-driven DSS
can help improve customer service and create opportunities for your
agents to offer additional products and services.

Both situations present legitimate cases for implementing a DSS, but to

decide how to proceed you need to consider such things as: Which
business unit can deliver the most return on investment (ROI)? Which
project can deliver the most substantial ROI? How quickly can that ROI
be delivered?

The bottom line here is that companies that successfully implement a

DSS clearly define and prioritise the problems they are trying to solve,
understand what they expect the DSS to achieve, and establish a way to
measure its success. Once you have prioritised and implemented - your
measurable results can justify extending the data-driven DSS to other
business areas and applications.

Defining User Needs

Once youhave defined the business goal, it is time to define the targeted
user group and its particular needs. Two of the most important questions
to explore are: How current does the information need to be? And in
what form do the users need it?

59
MBA 757 DECISION SUPPORT SYSTEM

Consider three potential user groups. Executives tend to need a global,

high-level look with much of the analysis done behind the scenes.
Rarely do they need information in real-time. In contrast, the front-line
employee does need up-to-date information in real-time, but does not
typically need global or in-depth types of analysis. And your power
users - mid-tier decision-makers such as buyers in retail stores or
operations managers who do scheduling for airlines - need both real
time and historical detail.

It is helpful to create a matrix or table that details the system's users by

job positions or by department and document how many individuals
comprise each category. From there, you can define the general data
requirements of each audience. Include such things as output formats,
the type of data, the audience's need to analyse the data, the required
frequency of the reports, and how the data will be used.

It is also crucial at this point to consider what the needs of each user
group imply for privacy and security concerns. For example, at a health
insurer, some people may need to see only the number of emergency
room admissions over the last six months, while others may need to see
individual diagnoses and treatments. The system must be designed in
such a way that it clearly identifies and provides access to those who
need the selected information and those who should be denied access.
This too should become part of your matrix.

Defining the Data Needs

The third step is to evaluate what data you will need for the system,
which involves creating a model that will describe all the data you will
need to address the business problem you are trying to solve.

Data Sources: Let's assume you are trying to create a direct marketing
campaign for a new life insurance product. You know that at the very
least you want to be able to see your prospective clients broken down by
age, income, and their current life stage (for example, whether or not
they have recently had children). Once you have identified the data you
will need, you can map that data against the data elements that currently
exist in your environment - and identify where those elements exist. You
may find that you are not collecting some data that you need and so will
have to start collecting it.

Then you can determine contributing factors such as: How many sources
are involved? What type of data is contained in each source and in what
formats? How much data does each database contain (the number of
tables and columns available for query purposes)? Are these databases
snapshots at a point in time or are they online in real time?

60
MBA 757 DECISION SUPPORT SYSTEM

You will need all this information to determine your strategy for loading
data into the DSS. Which data gets loaded first? Does all the data need
to be refreshed simultaneously? You need to look holistically at all the
source information to create your data loading strategy.
It is also important to remember that as you identify common data from
multiple sources, you must plan to integrate it into the single data
warehouse so that you have a consistent view of the same data. This
may require data cleansing or data transformations.

This consistent view of the data is crucial because so often a data-driven

DSS project can be tripped up by bad or inconsistent data. When the
entire user group is working from the same, reliable and up-to-date
information, they make better, more aligned decisions across the board
and get the most out of the information you possess.
Data Access: Getting the maximum return on information, of course, is
the ultimate goal of data-driven DSS. It is encouraging that the potential
to achieve that maximum return has grown with the emergence of
powerful analytical tools and applications that provide access to data in
a number of ways - and which deliver important new business insights.

To get the most out of these tools they must connect to a database that is
optimally configured to handle multiple, concurrent queries and to keep
the data accurate, up-to-date and consistent for all of the system's users.
An enterprise data warehouse provides those qualities in the most
efficient and cost-effective way.
Gap Analysis to Action Plan
Having identified the business needs, the user needs, and the data needs,
you can now compare your findings to the existing environment and
determine what gaps you will need to fill.

The gap analysis should lead to a step-by-step action plan that addresses
both short- and long-term needs. You need to identify priorities and
develop strategies that include a description of initial investments as
well as pilot projects upon which the entire DSS can build.
One common problem in the planning phase is that IT projects are not
well-defined. This leads to unmet expectations, cost overruns and a
perception of limited success which translates into not getting an
adequate return on investment. It is critical to spend sufficient time
planning to avoid these pitfalls.

Ultimately, building a flexible, scalable system that keeps business

intelligence flowing and that can respond to ever-changing business
needs is the mark of an effective data-driven DSS. A careful, step-by-

61
MBA 757 DECISION SUPPORT SYSTEM

step development process tailored to the needs of your business - with

an enterprise data warehouse at the heart of the solution - can deliver
ongoing competitive advantage.

4.0 CONCLUSION
The effect or importance of decision support systems are felt more in
business organisations than probably in other areas of human endeavour.
Moreover now that business is tending towards being totally electronic,
decision support systems now become much more important in the
business world. Decision support systems go a long way in assisting
businesses to be efficient and productive.

5.0 SUMMARY
• Using information systems to support business decision-making has
been one of the primary thrusts of the business use of information
technology.
• Target Corporation’s decision support system (DSS) is composed of
several applications known as Decision Maker’s Workbench, which
use Decision Suite and WebOLAP Software from Information
Advantage.
• The type of information required by decision makers in a company is
directly related to the level of management decision-making and
the amount of structure in the decision situation they face.
• Decisions made at the operational management level tend to more
structure, those at tactical level more semi-structured, and those at
the strategic management level more unstructured.
• In What-if analysis, an end user makes changes to variables, or
relationships among variables, and observes the resulting changes in
the value of other variables.
• The concept of an interactive computer-based system that helps
companies make better business decisions has been around since
computers came into widespread use.

6.0 TUTOR-MARKED ASSIGNMENT

1. Mention the characteristics of unstructured decisions
2. Briefly discuss Goal-Seeking Analysis

7.0 REFERENCES/FURTHER READING

Jessani, R., Creating an Effective Data-Driven Decision Support
System.

DSSResources.COM, 12/05/2003.

62
MBA 757 DECISION SUPPORT SYSTEM

MODULE 2

Unit 1 Online Analytic Processing, Online Transaction

Processing and Business Analytics
Unit 2 Predictive Analytics
Unit 3 Spreadsheet
Unit 4 Executive Information System I
Unit 5 Implementing Executive Information System

UNIT 1 ONLINE ANALYTIC PROCESSING, ONLINE

TRANSACTION PROCESSING AND BUSINESS
ANALYTICS

CONTENTS

1.0 Introduction
2.0 Objectives
3.0 Main Content
3.1 History
3.2 Functionality
3.3 Aggregations
3.4 Types
3.5 Apis and Query Languages
3.6 Market Structure
3.7 Online Transaction Processing
3.8 Business Analytics
4.0 Conclusion
5.0 Summary
6.0 Tutor-Marked Assignment
7.0 References/Further Reading

1.0 INTRODUCTION

Online Analytical Processing, or OLAP (IPA), is an approach to

quickly provide answers to analytical queries that are multi-dimensional
in nature. OLAP is part of the broader category business intelligence,
which also encompasses relational reporting and data mining. The
typical applications of OLAP are in business reporting for sales,
marketing, management reporting, business process management
(BPM), budgeting and forecasting, financial reporting and similar areas.
The term OLAP was created as a slight modification of the traditional
database term OLTP (Online Transaction Processing).

63
MBA 757 DECISION SUPPORT SYSTEM

Databases configured for OLAP employ a multidimensional data model,

allowing for complex analytical and ad-hoc queries with a rapid
execution time. They borrow aspects of navigational databases and
hierarchical databases that are speedier than their relational kin.

Nigel Pendse has suggested that an alternative and perhaps more

descriptive term to describe the concept of OLAP is Fast Analysis of
Shared Multidimensional Information (FASMI)

The output of an OLAP query is typically displayed in a matrix (or

pivot) format. The dimensions form the row and column of the matrix;
the measures, the values.
OLAP enables managers and analysts to interactively examine and
manipulate large amounts of detailed and consolidated data from many
perspectives. OLAP involves analysing complex relationships among
thousands or even millions of data items stored in multi-dimensional
databases to discover patterns, trends, and exception conditions. An
OLAP session takes place online in real-time, with rapid responses to a
managers’ or analyst’s queries so that their analytical or decision-
making process is undisturbed. (Figure 1).

2.0 OBJECTIVES

At the end of this unit, the students should be able to:

• define online analytic processing (OLAP)

• trace the development and history of OLAP
• outline the functions of OLAP
• identify the different types of OLAP
• describe the market structure of OLAP
• define online transaction processing and its requirement, benefits and
disadvantages
• define business analytic, its history, applications and challenges.

64
MBA 757 DECISION SUPPORT SYSTEM

Figure 1: Online Analytic Processing may involve the use of Special

Servers and Multidimensional Databases

3.0 MAIN CONTENT

3.1 History

The first product that performed OLAP queries was Express, which was
released in 1970 (and acquired by Oracle in 1995 from Information
Resources). However, the term did not appear until 1993 when it was
coined by Ted Codd, who has been described as "the father of the
relational database". Codd's paper resulted from a short consulting
assignment which Codd undertook for former Arbor Software (later
Hyperion Solutions, and in 2007 acquired by Oracle), as a sort of
marketing coup. The company had released its own OLAP product,
Essbase, a year earlier. As a result Codd's "twelve laws of online
analytical processing" were explicit in their reference to Essbase. There
was some ensuing controversy and when Computerworld learned that
Codd was paid by Arbor, it retracted the article. OLAP market
experienced strong growth in the late 90s with dozens of commercial
products going into the market. In 1998, Microsoft released its first
OLAP Server - Microsoft Analysis Services, which drove wider
adoption of OLAP technology and moved it into mainstream.

65
MBA 757 DECISION SUPPORT SYSTEM

3.2 Functionality

In the core of any OLAP system is a concept of an OLAP cube (also

called a multidimensional cube or a hypercube). It consists of numeric
facts called measures which are categorised by dimensions. The cube
metadata is typically created from a star schema or snowflake schema of
tables in a relational database. Measures are derived from the records in
the fact table and dimensions are derived from the dimension tables.

3.3 Aggregations

It has been claimed that for complex queries OLAP cubes can produce
an answer in around 0.1% of the time for the same query on OLTP
relational data. The single most important mechanism in OLAP which
allows it to achieve such performance is the use of aggregations.
Aggregations are built from the fact table by changing the granularity on
specific dimensions and aggregating up data along these dimensions.
The number of possible aggregations is determined by every possible
combination of dimension granularities.

The combination of all possible aggregations and the base data contains
the answers to every query which can be answered from the data. Due to
the potentially large number of aggregations to be calculated, often only
a predetermined number are fully calculated while the remainder are
solved on demand. The problem of deciding which aggregations (a.k.a.
views) to calculate is known as the view selection problem. View
selection can be constrained by the total size of the selected set of
aggregations, the time to update them from changes in the base data, or
both. The objective of view selection is typically to minimise the
average time to answer OLAP queries, although some studies also
minimise the update time as well. Many different approaches have been
taken to view selection (which is NP-Complete), including greedy
algorithms, randomised search, genetic algorithms and A* search
algorithm.

A very effective way to support aggregation and other common OLAP

operations is the use of bitmap indexes.

3.4 Types

OLAP systems have been traditionally categorised using the following

taxonomy.

66
MBA 757 DECISION SUPPORT SYSTEM

Multidimensional

MOLAP is the 'classic' form of OLAP and is sometimes referred to as

just OLAP. MOLAP uses database structures that are generally optimal
for attributes such as time period, location, product or account code. The
way that each dimension will be aggregated is defined in advance by
one or more hierarchies.

Relational

ROLAP works directly with relational databases. The base data and the
dimension tables are stored as relational tables and new tables are
created to hold the aggregated information. It depends on a specialised
schema design.

Hybrid

There is no clear agreement across the industry as to what constitutes

"Hybrid OLAP", except that a database will divide data between
relational and specialised storage. For example, for some vendors, a
HOLAP database will use relational tables to hold the larger quantities
of detailed data, and use specialised storage for at least some aspects of
the smaller quantities of more-aggregate or less-detailed data.

Comparison

Each type has certain benefits, although there is disagreement about the
specifics of the benefits between providers.

Some MOLAP implementations are prone to database explosion.

Database explosion is a phenomenon causing vast amounts of storage
space to be used by MOLAP databases when certain common conditions
are met: high number of dimensions, pre-calculated results and sparse
multidimensional data. The typical mitigation technique for database
explosion is not to materialise all the possible aggregation, but only the
optimal subset of aggregations based on the desired performance vs.
storage trade off.

MOLAP generally delivers better performance due to specialised

indexing and storage optimisations. MOLAP also needs less storage
space compared to ROLAP because the specialised storage typically
includes compression techniques.

ROLAP is generally more scalable. However, large volume pre-

processing is difficult to implement efficiently so it is frequently
skipped. ROLAP query performance can therefore suffer.

67
MBA 757 DECISION SUPPORT SYSTEM

Since ROLAP relies more on the database to perform calculations, it has

more limitations in the specialised functions it can use.

HOLAP encompasses a range of solutions that attempt to mix the best of

ROLAP and MOLAP. It can generally pre-process quickly, scale well,
and offer good function support.

Other types

The following acronyms are also sometimes used, although they are not
as widespread as the ones above:

•WOLAP - Web-based OLAP

•DOLAP - Desktop OLAP
•RTOLAP - Real-Time OLAP

3.5 APIs and Query Languages

Unlike relational databases, which had SQL as the standard query
language, and widespread APIs such as ODBC, JDBC and OLEDB,
there was no such unification in the OLAP world for a long time. The
first real standard API was OLE DB for OLAP (ODBO) specification
from Microsoft which appeared in 1997 and introduced the MDX query
language. Several OLAP vendors - both server and client - adopted it. In
2001 Microsoft and Hyperion announced the XML for Analysis
specification, which was endorsed by most of the OLAP vendors. Since
this also used MDX as a query language, MDX became the de-facto
standard.

3.6 Market Structure

Given below is a list of top OLAP vendors in 2006 with figures in

millions of United States Dollars.
Vendor Global Revenue
Microsoft Corporation 1,801
Hyperion Solutions Corporation 1,077
Cognos 735
Business Objects 416
MicroStrategy 416
SAP AG 330
Cartesis SA 210
Applix 205
Infor 199
Oracle Corporation 159
Others 152
Total 5,700
It should be noted that Microsoft was the only vendor that continuously

68
MBA 757 DECISION SUPPORT SYSTEM

exceeded the industrial average growth during 2000-6. Since the above
data was collected, Hyperion has been acquired by Oracle, Business
Objects by SAP, Applix by Cognos, and Cognos by IBM.

3.7 Online Transaction Processing,

Online Transaction Processing, or OLTP, refers to a class of systems

that facilitate and manage transaction-oriented applications, typically for
data entry and retrieval transaction processing. The term is somewhat
ambiguous; some understand a "transaction" in the context of computer
or database transactions, while others (such as the Transaction
Processing Performance Council) define it in terms of business or
commercial transaction OLTP has also been used to refer to processing
in which the system responds immediately to user requests. An
automatic teller machine (ATM) for a bank is an example of a
commercial transaction processing application.
The technology is used in a number of industries, including banking,
airlines, mailorder, supermarkets, and manufacturing. Applications
include electronic banking, order processing, employee time clock
systems, e-commerce, and eTrading. The most widely used OLTP
system is probably IBM's CICS.

Requirements

Online transaction processing increasingly requires support for

transactions that span a network and may include more than one
company. For this reason, new OLTP software uses client/server
processing and brokering software that allows transactions to run on
different computer platforms in a network.

In large applications, efficient OLTP may depend on sophisticated

transaction management software (such as CICS) and/or database
optimisation tactics to facilitate the processing of large numbers of
concurrent updates to an OLTP-oriented database.

For even more demanding decentralised database systems, OLTP

brokering programs can distribute transaction processing among
multiple computers on a network. OLTP is often integrated into SOA
service-oriented architecture and Web services.

Benefits

Online Transaction Processing has two key benefits: simplicity and

efficiency.

Reduced paper trails and the faster, more accurate forecasts for revenues

69
MBA 757 DECISION SUPPORT SYSTEM

and expenses are both examples of how OLTP makes things simpler for
businesses. It also provides a concrete foundation for a stable
organisation because of the timely updating. Another simplicity factor is
that of allowing consumers the choice of how they want to pay, making
it that much more enticing to make transactions.

OLTP is proven efficient because it vastly broadens the consumer base

for an organisation, the individual processes are faster, and it’s available
24/7.

Disadvantages

It is a great tool for any organisation, but in using OLTP, there are a few
things to be wary of: the security issues and economic costs.

One of the benefits of OLTP is also an attribute to a potential problem.

The worldwide availability that this system provides to companies
makes their databases that much more susceptible to intruders and
hackers.

For B2B transactions, businesses must go offline to complete certain

steps of an individual process, causing buyers and suppliers to miss out
on some of the efficiency benefits that the system provides. As simple as
OLTP is, the simplest disruption in the system has the potential to cause
a great deal of problems, causing a waste of both time and money.
Another economic cost is the potential for server failures. This can cause
delays or even wipe out an immeasurable amount of data.

3.8 Business Analytics

Business Analytics is how organisations gather and interpret data in

order to make better business decisions and to optimise business
processes. Analytical activities are expanding fast in businesses,
government agencies and not-for-profit organisations. Analytics are
defined as the extensive use of data, statistical and quantitative analysis,
explanatory and predictive modeling, and fact-based decision-making.
Analytics may be used as input for human decisions; however, in
business there are also examples of fully automated decisions that
require minimal human intervention. In businesses, analytics (alongside
data access and reporting) represents a subset of business intelligence
(BI).

The Age of Analytics may be thought of as a new subcategory of the

Information Age, with the key difference that the early years of the
Information Age were a time when information was a scarce resource,
whereas today there is an abundance of information. The Age of

70
MBA 757 DECISION SUPPORT SYSTEM

Analytics therefore represents another way to think of the activities

necessary for success in a knowledge economy or increasingly typical of
a modern information society.

Application of Analytics

Many organisations already use analytics in some form. Operating

metrics and performance gauges such as the balanced scorecard are
familiar to most managers. For instance, a manufacturer may track,
interpret and use data to improve how it manages product quality, and a
marketing group might base decisions on the long-term analysis of
different customer segments. Businesses as diverse as global cement
giant CEMEX, California winemaker E & J Gallo Winery, industrial
equipment maker John Deere, retailer Tesco, and Bank of America are
regularly applying analytics to achieve advantage. For example, Gallo,
operating in a business built on using intuition to gauge unpredictable
consumer preferences, now quantitatively analyses and predicts the
appeal of its wines. Between 2002 and 2005, John Deere saved more
than $1 billion by employing a new analytical tool to better optimise
inventory.

However, only a handful of companies are using analytics as a

foundation for their business strategies. Capital One is among those full-
fledged analytical competitors. The financial services provider is very
open about its use of data analysis to differentiate among customers
based on credit risk, usage and other characteristics, and to match
customer characteristics with appropriate product offerings. Harrahs, the
world’s largest gaming firm, is another aggressive analytical competitor,
particularly in the area of customer loyalty.

Research by global management consultancy Accenture found that high-

performance businesses — those that substantially outperform
competitors over the long term and across economic, industry and
leadership cycles — are twice as likely to use analytics strategically
compared with the overall sample, and five times more likely to do so
than low performers.

Common to all those aspiring to that level of competitiveness is the need

to focus on developing four fundamental assets:

•Committed senior executives: Taking a broad analytical approach to

business calls for big changes in culture, process, behaviour and skills
for many employees. Such changes must be spearheaded by senior
executives who are passionate about analytics and fact-based decision-
making.
•A strong base of skills in use of data: It is very important to have a

71
MBA 757 DECISION SUPPORT SYSTEM

broad base of employees who are data-savvy — or who can quickly

become data-savvy. This calls for hiring, training and rewarding for
analytical skills, especially at management levels. It also highlights the
need to understand where those skills matter most and where they will
matter most in the future.
•Fact-driven business processes: Analytical competitors begin with “a
single version of the truth” — not the conflicting views of the same
metrics that stymie other companies. What’s needed is an integrated,
cross-enterprise view of the data — a state that may require business
process redesign on a broad scale.
•Technology to capture, sort, and make sense of the data: The
processing power to support an analytics thrust is readily available.
There is wider use of dedicated “business intelligence appliances” —
supercomputer — like machines that can quickly find and sort data in
large databases and analyses. Much of the necessary analytical software
is also available. “Real-time BI,” in which automated decisions are
embedded in operational business processes, is gaining ground.

History

Data analysis has been used in business since the dawn of the industrial
era — from the time management exercises initiated by Frederick
Winslow Taylor in the late 19th century to the measured pacing of the
mechanised assembly lines developed by Henry Ford. But it began to
command more attention in the late 1960s when computers were used in
experiments to aid decision-making. These earliest “decision support
systems” addressed repetitive and non-strategic activities such as
financial reporting. (One notable exception was at American Airlines,
which depended on Sabre, its breakthrough yield management system,
to beat its competitors.) Analysis of statistics became more routine in the
1970s with the arrival of packaged computer applications. But few
executives embraced the strategic use of data; number-crunching was
left largely to the statisticians.

Since then, analytics have evolved with the development of enterprise

resource planning (ERP) systems, data warehouses, and a wide variety
of other hardware and software tools and applications. But until
recently, companies have focused on analysing historical data rather
than developing predictive analytics for decision-making.

Many companies today are collecting and storing a mind-boggling

quantity of data. In just a few years, the common terminology for data
volumes has grown from megabytes to gigabytes to terabytes (TB) — a
trillion bytes. Some corporate databases are even approaching one
petabyte — a quadrillion bytes — in size. The 583 TB in Wal-Mart’s
data warehouse, for example, is far more than the digital capacity

72
MBA 757 DECISION SUPPORT SYSTEM

needed if all 17 million of the books in the U.S. Library of Congress

were fully formatted. Gargantuan storage facilities are not the only
technological frontier: statistical software, high-end 64-bit processors,
and specialty “data appliances” can quickly churn through enormous
amounts of data—and do so with greater sophistication.

Challenges of analytics

Analytics is dependent on data. If there is no data, there can be no

analytics. However, if data is sparse or non-existent, an organisation can
conduct surveys or a census to obtain data. In many cases to save
expenses, organisations can look for data obtained from situations that
are similar but not quite meet the current requirements, and make minor
modifications (i.e., a company trying to introduce an energy drink for
the first time in a town can use existing data from a survey of athletes
that drink carbonated beverages). However, in these cases, businesses
should be aware of the risks inherent in using data obtained in such
manner.

For many organisations aspiring to be analytical competitors, the

primary problem is not that they lack data. It is that they must contend
with dirty data. The challenge is that they do not know which data is
trustworthy — “clean” — and which contains duplicates, outdated
records and erroneous data entries.

According to Gartner, an alarming proportion of all business data is

inaccurate. The research firm estimates that at least 25 percent of critical
data within Fortune 1,000 companies will continue to be inaccurate
through 2007. In a separate study by a leading accounting firm, only a
little more than a third of executives were “very confident” in the quality
of their corporate data.

A company that finds it has poor-quality data should postpone any plans
to compete on analytics and instead should fix its data first. UPS
demonstrates the patience that is often necessary. Although the delivery
company has been collecting customer information for more than five
years, it took more than half that time to validate that data before it was
usable.

Unlike mature economies, in some of the fastest growing developing

economies, such as India and China, analytics has to contend with
"noisy" data wherein the data is incomplete (e.g. credit rating of a
customer) or suspect (e.g. demographic information of a mobile telecom
customer) or plain missing. A new generation of analytical algorithms
that compensates for this "noise" appropriately helps in deployment of
analytics solutions without the need to rely on fixing data - something

73
MBA 757 DECISION SUPPORT SYSTEM

that may never be possible in the near future. Such innovative

algorithms are an example of technology innovations in developing
markets that promise to leapfrog existing methods that have been
developed primarily for mature markets and not easily transposable
given constraints such as data sanctity.

4.0 CONCLUSION

Processing and analysing data is a very important aspect of decision

support systems. In fact, it is the hallmark of DSS. So online analytic
processing, online transaction processing and business analytics are
important tools in decision support systems. These tools collectively and
individually have their various advantages and disadvantages that need
to be explored and reevaluated. The electronic nature of the analysis has
made them more supportive to decision support systems.

5.0 SUMMARY

• Online Analytical Processing, or OLAP (IPA), is an approach to

quickly provide answers to analytical queries that are multi-
dimensional in nature. OLAP is part of the broader category business
intelligence, which also encompasses relational reporting and data
mining.
• At the core of any OLAP system is a concept of an OLAP cube (also
called a multidimensional cube or a hypercube). It consists of
numeric facts called measures, which are categorised by dimensions.
• It has been claimed that for complex queries OLAP cubes can
produce an answer in around 0.1% of the time for the same query on
OLTP relational data.
• OLAP systems have been traditionally categorised using different
taxonomy.
• Unlike relational databases, which had SQL as the standard query
language, and wide-spread APIs such as ODBC, JDBC and OLEDB,
there was no such unification in the OLAP world for a long time.
• Online Transaction Processing, or OLTP, refers to a class of
systems that facilitate and manage transaction-oriented applications,
typically for data entry and retrieval transaction processing.
• Business Analytics is how organisations gather and interpret data in
order to make better business decisions and to optimise business
processes. Analytical activities are expanding fast in businesses,
government agencies and not-for-profit organisations.
6.0 TUTOR-MARKED ASSIGNMENT

1. Mention 5 types of online analytic processing (OLAP).

2. Discuss briefly the requirements of online processing transactions
(OLTP).

74
MBA 757 DECISION SUPPORT SYSTEM

7.0 REFERENCES/FURTHER READING

Codd E.F., Codd S.B., and Salley C.T. (1993). Providing OLAP (On-
Line Analytical Processing) to User-Analysts: An IT Mandate (in
English). Codd & Date, Inc.

Deepak Pareek (2007). Business Intelligence for Telecommunications

(in English). CRC Press, 294 pp.

OLAP Council White Paper (in English). OLAP Council (1997).

Retrieved on 2008-03-18.

Hari Mailvaganam (2007). Introduction to OLAP - Slice, Dice and

Drill! (in English). Data Warehousing Review.

Nigel Pendse (2008-03-03). What is OLAP? An Analysis of what the

Often Misused OLAP Term is Supposed to Mean (in English).
OLAP Report.

MicroStrategy, Incorporated (1995). The Case for Relational OLAP (in

English).

Surajit Chaudhuri and Umeshwar Dayal (1997). An overview of data

warehousing and OLAP technology (in English). SIGMOD Rec.
26: 65. ACM. doi:10.1145/248603.248616. ISSN 0163-5808.

Data Cube: {A} Relational Aggregation Operator Generalising Group-

By, Cross-Tab, and Sub-Totals (in English) (1997). J. Data
Mining and Knowledge Discovery 1 (1): pp. 29–53.

Nigel Pendse (2006-06-27). OLAP Architectures (in English). OLAP

Report.

Nigel Pendse (2007-08-23). Commentary: OLAP API wars (in English).

OLAP Report.

Nigel Pendse (2007-08-23). The Origins of Today’s OLAP Products (in

English). OLAP Report.

Nigel Pendse (2006). OLAP Marke (in English). OLAP Report.

Nigel Pendse (2008-03-07). Consolidations in the BI industry (in
English).

Transaction Processing Performance Council website.

75
MBA 757 DECISION SUPPORT SYSTEM

Davenport, Thomas H.; Jeanne G. Harris (March 2007). Competing on

Analytics: The New Science of Winning. Harvard Business
School Press.

McDonald, Mark; Tina Nunno (February 2007). Creating Enterprise

Leverage: The 2007 CIO Agenda. Stamford, CT: Gartner, Inc.

Baker, Stephen (January 23, 2006). Math Will Rock Your World.
BusinessWeek..

Davenport, Thomas H. (January 1, 2006). Competing on Analytics.

Harvard Business Review.

Pfeffer, Jeffrey; Robert Sutton (January 2006). Evidence-Based

Managemen. Harvard Business Review.

Davenport, Thomas H.; Jeanne G. Harris (Summer 2005). Automated

Decision Making Comes of Age. MIT Sloan Management
Review.

Lewis, Michael (April 2004). Moneyball: The Art of Winning an Unfair

Game. W.W. Norton & Co..

Bonabeau, Eric (May 2003). Don’t Trust Your Gut. Harvard Business
Review.

Davenport, Thomas H.; Jeanne G. Harris, David W. De Long, Alvin L.

Jacobson. Data to Knowledge to Results: Building an Analytic
Capability. California Management Review 43 (2): 117–138.

Ranadive, Vivek (2006-01-26). The Power to Predict: How Real Time

Businesses Anticipate Customer Needs, Create Opportunities,
and Beat the Competition. McGraw-Hill.

Zabin, Jeffrey; Gresh Brebach (February 2004). Precision Marketing.

John Wiley.

UNIT 2 PREDICTIVE ANALYTICS

CONTENTS

76
MBA 757 DECISION SUPPORT SYSTEM

1.0 Introduction
2.0 Objectives
3.0 Main Content
3.1 Types of Predictive Analytics
3.2 Current Uses
3.3 Statistical Techniques
3.4 Neural Networks
3.5 Radial Basis Functions
3.6 Support Vector Machines
3.7 Naïve Bayes
3.8 K-nearest Neighbours
3.9 Popular Tools
4.0 Conclusion
5.0 Summary
6.0 Tutor-Marked Assignment
7.0 References/Further Reading

1.0 INTRODUCTION

Predictive analytics encompasses a variety of techniques from statistics

and data mining that analyse current and historical data to make
predictions about future events. Such predictions rarely take the form of
absolute statements, and are more likely to be expressed as values that
correspond to the odds of a particular event or behaviour taking place in
the future.

Predictive analytics is an area of statistical analysis that deals with

extracting information from data and using it to predict future trends and
behaviour patterns. The core of predictive analytics relies on capturing
relationships between explanatory variables and the predicted variables
from past occurrences, and exploiting it to predict future outcomes.

In business, predictive models exploit patterns found in historical and

transactional data to identify risks and opportunities. Models capture
relationships among many factors to allow assessment of risk or
potential associated with a particular set of conditions, guiding decision
making for candidate transactions.

One of the most well-known applications is credit scoring, which is used

throughout financial services. Scoring models process a customer’s
credit history, loan application, customer data, etc., in order to rank-
order individuals by their likelihood of making future credit payments
on time. Predictive analytics are also used in insurance,
telecommunications, retail, travel, healthcare, pharmaceuticals and other
fields.

77
MBA 757 DECISION SUPPORT SYSTEM

2.0 OBJECTIVES

At the end of this unit, the students should be able to:

• define predictive analytics

• identify the different types of predictive analytics
• explain different ways of applying predictive analysis in decision
making in life and business
• identify, compare and contrast the various techniques associated with
predictive analytics
• name some of the popular tools used in predictive analytics.

3.0 MAIN CONTENT

3.1 Types of Predictive Analytics

Generally, predictive analytics is used to mean predictive modelling,

scoring of predictive models, and forecasting. However, people are
increasingly using the term to describe related analytic disciplines, such
as descriptive modelling and decision modelling or optimisation. These
disciplines also involve rigorous data analysis, and are widely used in
business for segmentation and decision making but have different
purposes and the statistical techniques underlying them vary.

Predictive Models

Predictive models analyse past performance to assess how likely a

customer is to exhibit a specific behaviour in the future in order to
improve marketing effectiveness. This category also encompasses
models that seek out subtle data patterns to answer questions about
customer performance, such as fraud detection models. Predictive
models often perform calculations during live transactions, for example,
to evaluate the risk or opportunity of a given customer or transaction, in
order to guide a decision.

Descriptive Models

Descriptive models “describe” relationships in data in a way that is often

used to classify customers or prospects into groups. Unlike predictive
models that focus on predicting a single customer behaviour (such as
credit risk), descriptive models identify many different relationships
between customers or products. But the descriptive models do not rank-
order customers by their likelihood of taking a particular action the way
predictive models do. Descriptive models are often used “offline,” for
example, to categorise customers by their product preferences and life

78
MBA 757 DECISION SUPPORT SYSTEM

stage. Descriptive modelling tools can be utilised to develop agent based

models that can simulate large number of individualised agents to
predict possible futures.

Decision Models

Decision models describe the relationship between all the elements of a

decision — the known data (including results of predictive models), the
decision and the forecast results of the decision — in order to predict the
results of decisions involving many variables. These models can be used
in optimisation, a data-driven approach to improving decision logic that
involves maximising certain outcomes while minimising others.
Decision models are generally used offline, to develop decision logic or
a set of business rules that will produce the desired action for every
customer or circumstance.

3.2 Current Uses

Although predictive analytics can be put to use in many applications, we

outline a few examples where predictive analytics has shown positive
impact in recent years.

Analytical Customer Relationship Management (CRM)

Analytical Customer Relationship Management is a frequent

commercial application of Predictive Analysis. Methods of predictive
analysis are applied to customer data to pursue CRM objectives.

Direct Marketing

Product marketing is constantly faced with the challenge of coping with

the increasing number of competing products, different consumer
preferences and the variety of methods (channels) available to interact
with each consumer. Efficient marketing is a process of understanding
the amount of variability and tailoring the marketing strategy for greater
profitability. Predictive analytics can help identify consumers with a
higher likelihood of responding to a particular marketing offer. Models
can be built using data from consumers’ past purchasing history and past
response rates for each channel. Additional information about the
consumers demographic, geographic and other characteristics can be
used to make more accurate predictions. Targeting only these consumers
can lead to substantial increase in response rate which can lead to a
significant reduction in cost per acquisition. Apart from identifying
prospects, predictive analytics can also help to identify the most
effective combination of products and marketing channels that should be
used to target a given consumer.

79
MBA 757 DECISION SUPPORT SYSTEM

Cross-Sell

Often corporate organisations collect and maintain abundant data (e.g.

customer records, sale transactions) and exploiting hidden relationships
in the data can provide a competitive advantage to the organisation. For
an organisation that offers multiple products, an analysis of existing
customer behaviour can lead to efficient cross sell of products. This
directly leads to higher profitability per customer and strengthening of
the customer relationship. Predictive analytics can help analyse
customers’ spending, usage and other behaviour, and help cross-sell the
right product at the right time.

Customer Retention

With the amount of competing services available, businesses need to

focus efforts on maintaining continuous consumer satisfaction. In such a
competitive scenario, consumer loyalty needs to be rewarded and
customer attrition needs to be minimised. Businesses tend to respond to
customer attrition on a reactive basis, acting only after the customer has
initiated the process to terminate service. At this stage, the chance of
changing the customer’s decision is almost impossible. Proper
application of predictive analytics can lead to a more proactive retention
strategy. By a frequent examination of a customer’s past service usage,
service performance, spending and other behaviour patterns, predictive
models can determine the likelihood of a customer wanting to terminate
service sometime in the near future. An intervention with lucrative
offers can increase the chance of retaining the customer. Silent attrition
is the behaviour of a customer to slowly but steadily reduce usage and is
another problem faced by many companies. Predictive analytics can also
predict this behaviour accurately and before it occurs, so that the
company can take proper actions to increase customer activity.

Underwriting

Many businesses have to account for risk exposure due to their different
services and determine the cost needed to cover the risk. For example,
auto insurance providers need to accurately determine the amount of
premium to charge to cover each automobile and driver. A financial
company needs to assess a borrower’s potential and ability to pay before
granting a loan. For a health insurance provider, predictive analytics can
analyse a few years of past medical claims data, as well as lab,
pharmacy and other records where available, to predict how expensive
an enrollee is likely to be in the future. Predictive analytics can help
underwriting of these quantities by predicting the chances of illness,
default, bankruptcy, etc. Predictive analytics can streamline the process

80
MBA 757 DECISION SUPPORT SYSTEM

of customer acquisition, by predicting the future risk behaviour of a

customer using application level data. Proper predictive analytics can
lead to proper pricing decisions, which can help mitigate future risk of
default.

Collection Analytics

Every portfolio has a set of delinquent customers who do not make their
payments on time. The financial institution has to undertake collection
activities on these customers to recover the amounts due. A lot of
collection resources are wasted on customers who are difficult or
impossible to recover. Predictive analytics can help optimise the
allocation of collection resources by identifying the most effective
collection agencies, contact strategies, legal actions and other strategies
to each customer, thus significantly increasing recovery at the same time
reducing collection costs.

Fraud Detection

Fraud is a big problem for many businesses and can be of various types.
Inaccurate credit applications, fraudulent transactions, identity thefts and
false insurance claims are some examples of this problem. These
problems plague firms all across the spectrum and some examples of
likely victims are credit card issuers, insurance companies, retail
merchants, manufacturers, business to business suppliers and even
services providers. This is an area where a predictive model is often
used to help weed out the “bads” and reduce a business's exposure to
fraud.

Portfolio, Product Oror Economy Level Prediction

Often the focus of analysis is not the consumer but the product,
portfolio, firm, industry or even the economy. For example a retailer
might be interested in predicting store level demand for inventory
management purposes. Or the Federal Reserve Board might be
interested in predicting the unemployment rate for the next year. These
types of problems can be addressed by predictive analytics using Time
Series techniques

3.3 Statistical Techniques

81
MBA 757 DECISION SUPPORT SYSTEM

The approaches and techniques used to conduct predictive analytics can

broadly be grouped into regression techniques and machine learning
techniques.

Regression Techniques

Regression models are the mainstay of predictive analytics. The focus

lies on establishing a mathematical equation as a model to represent the
interactions between the different variables in consideration. Depending
on the situation, there is a wide variety of models that can be applied
while performing predictive analytics. Some of them are briefly
discussed below.

Linear Regression Model

The linear regression model analyses the relationship between the

response or dependent variable and a set of independent or predictor
variables. This relationship is expressed as an equation that predicts the
response variable as a linear function of the parameters. These
parameters are adjusted so that a measure of fit is optimised. Much of
the effort in model fitting is focused on minimising the size of the
residual, as well as ensuring that it is randomly distributed with respect
to the model predictions.

The goal of regression is to select the parameters of the model so as to

minimise the sum of the squared residuals. This is referred to as
ordinary least squares (OLS) estimation and results in best linear
unbiased estimates (BLUE) of the parameters if and only if the Gauss-
Markowitz assumptions are satisfied.

Once the model has been estimated we would be interested to know if

the predictor variables belong in the model – i.e. is the estimate of each
variable’s contribution reliable? To do this we can check the statistical
significance of the model’s coefficients which can be measured using
the t-statistic. This amounts to testing whether the coefficient is
significantly different from zero. How well the model predicts the
dependent variable based on the value of the independent variables can
be assessed by using the R² statistic. It measures predictive power of the
model i.e. the proportion of the total variation in the dependent variable
that is “explained” (accounted for) by variation in the independent
variables.

Discrete Choice Models

82
MBA 757 DECISION SUPPORT SYSTEM

Multivariate regression (above) is generally used when the response

variable is continuous and has an unbounded range. Often the response
variable may not be continuous but rather discrete. While
mathematically it is feasible to apply multivariate regression to discrete
ordered dependent variables, some of the assumptions behind the theory
of multivariate linear regression no longer hold, and there are other
techniques such as discrete choice models which are better suited for
this type of analysis. If the dependent variable is discrete, some of those
superior methods are logistic regression, multinomial logit and probit
models. Logistic regression and probit models are used when the
dependent variable is binary.

Logistic Regression

In a classification setting, assigning outcome probabilities to

observations can be achieved through the use of a logistic model, which
is basically a method which transforms information about the binary
dependent variable into an unbounded continuous variable and estimates
a regular multivariate model (See Allison’s Logistic Regression for
more information on the theory of Logistic Regression).
The Wald and likelihood-ratio test are used to test the statistical
significance of each coefficient b in the model (analogueous to the t tests
used in OLS regression; see above). A test assessing the goodness-of-fit
of a classification model is the Hosmer and Lemeshow test.

Multinomial Logistic Regression

An extension of the binary logit model to cases where the dependent

variable has more than 2 categories is the multinomial logit model. In
such cases collapsing the data into two categories might not make good
sense or may lead to loss in the richness of the data. The multinomial
logit model is the appropriate technique in these cases, especially when
the dependent variable categories are not ordered (for examples colors
like red, blue, green). Some authors have extended multinomial
regression to include feature selection/importance methods such as
Random multinomial logit.

Probit Regression

Probit models offer an alternative to logistic regression for modelling

categorical dependent variables. Even though the outcomes tend to be
similar, the underlying distributions are different. Probit models are
popular in social sciences like economics.
A good way to understand the key difference between probit and logit
models, is to assume that there is a latent variable z.
We do not observe z but instead observe y which takes the value 0 or 1.
In the logit model we assume that follows a logistic distribution. In the

83
MBA 757 DECISION SUPPORT SYSTEM

probit model we assume that follows a standard normal distribution.

Note that in social sciences (example economics), probit is often used to
model situations where the observed variable y is continuous but takes
values between 0 and 1.

Logit vs. Probit

The Probit model has been around longer than the logit model. They
look identical, except that the logistic distribution tends to be a little flat
tailed. In fact one of the reasons the logit model was formulated was that
the probit model was extremely hard to compute because it involved
calculating difficult integrals. Modern computing however has made this
computation fairly simple. The coefficients obtained from the logit and
probit model are also fairly close. However the odds ratio makes the
logit model easier to interpret.

For practical purposes the only reasons for choosing the probit model
over the logistic model would be:

• There is a strong belief that the underlying distribution is normal

• The actual event is not a binary outcome (e.g. Bankrupt/not
bankrupt) but a proportion (e.g. Proportion of population at different
debt levels).

Time Series Models

Time series models are used for predicting or forecasting the future
behaviour of variables. These models account for the fact that data
points taken over time may have an internal structure (such as
autocorrelation, trend or seasonal variation) that should be accounted
for. As a result standard regression techniques cannot be applied to time
series data and methodology has been developed to decompose the
trend, seasonal and cyclical component of the series. Modelling the
dynamic path of a variable can improve forecasts since the predictable
component of the series can be projected into the future.

Time series models estimate difference equations containing stochastic

components. Two commonly used forms of these models are
autoregressive models (AR) and moving average (MA) models. The
Box-Jenkins methodology (1976) developed by George Box and G.M.
Jenkins combines the AR and MA models to produce the ARMA
(autoregressive moving average) model which is the cornerstone of
stationary time series analysis. ARIMA (autoregressive integrated
moving average models) on the other hand are used to describe non-
stationary time series. Box and Jenkins suggest differencing a non
stationary time series to obtain a stationary series to which an ARMA

84
MBA 757 DECISION SUPPORT SYSTEM

model can be applied. Non stationary time series have a pronounced

trend and do not have a constant long-run mean or variance.

Box and Jenkins proposed a three stage methodology which includes:

model identification, estimation and validation. The identification stage
involves identifying if the series is stationary or not and the presence of
seasonality by examining plots of the series, autocorrelation and partial
autocorrelation functions. In the estimation stage, models are estimated
using non-linear time series or maximum likelihood estimation
procedures. Finally the validation stage involves diagnostic checking
such as plotting the residuals to detect outliers and evidence of model
fit.

In recent years time series models have become more sophisticated and
attempt to model conditional heteroskedasticity with models such as
ARCH (autoregressive conditional heteroskedasticity) and GARCH
(generalised autoregressive conditional heteroskedasticity) models
frequently used for financial time series. In addition time series models
are also used to understand inter-relationships among economic
variables represented by systems of equations using VAR (vector
autoregression) and structural VAR models.

Survival or Duration Analysis

Survival analysis is another name for time to event analysis. These

techniques were primarily developed in the medical and biological
sciences, but they are also widely used in the social sciences like
economics, as well as in engineering (reliability and failure time
analysis).

Censoring and non-normality which are characteristic of survival data

generate difficulty when trying to analyse the data using conventional
statistical models such as multiple linear regression. The Normal
distribution, being a symmetric distribution, takes positive as well as
negative values, but duration by its very nature cannot be negative and
therefore normality cannot be assumed when dealing with
duration/survival data. Hence the normality assumption of regression
models is violated.

A censored observation is defined as an observation with incomplete

information. Censoring introduces distortions into traditional statistical
methods and is essentially a defect of the sample data. The assumption
is that if the data were not censored it would be representative of the
population of interest. In survival analysis, censored observations arise
whenever the dependent variable of interest represents the time to a
terminal event, and the duration of the study is limited in time.

85
MBA 757 DECISION SUPPORT SYSTEM

An important concept in survival analysis is the hazard rate. The hazard

rate is defined as the probability that the event will occur at time t
conditional on surviving until time t. Another concept related to the
hazard rate is the survival function which can be defined as the
probability of surviving to time t.

Most models try to model the hazard rate by choosing the underlying
distribution depending on the shape of the hazard function. A
distribution whose hazard function slopes upward is said to have
positive duration dependence, a decreasing hazard shows negative
duration dependence whereas constant hazard is a process with no
memory usually characterised by the exponential distribution. Some of
the distributional choices in survival models are: F, gamma, Weibull,
log normal, inverse normal, exponential etc. All these distributions are
for a non-negative random variable.

Duration models can be parametric, non-parametric or semi-parametric.

Some of the models commonly used are Kaplan-Meier, Cox
proportional hazard model (non parametric).

Classification and Regression Trees

Classification and regression trees (CART) is a non-parametric

technique that produces either classification or regression trees,
depending on whether the dependent variable is categorical or numeric,
respectively.

Trees are formed by a collection of rules based on values of certain

variables in the modelling data set:

• Rules are selected based on how well splits based on variables’

values can differentiate observations based on the dependent variable
• Once a rule is selected and splits a node into two, the same logic is
applied to each “child” node (i.e. it is a recursive procedure)
• Splitting stops when CART detects no further gain can be made, or
some pre-set stopping rules are met.

Each branch of the tree ends in a terminal node;

• Each observation falls into one and exactly one terminal node
• Each terminal node is uniquely defined by a set of rules.
A very popular method for predictive analytics is Leo Breiman's
Random forests or derived versions of this technique like Random
multinomial logit.

86
MBA 757 DECISION SUPPORT SYSTEM

Multivariate Adaptive Regression Splines

Multivariate adaptive regression splines (MARS) is a non-parametric

technique that builds flexible models by fitting piecewise linear
regressions.
An important concept associated with regression splines is that of a
knot. Knot is where one local regression model gives way to another and
thus is the point of intersection between two splines.

In multivariate and adaptive regression splines, basis functions are the

tool used for generalising the search for knots. Basis functions are a set
of functions used to represent the information contained in one or more
variables. Multivariate and Adaptive Regression Splines model almost
always creates the basis functions in pairs.
Multivariate and adaptive regression spline approach deliberately
overfits the model and then prunes to get to the optimal model. The
algorithm is computationally very intensive and in practice we are
required to specify an upper limit on the number of basis functions.

Machine Learning Techniques

Machine learning, a branch of artificial intelligence, was originally

employed to develop techniques to enable computers to learn. Today,
since it includes a number of advanced statistical methods for regression
and classification, it finds application in a wide variety of fields
including medical diagnostics, credit card fraud detection, face and
speech recognition and analysis of the stock market. In certain
applications it is sufficient to directly predict the dependent variable
without focusing on the underlying relationships between variables. In
other cases, the underlying relationships can be very complex and the
mathematical form of the dependencies unknown. For such cases,
machine learning techniques emulate human cognition and learn from
training examples to predict future events.

A brief discussion of some of these methods used commonly for

predictive analytics is provided below. A detailed study of machine
learning can be found in Mitchell (1997).

3.4 Neural Networks

Neural networks are nonlinear sophisticated modelling techniques that
are able to model complex functions. They can be applied to problems
of prediction, classification or control in a wide spectrum of fields such
as finance, cognitive psychology/neuroscience, medicine, engineering,
and physics.

87
MBA 757 DECISION SUPPORT SYSTEM

Neural networks are used when the exact nature of the relationship
between inputs and output is not known. A key feature of neural
networks is that they learn the relationship between inputs and output
through training. There are two types of training in neural networks used
by different networks, supervised and unsupervised training, with
supervised being the most common one.
Some examples of neural network training techniques are
backpropagation, quick propagation, conjugate gradient descent,
projection operator, Delta-Bar-Delta etc. Theses are applied to network
architectures such as multilayer perceptrons, Kohonen networks,
Hopfield networks, etc.

3.5 Radial Basis Functions

A radial basis function (RBF) is a function which has built into it a
distance criterion with respect to a centre. Such functions can be used
very efficiently for interpolation and for smoothing of data. Radial basis
functions have been applied in the area of neural networks where they
are used as a replacement for the sigmoidal transfer function. Such
networks have 3 layers, the input layer, the hidden layer with the RBF
non-linearity and a linear output layer. The most popular choice for the
non-linearity is the Gaussian. RBF networks have the advantage of not
being locked into local minima as do the feed-forward networks such as
the multilayer perceptron.

3.6 Support Vector Machines

Support Vector Machines (SVM) are used to detect and exploit complex
patterns in data by clustering, classifying and ranking the data. They are
learning machines that are used to perform binary classifications and
regression estimations. They commonly use kernel based methods to
apply linear classification techniques to non-linear classification
problems. There are a number of types of SVM such as linear,
polynomial, sigmoid etc.

3.7 Naïve Bayes

Naïve Bayes based on Bayes conditional probability rule is used for
performing classification tasks. Naïve Bayes assumes the predictors are
statistically independent which makes it an effective classification tool
that is easy to interpret. It is best employed when faced with the problem
of ‘curse of dimensionality’ i.e. when the number of predictors is very
high.

88
MBA 757 DECISION SUPPORT SYSTEM

3.8 K-Nearest Neighbours

The nearest neighbour algorithm (KNN) belongs to the class of pattern
recognition statistical methods. The method does not impose a priori any
assumptions about the distribution from which the modelling sample is
drawn. It involves a training set with both positive and negative values.
A new sample is classified by calculating the distance to the nearest
neighbouring training case. The sign of that point will determine the
classification of the sample. In the k-nearest neighbour classifier, the k
nearest points are considered and the sign of the majority is used to
classify the sample. The performance of the kNN algorithm is
influenced by three main factors: (1) the distance measure used to locate
the nearest neighbours; (2) the decision rule used to derive a
classification from the k-nearest neighbours; and (3) the number of
neighbours used to classify the new sample. It can be proved that, unlike
other methods, this method is universally asymptotically convergent,
i.e.: as the size of the training set increases, if the observations are iid,
regardless of the distribution from which the sample is drawn, the
predicted class will converge to the class assignment that minimises
misclassification error. See Devroy et alt.

3.9 Popular Tools

There are numerous tools available in the marketplace which helps with
the execution of predictive analytics. These range from those which
need very little user sophistication to those that are designed for the
expert practitioner. The difference between these tools is often in the
level of customisation and heavy data lifting allowed. For traditional
statistical modelling some of the popular tools are DAP/SAS, S-Plus,
PSPP/SPSS and Stata. For machine learning/data mining type of
applications, KnowledgeSEEKER, KnowledgeSTUDIO, Enterprise
Miner, GeneXproTools, Viscovery, Clementine, KXEN Analytic
Framework, InforSense and Excel Miner are some of the popularly used
options. Classification Tree analysis can be performed using CART
software. SOMine is a predictive analytics tool based on self-organising
maps (SOMs) available from Viscovery Software. R is a very powerful
tool that can be used to perform almost any kind of statistical analysis,
and is freely downloadable. WEKA is a freely available open-source
collection of machine learning methods for pattern classification,
regression, clustering, and some types of meta-learning, which can be
used for predictive analytics. RapidMiner is another freely available
integrated open-source software environment for predictive analytics,
data mining, and machine learning fully integrating WEKA and
providing an even larger number of methods for predictive analytics.
Recently, in an attempt to provide a standard language for expressing
predictive models, the Predictive Model Markup Language (PMML) has

89
MBA 757 DECISION SUPPORT SYSTEM

been proposed. Such an XML-based language provides a way for the

different tools to define predictive models and to share these between
PMML compliant applications. Several tools already produce or
consume PMML documents, these include ADAPA, IBM DB2
Warehouse, CART, SAS Enterprise Miner, and SPSS. Predictive
analytics has also found its way into the IT lexicon, most notably in the
area of IT Automation. Vendors such as Stratavia and their Data Palette
product offer predictive analytics as part of their automation platform,
predicting how resources will behave in the future and automate the
environment accordingly.
The widespread use of predictive analytics in industry has led to the
proliferation of numerous productised solutions firms. Some of them are
highly specialised (focusing, for example, on fraud detection, automatic
sales lead generation or response modelling) in a specific domain (Fair
Isaac for credit card scores) or industry verticals (MarketRx in
Pharmaceutical). Others provide predictive analytics services in support
of a wide range of business problems across industry verticals (Fifth C).
Predictive Analytics competitions are also fairly common and often pit
academics and Industry practitioners (see for example, KDD CUP).

4.0 CONCLUSION
Predictive analytics adds great value to businessesto businesses
decision making capabilities by allowing them to formulate smart
policies on the basis of predictions of future outcomes. A broad range of
tools and techniques are available for this type of analysis and their
selection is determined by the analytical maturity of the firm as well as
the specific requirements of the problem being solved.

5.0 SUMMARY
• Predictive analytics encompasses a variety of techniques from
statistics and data mining that analyse current and historical data to
make predictions about future events.
• Generally, predictive analytics is used to mean predictive modelling,
scoring of predictive models, and forecasting. However, people are
increasingly using the term to describe related analytic disciplines,
such as descriptive modelling and decision modelling or
optimisation.
• Although predictive analytics can be put to use in many applications,
we outline a few examples where predictive analytics has shown
positive impact in recent years.
• The approaches and techniques used to conduct predictive analytics
can broadly be grouped into regression techniques and machine
learning techniques.

90
MBA 757 DECISION SUPPORT SYSTEM

• Neural networks are nonlinear sophisticated modelling techniques

that are able to model complex functions.
• A radial basis function (RBF) is a function which has built into it a
distance criterion with respect to a centre
• Support Vector Machines (SVM) are used to detect and exploit
complex patterns in data by clustering, classifying and ranking the
data.
• Naïve Bayes based on Bayes conditional probability rule is used for
performing classification tasks.
• The nearest neighbour algorithm (KNN) belongs to the class of
pattern recognition statistical methods.
• There are numerous tools available in the marketplace which helps
with the execution of predictive analytics. These range from those
which need very little user sophistication to those that are designed
for the expert practitioner.

6.0 TUTOR-MARKED ASSIGNMENT

8. List 5 uses of predictive analysis

9. Briefly discuss Classification and Regression Trees (CART)

7.0 REFERENCES/FURTHER READING

L. Devroye, L. Györfi, G. Lugosi (1996). A Probabilistic Theory of
Pattern Recognition. New York: Springer-Verlag.
John R. Davies, Stephen V. Coggeshall, Roger D. Jones, and Daniel
Schutzer, Intelligent Security Systems, in Freedman, Roy S.,
Flein, .

Robert A., and Lederman, Jess, Editors (1995). Artificial Intelligence in

the Capital Markets. Chicago: Irwin. ISBN 1-55738-811-3.

Agresti, Alan (2002). Categorical Data Analysis. Hoboken: John Wiley

and Sons. ISBN 0-471-36093-7.

Enders, Walter (2004). Applied Time Series Econometrics. Hoboken:

John Wiley and Sons. ISBN: 052183919X.

Greene, William (2000). Econometric Analysis. London: Prentice Hall.

ISBN: 0-13-013297-7.

Mitchell, Tom (1997). Machine Learning. New York: McGraw-Hill.

ISBN 0-07-042807-7

91
MBA 757 DECISION SUPPORT SYSTEM

Tukey, John (1977). Exploratory Data Analysis. New York: Addison-

Wesley. ISBN: 0.

UNIT 3 SPREADSHEET

CONTENTS

1.0 Introduction
2.0 Objectives
3.0 Main Content
3.1 History
3.2 Use of Spreadsheets
3.3 Concepts
3.4 Shortcomings
3.5 Spreadsheets as Decision-making Tools
4.0 Conclusion
5.0 Summary
6.0 Tutor-Marked Assignment
7.0 References/Further Reading

1.0 INTRODUCTION

A spreadsheet is a computer application that simulates a paper

worksheet. It displays multiple cells that together make up a grid
consisting of rows and columns, each cell containing either
alphanumeric text or numeric values. A spreadsheet cell may
alternatively contain a formula that defines how the contents of that cell
is to be calculated from the contents of any other cell (or combination of
cells) each time any cell is updated. Spreadsheets are frequently used for
financial information because of their ability to re-calculate the entire
sheet automatically after a change to a single cell is made.

In 1971, Rene K. Pardo and Remy Landau filed a patent on a

spreadsheet related algorithm. Visicalc is usually considered the first
electronic spreadsheet (although this has been challenged), and it helped
turn the Apple II computer into a success and greatly assisted in their
widespread application. Lotus 1-2-3 was the leading spreadsheet of DOS
era. Excel is now generally considered to have the largest market share.

2.0 OBJECTIVES

At the end of this unit, the students should be able to:

• define spreadsheet

92
MBA 757 DECISION SUPPORT SYSTEM

• evaluate the history and development of spreadsheet

• identify types of spreadsheet and their uniqueness
• describe the concepts of cell, sheets, and charts which are the major
structure of a spreadsheet
• explain the evolution of languages to deal with changes in
spreadsheets
• identify the challenges facing spreadsheets
• identify the applications of spreadsheets as decision making tools.

3.0 MAIN CONTENT

3.1 History

Paper Spreadsheets

The word "spreadsheet" came from "spread" in its sense of a newspaper

or magazine item (text and/or graphics) that covers two facing pages,
extending across the centre fold and treating the two pages as one large
one. The compound word "spread-sheet" came to mean the format used
to present book-keeping ledgers—with columns for categories of
expenditures across the top, invoices listed down the left margin, and the
amount of each payment in the cell where its row and column intersect
—which were, traditionally, a "spread" across facing pages of a bound
ledger (book for keeping accounting records) or on oversized sheets of
paper ruled into rows and columns in that format and approximately
twice as wide as ordinary paper.

Early Implementations

Batch spreadsheet report generator: The concept of an electronic

spreadsheet was outlined in the 1961 paper "Budgeting Models and
System Simulation" by Richard Mattessich. The subsequent work by
Mattessich (1964a, Chpt. 9, Accounting and Analytical Methods) and its
companion volume, Mattessich (1964b, Simulation of the Firm through
a Budget Computer Program) applied computerised spreadsheets to
accounting and budgeting systems (on main-frame computers in
FORTRAN IV). Batch Spreadsheets dealt primarily with the addition or
subtraction of entire columns or rows - rather than individual cells.

LANPAR spreadsheet compiler: Key invention in the development of

electronic spreadsheets was made by Rene K. Pardo and Remy Landau,
who filed in 1971 U.S. Patent 4,398,249 on4,398,249 on spreadsheet
automatic natural order recalculation algorithm in 1970. While the
patent was initially rejected by the patent office as being a purely
mathematical invention, following 12 years of Appeals, Pardo and

93
MBA 757 DECISION SUPPORT SYSTEM

Landau won a landmark court case at the CCPA (Predecessor Court of

the Federal Circuit) overturning the Patent Office in 1983 with the
world's first software patent - establishing that "something does not
cease to become patentable merely because the point of novelty is in an
algorithm." This case helped establish the viability of software patents.
The actual software was called LANPAR - LANguage for Programming
Arrays at Random. This was conceived and entirely developed in the
summer of 1969 following Pardo and Landau's recent graduation from
Harvard University. Co-inventor Rene Pardo recalls that he felt that one
manager at Bell Canada should not have to depend on programmers to
program and modify budgeting forms, and he thought of letting users
type out forms in any order and having computer calculating results in
the right order. The software was developed in 1969.

LANPAR was used by Bell Canada, AT&T and the 18 operating telcos
nationwide for their local and national budgeting operations. LANPAR
was also used by General Motors. Its uniqueness was the incorporation
of natural order recalculation, as opposed to left-to-right, top to bottom
sequence for calculating the results in each cell that was used by
Visicalc, Supercalc and the first version of Multiplan. Without natural
order recalculation the users had to manually recalculate the spreadsheet
as many times as necessary until the values in all the cells had stopped
changing.

The LANPAR system was implemented on GE400 and Honeywell 6000

on line timesharing systems enabling users to program remotely via
computer terminals and modems. Data could be entered dynamically
either by paper tape, specific file access, on line, or even external data
bases. Sophisticated mathematical expressions including logical
comparisons and "if/then" statements could be used in any cell, and cells
could be presented in any order.

Autoplan/Autotab spreadsheet programming language: In 1968,

three former employees from the General Electric computer company
headquartered in Phoenix, Arizona set out to start their own software
development house. A. Leroy Ellison, Harry N. Cantrell, and Russell E.
Edwards found themselves doing a large number of calculations when
making tables for the business plans that they were presenting to venture
capitalists. They decided to save themselves a lot of effort and wrote a
computer program that produced their tables for them. This program,
originally conceived as a simple utility for their personal use, would turn
out to be the first software product offered by the company that would
become known as Capex Corporation. "AutoPlan" ran on GE’s Time-
sharing service; afterward, a version that ran on IBM mainframes was
introduced under the name "AutoTab". (National CSS offered a similar
product, CSSTAB, which had a moderate timesharing user base by the

94
MBA 757 DECISION SUPPORT SYSTEM

early 70s. A major application was opinion research tabulation.)

AutoPlan/AutoTab was not a WYSIWYG interactive spreadsheet
program; it was a simple scripting language for spreadsheets. The user
defined the names and labels for the rows and columns, then the
formulas that defined each row or column.
Interactive Spreadsheets: Interactive spreadsheets became possible
when computer displays became available. Except for LANPAR- which
allowed many users in real time and online to timesharing systems to
simultaneously program or run their spreadsheets from their computer
terminals across the country - earlier implementations were mainly
designed around batch programs and certainly none of these batch
programs allowed for forward referencing of cells or natural order
recalculation. In the early 1970s text based computer displays began to
be used as input/output devices for interactive transaction processes.
This was sufficient for early interactive spreadsheets to be implemented.
The lack of on-line historical material relating to such systems, and their
limited coverage in academic and commercial publications, makes it
hard to assess their level of innovation and ultimate impact.

APLDOT Modelling Language

An example of an early "industrial weight" spreadsheet was APLDOT,

developed in 1976 at the United States Railway Association on an IBM
360/91, running at The Johns Hopkins University Applied Physics
Laboratory in Laurel, MD. The application was used successfully for
many years in developing such applications as financial and costing
models for the US Congress and for Conrail. APLDOT was dubbed a
"spreadsheet" because financial analysts and strategic planners used it to
solve the same problems they addressed with paper spreadsheet pads.

The spreadsheet concept became widely known in the late 1970s and
early 1980s because of Dan Bricklin’s implementation of VisiCalc.
VisiCalc was the first spreadsheet that combined all essential features of
modern spreadsheet applications, such as WYSIWYG interactive user
interface, automatic recalculation, status and formula lines, range
copying with relative and absolute references, formula building by
selecting referenced cells. PC World magazine has called VisiCalc the
first electronic spreadsheet.

Bricklin has spoken of watching his university professor create a table

of calculation results on a blackboard. When the professor found an
error, he had to tediously erase and rewrite a number of sequential
entries in the table, triggering Bricklin to think that he could replicate
the process on a computer, using the blackboard as the model to view
results of underlying formulas. His idea became VisiCalc, the first

95
MBA 757 DECISION SUPPORT SYSTEM

application that turned the personal computer from a hobby for

computer enthusiasts into a business tool.

96
MBA 757 DECISION SUPPORT SYSTEM

Screenshot of VisiCalc, the First PC Spreadsheet

VisiCalc went on to become the first "killer app", an application that

was so compelling: people would buy a particular computer just to own
it. In this case the computer was the Apple II, and VisiCalc was no small
part in that machine's success. The program was later ported to a number
of other early computers, notably CP/M machines, the Atari 8-bit family
and various Commodore platforms. Nevertheless, VisiCalc remains best
known as "an Apple II program".

Lotus 1-2-3 and Other MS-DOS Spreadsheets

The acceptance of the IBM PC following its introduction in August,

1981, began slowly, because most of the programs available for it were
ports from other 8-bit platforms. Things changed dramatically with the
introduction of Lotus 1-2-3 in November, 1982, and release for sale in
January, 1983. It became that platform's killer app, and drove sales of
the PC due to the improvements in speed and graphics compared to
VisiCalc.

Lotus 1-2-3, along with its competitor Borland Quattro, soon displaced
VisiCalc. Lotus 1-2-3 was released on January 26, 1983, started
outselling then-most-popular VisiCalc the very same year, and for a
number of years was the leading spreadsheet for DOS.

Microsoft Excel

Microsoft had been developing Excel on the Macintosh platform for

several years at this point, where it had developed into a fairly powerful
system. A port of Excel to Windows 2.0 resulted in a fully functional
Windows spreadsheet. The more robust Windows 3.x platforms of the
early 1990s made it possible for Excel to take market share from Lotus.
By the time Lotus responded with usable Windows products, Microsoft
had started compiling their Office suite. Starting in the mid 1990s
continuing through 2008, Microsoft Excel has dominated the
commercial spreadsheet market.

Apple Numbers

Number is Apple Inc.'s spreadsheet software, part of iWork. It focuses

on usability and the elegance of chart presentation. Numbers completed
Apple's productivity suite, making it a viable competitor to Microsoft
Office. It lacks features such as pivot tables.

97
MBA 757 DECISION SUPPORT SYSTEM

OpenOffice.org

OpenOffice.org Calc is a freely available, open-source program

modelled after Microsoft Excel. Calc can both open and save in the
Excel (XLS) file format. Calc can be acquired as both an installation file
and a portable program, capable of being run from a device such as a
USB memory drive. It can be downloaded from the OpenOffice.org
website.

Web Based Spreadsheets

With the advent of advanced web technologies such as Ajax circa 2005,
a new generation of online spreadsheets has emerged. Equipped with a
rich Internet application user experience, the best web based online
spreadsheets have many of the features seen in desktop spreadsheet
applications. Some of them have strong multi-user collaboration
features. Some of them offer real time updates from remote sources such
as stock prices and currency exchange rates.

3.2 Use of Spreadsheets

The uses of spreadsheets are tremendously diverse. You can use

spreadsheet for on-the-moment numeric calculations that you don’t need
to save, for long-term projects that accumulate monthly or yearly data,
and for myriad other applications from billing invoices to preparing
financial statement and tax worksheet. In general, you use a spreadsheet
to deal with numeric data and especially to perform any kind of analysis
to aid in decision making.

Financial Analysis

If there is any one area where spreadsheets are truly pervasive, it is in

business. Here are few examples of how spreadsheets aid decision
making in businesses.

• The marketing department of a direct-sales company might use a

spreadsheet to keep track record of sales totals for its sales staff.
They can use the information to calculate commissions for the sales
staff and to project materials and product requirements for
purchasing and manufacturing departments.
• The purchasing department may use a spreadsheet to keep track of
purchases from vendors, including running totals of purchases from
individual vendors and prices paid for specific products.
• Employees in the manufacturing departments could use a
spreadsheet to keep a record of maintenance performed on

98
MBA 757 DECISION SUPPORT SYSTEM

equipment. They can also record receipts of goods from loading

docks and transfers of finished goods to a warehouse.
• The payroll department might use a spreadsheet for some types of
analysis, even if the payroll system is already automated. For
example, they might compile a list of employees who receive a car
allowance in addition to commissions, or calculate the balance of an
employee’s retirement account.
• The accounting department uses spreadsheet to calculate monthly
journal entries or to schedule account balances. They may also keep
track of the depreciation and book values of company assets, and
even prepare their monthly, quarterly, or annual financial statements
with a spreadsheet.
• Marketing executives can create impressive slide shows with graphs
of past and anticipated product sales. Finance executives can also use
a spreadsheet’s graphical capabilities to depict the company’s
financial strengths compared to those of others in the same industry,
and to forecast financial trends.

Engineering Analysis

Engineering is another profession that benefits from using spreadsheets

for numeric computations.

• A civil engineer might use a spreadsheet for determining the

dimensions of drainage channel for a given flow capacity, or to
calculate the stress on a concrete beam in a bridge, or to find the
weight of a road.
• Electrical engineers may use a spreadsheet to calculate voltages or
capacities in the design of electrical circuits, or to create three-
dimensional graphs of the output of a circuit.
• A mechanical engineer might use a spreadsheet to calculate the
geometric dimensions of objects or to calculate the heat absorption
or dissipation of a material being exposed to external pressures.

Graphics and Presentations

Spreadsheets are excellent tools for creating graphs and presentations

materials, because these capabilities are built into them. With many
spreadsheets, creating a graphic is as simple as using the mouse to select
a block of cells, and clicking a graph button.

99
MBA 757 DECISION SUPPORT SYSTEM

3.3 Concepts

Cells

A "cell" can be thought of as a box for holding a datum. A single cell is

usually referenced by its column and row (A2 would represent the cell
below containing the value 10). Its physical size can usually be tailored
for its content by dragging its height or width at box intersections (or for
entire columns or rows by dragging the column or rows headers).

My Spreadsheet
A B C D
01 value1 Value2 added multiplied
02 10 20 30 200

An array of cells is called a "sheet" or "worksheet". It is analogous to an

array of variables in a conventional computer program (although certain
unchanging values, once entered, could be considered, by the same
analogy, constants). In most implementations, many worksheets may be
located within a single spreadsheet. A worksheet is simply a subset of
the spreadsheet divided for the sake of clarity. Functionally, the
spreadsheet operates as a whole and all cells operate as global variables
within the spreadsheet ('read' access only except its own containing
cell).

A cell may contain a value or a formula, or it may simply be left empty.

By convention, formulas usually begin with = sign.

Values: A value can be entered from the computer keyboard by directly

typing into the cell itself. Alternatively, a value can be based on a
formula (see below), which might perform a calculation, display the
current date or time, or retrieve external data such as a stock quote or a
database value.

The Spreadsheet Value Rule: Computer scientist Alan Kay used the
term value rule to summarise a spreadsheet's operation: a cell's value
relies solely on the formula the user has typed into the cell. The formula
may rely on the value of other cells, but those cells are likewise
restricted to user-entered data or formulas. There are no 'side effects' to
calculating a formula: the only output is to display the calculated result
inside its occupying cell. There is no natural mechanism for
permanently modifying the contents of a cell unless the user manually

100
MBA 757 DECISION SUPPORT SYSTEM

modifies the cell's contents. In the context of programming languages,

this yields a limited form of first-order functional programming.

Automatic recalculation: A standard of spreadsheets since the mid 80s,

this optional feature eliminates the need to manually request the
spreadsheet program to recalculate values (nowadays typically the
default option unless specifically 'switched off' for large spreadsheets,
usually to improve performance). Some earlier spreadsheets required a
manual request to recalculate, since recalculation of large or complex
spreadsheets often reduced data entry speed. Many modern spreadsheets
still retain this option.

Real Time Update: This feature refers to updating a cell's contents

periodically when its value is derived from an external source - such as a
cell in another "remote" spreadsheet. For shared, web-based
spreadsheets, it applies to "immediately" updating cells that have been
altered by another user. All dependent cells have to be updated also.

Formula: Animation of a simple spreadsheet that multiplies values in

the left column by 2, then sums the calculated values from the right
column to the bottom-most cell. In this example, only the values in the
A column are entered (10, 20, 30), and the remainder of cells are
formulas. Formulas in the B column multiply values from the A column
using relative references, and the formula in B4 uses the SUM()
function to find the sum of values in the B1:B3 range.

A formula identifies the calculation needed to place the result in the cell
it is contained within. A cell containing a formula therefore has two
display components; the formula itself and the resulting value. The
formula is normally only shown when the cell is selected by "clicking"
the mouse over a particular cell; otherwise it contains the result of the
calculation.

A formula assigns values to a cell or range of cells, and typically has the
format:
=expressio
n
where the expression consists of:

• values, such as 2, 9.14 or 6.67E-11;

• references to other cells, such as, e.g., A1 for a single cell or B1:B3
for a range;
• arithmetic operators, such as +, -, *, /, and others;
• relational operators, such as >=, <, and others; and,
• functions, such as SUM(), TAN(), and many others.

101
MBA 757 DECISION SUPPORT SYSTEM

When a cell contains a formula, it often contains references to other

cells. Such a cell reference is a type of variable. Its value is the value of
the referenced cell or some derivation of it. If that cell in turn references
other cells, the value depends on the values of those. References can be
relative (e.g., A1, or B1:B3), absolute (e.g., $A$1, or $B$1:$B$3) or
mixed row-wise or column-wise absolute/relative (e.g., $A1 is column-
wise absolute and A$1 is row-wise absolute).

The available options for valid formulas depend on the particular

spreadsheet implementation but, in general, most arithmetic operations
and quite complex nested conditional operations can be performed by
most of today's commercial spreadsheets. Modern implementations also
offer functions to access custom-build functions, remote data, and
applications.

A formula may contain a condition (or nested conditions) - with or

without an actual calculation - and is sometimes used purely to identify
and highlight errors. In the example below, it is assumed the sum of a
column of percentages (A1 through A6) is tested for validity and an
explicit message put into the adjacent right hand cell.

=IF (SUM(A1:A6) > 100, "More than 100%", SUM(A1:A6))

A spreadsheet does not, in fact, have to contain any formulas at all, in
which case it could be considered merely a collection of data arranged in
rows and columns (a database) like a calendar, timetable or simple list.
Because of its ease of use, formatting and hyper-linking capabilities,
many spreadsheets are used solely for this purpose.

Locked Cell: Once entered, selected cells (or the entire spreadsheet) can
optionally be "locked" to prevent accidental overwriting. Typically this
would apply to cells containing formulas but might be applicable to cells
containing "constants" such as a kilogram/pounds conversion factor
(2.20462262 to eight decimal places).

Data Format: A cell or range can optionally be defined to specify how

the value is displayed. The default display format is usually set by its
initial content if not specifically previously set, so that for example
"31/12/2007" or "31 Jan 2007" would default to the cell format of
"date". Similarly adding a % sign after a numeric value would tag the
cell as a percentage cell format. The cell contents are not changed by
this format, only the displayed value.

Some cell formats such as "numeric" or "currency" can also specify the
number of decimal places.

102
MBA 757 DECISION SUPPORT SYSTEM

This can allow invalid operations (such as doing multiplication on a cell

containing a date), resulting in illogical results without an appropriate
warning.

Text Format: Each cell (like its counterpart the "word" in a word
processor) can be separately defined in terms of its displayed format.
Any cell or range of cells can be highlighted in several different ways
such as use of bold text, colour, font, text size and so on.

These attributes typically do not alter the data content in any way and
some formatting may be lost or altered when copying spreadsheet data
between different implementations or software versions. In some
implementations, the format may be conditional upon the data within the
cell - for example, a value may be displayed red if it is negative.

Named Cells: In most implementations, a cell can be "named" so that

even if the cell is "cut and pasted" to a new location within the
spreadsheet, its reference always remains intact. Names must be unique
within the spreadsheet and, once defined, can then be used instead of a
"normal" cell reference.

Cell Reference: A cell reference is the name of some cell in some

spreadsheet. Most cell references indicate another cell in the same
spreadsheet, but a cell reference can also refer to a cell in a different
sheet within the same spreadsheet, or (depending on the
implementation) to a cell in another spreadsheet entirely, or to a value
from a remote application.

A typical cell reference in "A1" style consists of one or two case-

insensitive letters to identify the column (if there are up to 256 columns:
A-Z and AA-IV) followed by a row number (e.g. in the range 1-65536).
Either part can be relative (it changes when the formula it is in is moved
or copied), or absolute (indicated with $ in front of the part concerned of
the cell reference). The older "R1C1" reference style consists of the
letter R, the row number, the letter C, and the column number; relative
row or column numbers are indicated by enclosing the number in square
brackets. Most current spreadsheets use the A1 style, some providing the
R1C1 style as a compatibility option.

When the computer calculates a formula in one cell to update the

displayed value of that cell, cell reference(s) in that cell, naming some
other cell(s), cause the computer to fetch the value of the named cell(s).
A cell on the same "sheet" is usually addressed as:-
=A1
A cell on a different sheet of the same spreadsheet is usually addressed
as:-

103
MBA 757 DECISION SUPPORT SYSTEM

=SHEET2!A1 (that is; the first cell in sheet 2 of same spreadsheet).

Some spreadsheet implementations allow a cell references to another

spreadsheet (not the current open and active file) on the same computer
or a local network. It may also refer to a cell in another open and active
spreadsheet on the same computer or network that is defined as
shareable. These references contain the complete filename, such as:-
='C:\Documents and Settings\Username\My spreadsheets\[main
sheet]Sheet1!A1

In a spreadsheet, references to cells are automatically updated when new

rows or columns are inserted or deleted. Care must be taken however
when adding a row immediately before a set of column totals to ensure
that the totals reflect the additional rows values - which often they do
not!

A circular reference occurs when the formula in one cell has a reference
that directly -- or indirectly, through a chain of references, each one
pointing to another cell that has another reference to the next cell on the
chain -- points to the one cell. Many common kinds of errors cause such
circular references. However, there are some valid techniques that use
such circular references. Such techniques, after many recalculations of
the spreadsheet, (usually) converge on the correct values for those cells.

Cell Ranges: A reference to a range of cells is typically of the form

(A1:A6) which specifies all the cells in the range A1 through to A6. A
formula such as "= SUM (A1:A6)" would add all the cells specified and
put the result in the cell containing the formula itself.

Sheets

In the earliest spreadsheets, cells were a simple two-dimensional grid.

Over time, the model has been expanded to include a third dimension,
and in some cases a series of named grids, called sheets. The most
advanced examples allow inversion and rotation operations which can
slice and project the data set in various ways.

Remote Spreadsheet

Whenever a reference is made to a cell or group of cells that are not

located within the current physical spreadsheet file, it is considered as
accessing a "remote" spreadsheet. The contents of the referenced cell
may be accessed either on first reference with a manual update or more
recently in the case of web based spreadsheets, as a near real time value
with a specified automatic refresh interval.

104
MBA 757 DECISION SUPPORT SYSTEM

Charts

An example is histogram of the heights of 31 Black Cherry trees.

Many spreadsheet applications permit charts, graphs or histograms to be
generated from specified groups of cells which are dynamically re-built
as cell contents change. The generated graphic component can either be
embedded within the current sheet or added as a separate object.

3.4 Shortcomings

While spreadsheets are a great step forward in quantitative modelling,

they have deficiencies. At the level of overall user benefits, spreadsheets
have three main shortcomings.

• Spreadsheets have significant reliability problems. Research studies

estimate that roughly 94% of spreadsheets deployed in the field
contain errors, and 5.2% of cells in unedited spreadsheets contain
errors.
• The practical expressiveness of spreadsheets is limited. Several
factors contribute to this limitation. Implementing a complex model
requires implementing detailed layouts, cell-at-a-time. Authors have
difficulty remembering the meanings of hundreds or thousands of
cell addresses that appear in formula.
• Productivity of spreadsheet modellers is reduced by the cell-level
focus of spreadsheets. Even conceptually simple changes in
spreadsheets (such as changing starting or ending time or time grain,
adding new members or a level of hierarchy to a dimension, or
changing one conceptual formula that is represented as hundreds of
cell formulas) often require large numbers of manual cell-level
operations (such as inserting or deleting cells/rows/columns, editing
and copying formulas, re-laying out worksheets). Each of these
manual corrections increases the risk of introducing further mistakes.

These three deficiencies in high-level benefits have deeper causes that,

ironically, flow directly from the signature strength of spreadsheets (that
they capture the structure of models in terms of WYSIWYG sheet
layout for authors and report users).

• Spreadsheets capture model logic in terms of sheet layout, especially

contiguous layout of cells in a table. Spreadsheets have weak or
nonexistent methods to capture higher level structures such as named
variables, segmentation dimensions, and time series.
• Formulas are subordinated to the cell layout. This forces the sheet
layout to carry the structure of the model, not variables and formulas
that relate variables. This also causes a large proliferation of cells,
formulas and cell-level tasks even when only a few basic concepts

105
MBA 757 DECISION SUPPORT SYSTEM

are involved in a model. This forces authors to think and work at the
level of cells instead of at the level of the natural concepts and
structures of the model.
• Formulas expressed in terms of cell addresses are hard to keep
straight and hard to audit. Research shows that spreadsheet auditors
who check numerical results and cell formulas find no more errors
than auditors who only check numerical results.
• Proliferation of error-prone manual cell-level operations contributes
to all three of the high-level problems listed above.

3.5 Spreadsheets as Decision-Making Tools in Financial

Modelling

Financial modelling is the process of simulating the financial

performance of a company using spreadsheet. The purpose of the
financial model is to project the future financial performance of the
company. Spreadsheet software makes this projection possible because
it lets you see the effect of plugging different numbers into the formulas
that make up the model.

A simple example of financial model may involve that you run a bicycle
messenger service business. The messengers are paid 50 percent of the
price of each delivery. Other than the salaries, the only operating
expenses are office rent, utilities (electricity, telephone, and garbage), a
computer system, and the two-way radio system that is used to
communicate with the messengers.

Using a spreadsheet, you can plug into different sales volumes and
determine the profit you would make. The information might be vital
when planning to move offices or to buy a new two-way radio system.

Naturally, financial models for larger corporations can be far more

complex. The most common type of model has areas in the spreadsheet
for each of the primary financial statements-balance sheet, income
statement, and cash flow statements. Each of these financial statements
might be linked to other spreadsheets, so the data can be imported
automatically and analysed there.

The whole model can get complicated, but the goal is still the same. It
makes you see how different data affects the profitability of the
company. Results of financial model help to make basic business
decisions such as:

• How much inventory can a company afford to keep on hand?

• How big a bonus should employees receive?
• Is it better to find less expensive parts or to raise prices?

106
MBA 757 DECISION SUPPORT SYSTEM

In the old days, the financial models used to answer these questions
were created by accountants or financial manager of a company such as
the chief financial officer. But with the ever-widening use of computers,
all kinds of business people are now creating and gaining from financial
models. Large businesses assume that their new employees are
sufficiently adept with spreadsheet to create financial models. Owners
and managers of small businesses are equally likely to use such models
to help them make decisions. Given the great value that a financial
model can have when making business decisions, and the ease with
which these models can be made with modern spreadsheet software, the
ability to create financial model has become an essential and basic
business skill.

4.0 CONCLUSION

A spreadsheet is a tool for calculating, and evaluating numbers. It also

offers capabilities for creating reports and presentations to communicate
what analysis reveals. Spreadsheet software makes these tasks easy by
providing a visual framework to work within, and providing the tools
that is needed to make number calculating a breeze. Spreadsheet is an
excellent decision support system tool that cuts across disciplines.

5.0 SUMMARY

• A spreadsheet is a computer application that simulates a paper

worksheet. It displays multiple cells that together make up a grid
consisting of rows and columns, each cell containing either
alphanumeric text or numeric values.
• The word "spreadsheet" came from "spread" in its sense of a
newspaper or magazine item (text and/or graphics) that covers two
facing pages, extending across the centre fold and treating the two
pages as one large one.
• The uses of spreadsheets are tremendously diverse. You can use
spreadsheet for on-the-moment numeric calculations that you don’t
need to save, for long-term projects that accumulate monthly or
yearly data, and for myriad of other applications from billing
invoices to preparing financial statement and tax worksheet.
• A "cell" can be thought of as a box for holding a datum. A single
cell is usually referenced by its column and row (A2 would represent
the cell below containing the value 10).
• While spreadsheets are a great step forward in quantitative
modelling, they have deficiencies. At the level of overall user
benefits, spreadsheets have three main shortcomings.
• Financial modelling is the process of simulating the financial
performance of a company using spreadsheet. The purpose of the

107
MBA 757 DECISION SUPPORT SYSTEM

financial model is to project the future financial performance of the

company.

6.0 TUTOR-MARKED ASSIGNMENT

Mention and discuss briefly the uses of spreadsheet in financial analysis.

7.0 REFERENCES/FURTHER READING

Norton, Peter (1995). Introduction to Computers. MacMillan/McGraw-

Hill.

108
MBA 757 DECISION SUPPORT SYSTEM

UNIT 4 EXECUTIVE INFORMATION SYSTEM I

CONTENTS

1.0 Introduction
2.0 Objectives
3.0 Main Content
3.1 History
3.2 Components
3.3 Applications
3.4 Advantages and Disadvantages
3.5 Contents of EIS
3.6 Future Trends
4.0 Conclusion
5.0 Summary
6.0 Tutor-Marked Assignment
7.0 References/Further Reading

1.0 INTRODUCTION

An Executive Information System (EIS) is a type of management

information system intended to facilitate and support the information
and decision making needs of senior executives by providing easy
access to both internal and external information relevant to meeting the
strategic goals of the organisation. It is commonly considered as a
specialised form of a Decision Support System (DSS).

The emphasis of EIS is on graphical displays and easy-to-use user

interfaces. They offer strong reporting and drill-down capabilities. In
general, EIS are enterprise-wide DSS that help top-level executives
analyse, compare, and highlight trends in important variables so that
they can monitor performance and identify opportunities and problems.
EIS and data warehousing technologies are converging in the
marketplace.

In recent years, the term EIS has lost popularity in favour of Business
Intelligence (with the sub areas of reporting, analytics, and digital
dashboards).

2.0 OBJECTIVES

At the end of this unit, the students should be able to:

• define and understand the concept of executive information system

(EIS)

109
MBA 757 DECISION SUPPORT SYSTEM

• evaluate the development and history of EIS

• identify the major components and contents of EIS
• outline the various applications of EIS in sectors of business
• answer the questions of advantages and disadvantages associated
with EIS
• explain what the future holds for EIS.

3.0 MAIN CONTENT

3.1 History

Traditionally, executive information systems were developed as

mainframe computer-based programs. The purpose was to package a
company’s data and to provide sales performance or market research
statistics for decision makers, such as financial officers, marketing
directors, and chief executive officers, who were not necessarily well
acquainted with computers. The objective was to develop computer
applications that would highlight information to satisfy senior
executives’ needs. Typically, an EIS provides data that would only need
to support executive level decisions instead of the data for all the
company.

Today, the application of EIS is not only in typical corporate

hierarchies, but also at personal computers on a local area network. EIS
now cross computer hardware platforms and integrate information
stored on mainframes, personal computer systems, and minicomputers.
As some client service companies adopt the latest enterprise information
systems, employees can use their personal computers to get access to the
company’s data and decide which data are relevant for their decision
makings. This arrangement makes all users able to customise their
access to the proper company’s data and provide relevant information to
both upper and lower levels in companies.

3.1 Components

The components of an EIS can typically be classified as:

Hardware

When talking about hardware for an EIS environment, we should focus

on the hardware that meet the executive’s needs. The executive must be
put first and the executive’s needs must be defined before the hardware
can be selected. The basic computer hardware needed for a typical EIS
includes four components:

110
MBA 757 DECISION SUPPORT SYSTEM

(1) Input data-entry devices. These devices allow the executive to

enter, verify, and update data immediately;
(2) The central processing unit (CPU), which is the kernel because
it controls the other computer system components;
(3) Data storage files. The executive can use this part to save useful
business information, and this part also helps the executive to
search historical business information easily;
(4) Output devices, which provide a visual or permanent record for
the executive to save or read. This device refers to the visual
output device or printer.

In addition, with the advent of local area networks (LAN), several EIS
products for networked workstations became available. These systems
require less support and less expensive computer hardware. They also
increase access of the EIS information to many more users within a
company.

Software

Choosing the appropriate software is vital to design an effective EIS.

Therefore, the software components and how they integrate the data into
one system are very important. The basic software needed for a typical
EIS includes four components:

1. Text base software. The most common form of text is probably

documents;
2. Database. Heterogeneous databases residing on a range of vendor-
specific and open computer platforms help executives access both
internal and external data;
3. Graphic base. Graphics can turn volumes of text and statistics into
visual information for executives. Typical graphic types are: time
series charts, scatter diagrams, maps, motion graphics, sequence
charts, and comparison-oriented graphs (i.e., bar charts);
4. Model base. The EIS models contain routine and special statistical,
financial, and other quantitative analysis.

Perhaps a more difficult problem for executives is choosing from a

range of highly technical software packages. Ease of use, responsiveness
to executives' requests, and price are all reasonable considerations.
Further, it should be considered whether the package can run on existing
hardware.

User Interface

An EIS needs to be efficient to retrieve relevant data for decision

makers, so the user interface is very important. Several types of

111
MBA 757 DECISION SUPPORT SYSTEM

interfaces can be available to the EIS structure, such as scheduled

reports, questions/answers, menu driven, command language, natural
language, and input/output. It is crucial that the interface must fit the
decision maker’s decision-making style. If the executive is not
comfortable with the information questions/answers style, the EIS will
not be fully utilised. The ideal interface for an EIS would be simple to
use and highly flexible, providing consistent performance, reflecting the
executive’s world, and containing help information.

Telecommunication

As decentralising is becoming the current trend in companies,

telecommunications will play a pivotal role in networked information
systems. Transmitting data from one place to another has become
crucial for establishing a reliable network. In addition,
telecommunications within an EIS can accelerate the need for access to
distributed data.

3.3 Applications

EIS enables executives to find those data according to user-defined

criteria and promote information-based insight and understanding.
Unlike a traditional management information system presentation, EIS
can distinguish between vital and seldom-used data, and track different
key critical activities for executives, which are helpful in evaluating if
the company is meeting its corporate objectives. After realising its
advantages, people have applied EIS in many areas, especially, in
manufacturing, marketing, and finance areas.

Manufacturing

Basically, manufacturing is the transformation of raw materials into

finished goods for sale, or intermediate processes involving the
production or finishing of semi-manufactures. It is a large branch of
industry and of secondary production. Manufacturing operational
control focuses on day-to-day operations, and the central idea of this
process is effectiveness and efficiency. To produce meaningful
managerial and operational information for controlling manufacturing
operations, the executive has to make changes in the decision processes.
EIS provides the evaluation of vendors and buyers, the evaluation of
purchased materials and parts, and analysis of critical purchasing areas.
Therefore, the executive can oversee and review purchasing operations
effectively with EIS. In addition, because production planning and
control depends heavily on the plant’s data base and its communications
with all manufacturing work centres, EIS also provides an approach to
improve production planning and control.

112
MBA 757 DECISION SUPPORT SYSTEM

Marketing

In an organisation, marketing executives’ role is to create the future.

Their main duty is managing available marketing resources to create a
more effective future. For this, they need make judgments about risk and
uncertainty of a project and its impact on company in the short and long
term. To assist marketing executives in making effective marketing
decisions, an EIS can be applied. EIS provides an approach to sales
forecasting, which can allow the market executive to compare sales
forecast with past sales. EIS also offers an approach to product price,
which is found in venture analysis. The market executive can evaluate
pricing as related to competition along with the relationship of product
quality with price charged. In summary, EIS software package enables
marketing executives to manipulate the data by looking for trends,
performing audits of the sales data, and calculating totals, averages,
changes, variances, or ratios. All of these sales analysis functions help
marketing executives to make final decisions.

Financial

A financial analysis is one of the most important steps to companies

today. The executive needs to use financial ratios and cash flow
analysis to estimate the trends and make capital investment decisions.
An EIS is a responsibility-oriented approach that integrates planning or
budgeting with control of performance reporting, and it can be
extremely helpful to finance executives. Basically, EIS focuses on
accountability of financial performance and it recognises the importance
of cost standards and flexible budgeting in developing the quality of
information provided for all executive levels. EIS enables executives to
focus more on the long-term basis of current year and beyond, which
means that the executive not only can manage a sufficient flow to
maintain current operations but also can figure out how to expand
operations that are contemplated over the coming years. Also, the
combination of EIS and EDI environment can help cash managers to
review the company’s financial structure so that the best method of
financing for an accepted capital project can be concluded. In addition,
the EIS is a good tool to help the executive to review financial ratios,
highlight financial trends and analyse a company’s performance and its
competitors.

3.4 Advantages and Disadvantages

Advantages

113
MBA 757 DECISION SUPPORT SYSTEM

• Easy for upper-level executives to use, extensive computer

experience is not required in operations
• Provides timely delivery of company summary information
• Information that is provided is better understood
• Filters data for management
• Improves tracking of information

Disadvantages

• Functions are limited, cannot perform complex calculations

• Hard to quantify benefits and to justify implementation of an EIS
• Executives may encounter information overload
• System may become slow, large, and hard to manage
• Difficult to keep current data
• May lead to less reliable and insecure data
• Small companies may encounter excessive costs for implementation

3.4 Contents of EIS

A general answer to the question of what data is appropriate for
inclusion in an Executive Information System is "whatever is interesting
to executives." While this advice is rather simplistic, it does reflect the
variety of systems currently in use. Executive Information Systems in
government have been constructed to track data about Ministerial
correspondence, case management, worker productivity, finances, and
human resources to name only a few. Other sectors use EIS
implementations to monitor information about competitors in the news
media and databases of public information in addition to the traditional
revenue, cost, volume, sales, market share and quality applications.
Frequently, EIS implementations begin with just a few measures that are
clearly of interest to senior managers, and then expand in response to
questions asked by those managers as they use the system. Over time,
the presentation of this information becomes stale, and the information
diverges from what is strategically important for the organisation. A
"Critical Success Factors" approach is recommended by many
management theorists (Daniel, 1961, Crockett, 1992, Watson and
Frolick, 1992). Practitioners such as Vandenbosch (1993) found that:

While our efforts usually met with initial success, we often

found that after six months to a year, executives were
almost as bored with the new information as they had
been with the old. A strategy we developed to rectify this
problem required organisations to create a report of the
month. That is, in addition to the regular information
provided for management committee meetings, the CEO
was charged with selecting a different indicator to focus

114
MBA 757 DECISION SUPPORT SYSTEM

on each month (Vandenbosch, 1993, pp. 8-9).

While the above indicates that selection of data for inclusion in an EIS is
difficult, there are several guidelines that help to make that assessment.
A practical set of principles to guide the design of measures and
indicators to be included in an EIS is presented below (Kelly, 1992b).
For a more detailed discussion of methods for selecting measures that
reflect organisational objectives, see the section "EIS and Organisational
Objectives."

EIS measures must be easy to understand and collect. Wherever

possible, data should be collected naturally as part of the process of
work. An EIS should not add substantially to the workload of managers
or staff.

EIS measures must be based on a balanced view of the organisation's

objective. Data in the system should reflect the objectives of the
organisation in the areas of productivity, resource management, quality
and customer service.

Performance indicators in an EIS must reflect everyone's contribution in

a fair and consistent manner. Indicators should be as independent as
possible from variables outside the control of managers.

EIS measures must encourage management and staff to share ownership

of the organisation's objectives. Performance indicators must promote
both team-work and friendly competition. Measures will be meaningful
for all staff; people must feel that they, as individuals, can contribute to
improving the performance of the organisation.

EIS information must be available to everyone in the organisation. The

objective is to provide everyone with useful information about the
organisation's performance. Information that must remain confidential
should not be part of the EIS or the management system of the
organisation.

EIS measures must evolve to meet the changing needs of the

organisation.

3.6 Future Trends

The future of executive info systems will not be bound by mainframe

computer systems. This trend allows executives escaping from learning
different computer operating systems and substantially decreases the
implementation costs for companies. Because utilising existing software
applications lies in this trend, executives will also eliminate the need to
learn a new or special language for the EIS package. Future executive

115
MBA 757 DECISION SUPPORT SYSTEM

information systems will not only provide a system that supports senior
executives, but also contain the information needs for middle managers.
The future executive information systems will become diverse because
of integrating potential new applications and technology into the
systems, such as incorporating artificial intelligence (AI) and integrating
multimedia characteristics and ISDN technology into an EIS.

4.0 CONCLUSION

An executive information system is an information system which gives

the executive easy access to key internal and external data. EIS has been
made possible by the increasing cheapness and sophistication of
microcomputer and network technology. An EIS is not only a tool for
analysis, but also a tool for interrogating data. The concept of EIS is the
same as in the emerging concept of business intelligence.

5.0 SUMMARY

• The future of executive info systems will not be bound by mainframe

computer systems. This trend allows executives escaping from
learning different computer operating systems and substantially
decreases the implementation costs for companies.
• Traditionally, executive information systems were developed as
mainframe computer-based programs. The purpose was to package a
company’s data and to provide sales performance or market research
statistics for decision makers, such as financial officers, marketing
directors, and chief executive officers, who were not necessarily well
acquainted with computers.
• As decentralising is becoming the current trend in companies,
telecommunications will play a pivotal role in networked
information systems.
• Choosing the appropriate software is vital to design an effective EIS.
• When talking about hardware for an EIS environment, we should
focus on the hardware that meets the executive’s needs.
• In an organisation, marketing executives’ role is to create the future.
Their main duty is managing available marketing resources to create
a more effective future. For this, they need make judgments about
risk and uncertainty of a project and its impact on company in the
short and long term.
• EIS enables executives to find those data according to user-defined
criteria and promote information-based insight and understanding.
• A general answer to the question of what data is appropriate for
inclusion in an Executive Information System is "whatever is

116
MBA 757 DECISION SUPPORT SYSTEM

interesting to executives." While this advice is rather simplistic, it

does reflect the variety of systems currently in use.

6.0 TUTOR-MARKED ASSIGNMENT

1. Briefly discuss software as a component of EIS

2. Mention 5 disadvantages of EIS

7.0 REFERENCES/FURTHER READING

Thierauf, Robert J. (1994). Executive Information System: A Guide for

Senior Management and MIS Professionals. Quorum Books.

(January 1994). Executive Information Systems.

Salmeron, Jose L. and Herrero, Ines (July 2005). An AHP-Based

Methodology to Rank Critical Success Factors of Executive
Information Systems, Computer Standards & Interfaces, Volume
28, Issue 1, pp. 1-12.

Salmeron, Jose L. EIS (2003). Success: Keys and Difficulties in Major

Companies. Technovation Volume 23, Issue 1, pp. 35-38.

Salmeron, Jose L. EIS (2002). Evolution in Large Spanish Businesses.

Information & Management, Volume 40, Issue 1, pp. 41-50.

Salmeron, Jose L. (2002). EIS Profitability, Costs and Benefits: An

Evolutionary Approach. Industrial Management & Data
Systems,Volume 102, Issue 5-6, pp. 284-288.

Salmeron, Jose L. (2002). EIS Data: Findings from an Evolutionary

Study. Journal of Systems and Software, Volume 64, Issue 2, pp.
111-114.

117
MBA 757 DECISION SUPPORT SYSTEM

UNIT 5 IMPLEMENTING EXECUTIVE

INFORMATION SYSTEM

CONTENTS

1.0 Introduction
2.0 Objectives
3.0 Main Content
3.1 Purpose of EIS
3.2 Barriers to Effectiveness
3.3 Characteristics of Successful EIS Implementations
3.4 EIS and Organisational Objectives
4.0 Conclusion
5.0 Summary
6.0 Tutor-Marked Assignment
7.0 References/Further Reading

1.0 INTRODUCTION

An EIS is a tool that provides direct on-line access to relevant

information about aspects of a business that are of particular interest to
the senior manager.
Many senior managers find that direct on-line access to organisational
data is helpful. For example, Paul Frech, President of Lockheed-
Georgia, monitored employee contributions to company-sponsored
programs (United Way, blood drives) as a surrogate measure of
employee morale (Houdeshel and Watson, 1987). C. Robert Kidder,
CEO of Duracell, found that productivity problems were due to
salespeople in Germany wasting time calling on small stores and took
corrective action (Main, 1989).

Information systems have long been used to gather and store

information, to produce specific reports for workers, and to produce
aggregate reports for managers. However, senior managers rarely use
these systems directly, and often find the aggregate information to be of
little use without the ability to explore underlying details (Watson &
Rainer, 1991, Crockett, 1992).

An Executive Information System (EIS) is a tool that provides direct on-

line access to relevant information in a useful and navigable format.
Relevant information is timely, accurate, and actionable information
about aspects of a business that are of particular interest to the senior
manager. The useful and navigable format of the system means that it is
specifically designed to be used by individuals with limited time, limited
keyboarding skills, and little direct experience with computers. An EIS

118
MBA 757 DECISION SUPPORT SYSTEM

is easy to navigate so that managers can identify broad strategic issues,

and then explore the information to find the root causes of those issues.

Executive Information Systems differ from traditional information

systems in the following ways:

•are specifically tailored to executive's information needs

•are able to access data about specific issues and problems as well as
aggregate reports
•provide extensive on-line analysis tools including trend analysis,
exception reporting & "drill-down" capability
•access a broad range of internal and external data
•are particularly easy to use (typically mouse or touch-screen driven)
•are used directly by executives without assistance
•present information in a graphical form

2.0 OBJECTIVES

At the end of this unit, the students should be able to:

• differentiate EIS from traditional information systems

• identify the purposes of an EIS
• identify the numerous challenges to the effectiveness of EIS in an
organisation
• identify the major indices for an effective EIS implementation in
organisation.
• describe how EIS fits into organisational objectives.

3.0 MAIN CONTENT

3.1 Purpose of EIS

The primary purpose of an Executive Information System is to support

managerial learning about an organisation, its work processes, and its
interaction with the external environment. Informed managers can ask
better questions and make better decisions. Vandenbosch and Huff
(1992) from the University of Western Ontario found that Canadian
firms using an EIS achieved better business results if their EIS promoted
managerial learning. Firms with an EIS designed to maintain managers'
"mental models" were less effective than firms with an EIS designed to
build or enhance managers' knowledge.

This distinction is supported by Peter Senge in The Fifth Dimension. He

illustrates the benefits of learning about the behaviour of systems versus
simply learning more about their states. Learning more about the state of

119
MBA 757 DECISION SUPPORT SYSTEM

a system leads to reactive management fixes. Typically these reactions

feed into the underlying system behaviour and contribute to a downward
spiral. Learning more about system behaviour and how various system
inputs and actions interrelate will allow managers to make more
proactive changes to create long-term improvement.

A secondary purpose for an EIS is to allow timely access to information.

All of the information contained in an EIS can typically be obtained by a
manager through traditional methods. However, the resources and time
required to manually compile information in a wide variety of formats,
and in response to ever changing and ever more specific questions
usually inhibit managers from obtaining this information. Often, by the
time a useful report can be compiled, the strategic issues facing the
manager have changed, and the report is never fully utilised.

Timely access also influences learning. When a manager obtains the

answer to a question, that answer typically sparks other related questions
in the manager's mind. If those questions can be posed immediately, and
the next answer retrieved, the learning cycle continues unbroken. Using
traditional methods, by the time the answer is produced, the context of
the question may be lost, and the learning cycle will not continue. An
executive in Rockart & Treacy's 1982 study noted that:

Your staff really can't help you think. The problem with
giving a question to the staff is that they provide you with
the answer. You learn the nature of the real question you
should have asked when you muck around in the data (p.
9).

A third purpose of an EIS is commonly misperceived. An EIS has a

powerful ability to direct management attention to specific areas of the
organisation or specific business problems. Some managers see this as
an opportunity to discipline subordinates. Some subordinates fear the
directive nature of the system and spend a great deal of time trying to
outwit or discredit it. Neither of these behaviours is appropriate or
productive. Rather, managers and subordinates can work together to
determine the root causes of issues highlighted by the EIS.

The powerful focus of an EIS is due to the maxim "what gets measured
gets done." Managers are particularly attentive to concrete information
about their performance when it is available to their superiors. This
focus is very valuable to an organisation if the information reported is
actually important and represents a balanced view of the organisation's
objectives.

120
MBA 757 DECISION SUPPORT SYSTEM

Misaligned reporting systems can result in inordinate management

attention to things that are not important or to things which are
important but to the exclusion of other equally important things. For
example, a production reporting system might lead managers to
emphasise volume of work done rather than quality of work. Worse yet,
productivity might have little to do with the organisation's overriding
customer service objectives.

3.2 Barriers to Effectiveness

There are many ways in which an EIS can fail. Dozens of high profile,
high cost EIS projects have been cancelled, implemented and rarely
used, or implemented and used with negative results. An EIS is a high
risk project precisely because it is intended for use by the most powerful
people in an organisation. Senior managers can easily misuse the
information in the system with strongly detrimental effects on the
organisation. Senior managers can refuse to use a system if it does not
respond to their immediate personal needs or is too difficult to learn and
use.

Unproductive Organisational Behaviour Norms

Issues of organisational behaviour and culture are perhaps the most

deadly barriers to effective Executive Information Systems. Because an
EIS is typically positioned at the top of an organisation, it can create
powerful learning experiences and lead to drastic changes in
organisational direction. However, there is also great potential for
misuse of the information. Green, Higgins and Irving (1988) found that
performance monitoring can promote bureaucratic and unproductive
behaviour, can unduly focus organisational attention to the point where
other important aspects are ignored, and can have a strongly negative
impact on morale.

The key barrier to EIS effectiveness, therefore, is the way in which the
organisation uses the information in the system. Managers must be
aware of the dangers of statistical data, and be skilled at interpreting and
using data in an effective way. Even more important is the manager's
ability to communicate with others about statistical data in a non-
defensive, trustworthy, and constructive manner. Argyris (1991)
suggests a universal human tendency towards strategies that avoid
embarrassment or threat, and towards feelings of vulnerability or
incompetence. These strategies include:

•stating criticism of others in a way that you feel is valid but also in a
way that prevents others from deciding for themselves
•failing to include any data that others could use to objectively evaluate
your criticism

121
MBA 757 DECISION SUPPORT SYSTEM

•stating your conclusions in ways that disguise their logical implications

and denying those implications if they are suggested.

To make effective use of an EIS, mangers must have the self-confidence

to accept negative results and focus on the resolution of problems rather
than on denial and blame. Since organisations with limited exposure to
planning and targeting, data-based decision-making, statistical process
control, and team-based work models may not have dealt with these
behavioural issues in the past, they are more likely to react defensively
and reject an EIS.

Technical Excellence

An interesting result from the Vandenbosch & Huff (1988) study was
that the technical excellence of an EIS has an inverse relationship with
effectiveness. Systems that are technical masterpieces tend to be
inflexible, and thus discourage innovation, experimentation and mental
model development.

Flexibility is important because an EIS has such a powerful ability to

direct attention to specific issues in an organisation. A technical
masterpiece may accurately direct management attention when the
system is first implemented, but continue to direct attention to issues
that were important a year ago on its first anniversary. There is
substantial danger that the exploration of issues necessary for
managerial learning will be limited to those subjects that were important
when the EIS was first developed. Managers must understand that as the
organisation and its work changes, an EIS must continually be updated
to address the strategic issues of the day.

A number of explanations as to why technical masterpieces tend to be

less flexible are possible. Developers who create a masterpiece EIS may
become attached to the system and consciously or unconsciously
dissuade managers from asking for changes. Managers who are
uncertain that the benefits outweigh the initial cost of a masterpiece EIS
may not want to spend more on system maintenance and improvements.
The time required to create a masterpiece EIS may mean that it is
outdated before it is implemented.

While usability and response time are important factors in determining

whether executives will use a system, cost and flexibility are paramount.
A senior manager will be more accepting of an inexpensive system that
provides 20% of the needed information within a month or two than
with an expensive system that provides 80% of the needed information
after a year of development. The manager may also find that the
inexpensive system is easier to change and adapt to the evolving needs
of the business. Changing a large system would involve throwing away

122
MBA 757 DECISION SUPPORT SYSTEM

parts of a substantial investment. Changing the inexpensive system

means losing a few weeks of work. As a result, fast, cheap, incremental
approaches to developing an EIS increase the chance of success.

Technical Problems

Paradoxically, technical problems are also frequently reported as a

significant barrier to EIS success. The most difficult technical problem
-- that of integrating data from a wide range of data sources both inside
and outside the organisation -- is also one of the most critical issues for
EIS users. A marketing vice-president, who had spent several hundred
thousand dollars on an EIS, attended a final briefing on the system. The
technical experts demonstrated the many graphs and charts of sales
results, market share and profitability. However, when the vice-
president asked for a graph of market share and advertising expense
over the past ten years, the system was unable to access historical data.
The project was cancelled in that meeting.

The ability to integrate data from many different systems is important

because it allows managerial learning that is unavailable in other ways.
The president of a manufacturing company can easily get information
about sales and manufacturing from the relevant VPs. Unfortunately, the
information the president receives will likely be incompatible, and
learning about the ways in which sales and manufacturing processes
influence each other will not be easy. An EIS will be particularly
effective if it can overcome this challenge, allowing executives to learn
about business processes that cross organisational boundaries and to
compare business results in disparate functions.

Another technical problem that can kill EIS projects is usability. Senior
managers simply have the choice to stop using a system if they find it
too difficult to learn or use. They have very little time to invest in
learning the system, a low tolerance for errors, and initially may have
very little incentive to use it. Even if the information in the system is
useful, a difficult interface will quickly result in the manager assigning
an analyst to manipulate the system and print out the required reports.
This is counter-productive because managerial learning is enhanced by
the immediacy of the question - answer learning cycle provided by an
EIS. If an analyst is interacting with the system, the analyst will acquire
more learning than the manager, but will not be in a position to put that
learning to its most effective use.

Usability of Executive Information Systems can be enhanced through

the use of prototyping and usability evaluation methods. These methods
ensure that clear communication occurs between the developers of the
system and its users. Managers have an opportunity to interact with

123
MBA 757 DECISION SUPPORT SYSTEM

systems that closely resemble the functionality of the final system and
thus can offer more constructive criticism than they might be able to
after reading an abstract specification document. Systems developers
also are in a position to listen more openly to criticisms of a system
since a prototype is expected to be disposable. Several evaluation
protocols are available including observation and monitoring, software
logging, experiments and benchmarking, etc. (Preece et al, 1994). The
most appropriate methods for EIS design are those with an ethnographic
flavour because the experience base of system developers is typically so
different from that of their user population (senior executives).

Misalignment between Objectives and EIS

A final barrier to EIS effectiveness was mentioned earlier in the section

on purpose. As noted there, the powerful ability of an EIS to direct
organisational attention can be destructive if the system directs attention
to the wrong variables. There are many examples of this sort of
destructive reporting. Grant, Higgins and Irving (1988) report the
account of an employee working under a misaligned reporting system
thus:

I like the challenge of solving customer problems, but they

get in the way of hitting my quota. I'd like to get rid of the
telephone work. If (the company) thought dealing with
customers was important, I'd keep it; but if it's just going
to be production that matters, I'd gladly give all the calls
to somebody else.

Traditional cost accounting systems are also often misaligned with

organisational objectives, and placing these measures in an EIS will
continue to draw attention to the wrong things. Cost accounting
allocates overhead costs to direct labour hours. In some cases the
overhead burden on each direct labour hour is as much as 1000%. A
manager operating under this system might decide to sub-contract 100
hours of direct labor at $20 per hour. On the books, this $2,000 saving is
accompanied by $20,000 of savings in overhead. If the sub-contractor
charges $5,000 for the work, the book savings are $2,000 + $20,000 -
$5,000 = $17,000. In reality, however, the overhead costs for an idle
machine in a factory do not go down much at all. The sub-contract
actually ends up costing $5,000 - $2,000 = $3,000. (Peters, 1987)

124
MBA 757 DECISION SUPPORT SYSTEM

3.3 Characteristics of Successful EIS Implementations

Find an Appropriate Executive Champion

EIS projects that succeed do so because at least one member of the

senior management team agrees to champion the project. The executive
champion need not fully understand the technical issues, but must be a
person who works closely with all of the senior management team and
understands their needs, work styles and their current methods of
obtaining organisational information. The champion's commitment must
include a willingness to set aside time for reviewing prototypes and
implementation plans, influencing and coaching other members of the
senior management team, and suggesting modifications and
enhancements to the system.

Deliver a Simple Prototype Quickly

Executives judge a new EIS on the basis of how easy it is to use and
how relevant the information in the system is to the current strategic
issues in the organisation. As a result, the best EIS projects begin as a
simple prototype, delivered quickly, that provides data about at least one
critical issue. If the information delivered is worth the hassle of learning
the system, a flurry of requirements will shortly be generated by
executives who like what they see, but want more. These requests are
the best way to plan an EIS that truly supports the organisation, and are
more valuable than months of planning by a consultant or analyst.

One caveat concerning the simple prototype approach is that executive

requests will quickly scatter to questions of curiosity rather than strategy
in an organisation where strategic direction and objectives are not
clearly defined. A number of methods are available to support
executives in defining business objectives and linking them to
performance monitors in an EIS. These are discussed further in the
section on EIS and Organisational Objectives below.

Involve Your Information Systems Department

In some organisations, the motivation for an EIS project arises in the

business units quite apart from the traditional information systems (IS)
organisation. Consultants may be called in, or managers and analysts in
the business units may take the project on without consulting or
involving IS. This is a serious mistake. Executive Information Systems
rely entirely on the information contained in the systems created and
maintained by this department. IS professionals know best what
information is available in an organisation's systems and how to get it.
They must be involved in the team. Involvement in such a project can

125
MBA 757 DECISION SUPPORT SYSTEM

also be beneficial to IS by giving them a more strategic perspective on

how their work influences the organisation.

Communicate & Train to Overcome Resistance

A final characteristic of successful EIS implementations is that of

communication. Executive Information Systems have the potential to
drastically alter the prevailing patterns of organisational communication
and thus will typically be met with resistance. Some of this resistance is
simply a matter of a lack of knowledge. Training on how to use statistics
and performance measures can help. However, resistance can also be
rooted in the feelings of fear, insecurity and cynicism experienced by
individuals throughout the organisation. These attitudes can only be
influenced by a strong and vocal executive champion who consistently
reinforces the purpose of the system and directs the attention of the
executive group away from unproductive and punitive behaviours.

EIS and Organisational Culture

Henry Mintzberg (1972) has argued that impersonal statistical data is

irrelevant to managers. John Dearden (1966) argued that the promise of
real-time management information systems was a myth and would never
be of use to top managers. Grant, Higgins, and Irving (1988) argue that
computerised performance monitors undermine trust, reduce autonomy
and fail to illuminate the most important issues.

Many of these arguments against EISs have objective merit. Managers

really do value the tangible tidbits of detail they encounter in their daily
interactions more highly than abstract numerical reports. Rumours
suggest a future, while numbers describe a past. Conversations are rich
in detail and continuously probe the reasons for the situation, while
statistics are vague approximations of reality. When these vague
approximations are used to intimidate or control behaviour rather than to
guide learning, they really do have a negative impact on the
organisation.

Yet both of these objections point to a deeper set of problems -- the

assumptions, beliefs, values and behaviours that people in the
organisation hold and use to respond to their environment. Perhaps
senior managers find statistical data to be irrelevant because they have
found too many errors in previous reports? Perhaps people in the
organisation prefer to assign blame rather than discover the true root
cause of problems. The culture of an organisation can have a dramatic
influence on the adoption and use of an Executive Information System.
The following cultural characteristics will contribute directly to the
success or failure of an EIS project.

126
MBA 757 DECISION SUPPORT SYSTEM

Learning vs Blaming: A learning organisation is one that seeks first to

understand why a problem occurred, and not who is to blame. It is a
common and natural response for managers to try to deflect
responsibility for a problem on to someone else. An EIS can help to do
this by indicating very specifically who failed to meet a statistical target,
and by how much. A senior manager, armed with EIS data, can
intimidate and blame the appropriate person. The blamed person can
respond by questioning the integrity of the system, blaming someone
else, or even reacting in frustration by slowing work down further.

In a learning organisation, any unusual result is seen as an opportunity

to learn more about the business and its processes. Managers who find
an unusual statistic explore it further, breaking it down to understand its
components and comparing it with other numbers to establish cause and
effect relationships. Together as a team, management uses numerical
results to focus learning and improve business processes across the
organisation. An EIS facilitates this approach by allowing instant
exploration of a number, its components and its relationship to other
numbers.

Continuous Improvement vs Crisis Management: Some

organisations find themselves constantly reacting to crises, with little
time for any proactive measures. Others have managed to respond to
each individual crisis with an approach that prevents other similar
problems in the future. They are engaged in a continual cycle of
improving business practices and finding ways to avoid crisis.
Crises in government are frequently caused by questions about
organisational performance raised by an auditor, the Minister, or
members of the Opposition. An EIS can be helpful in responding to this
sort of crisis by providing instant data about the actual facts of the
situation. However, this use of the EIS does little to prevent future
crises.

An organisational culture in which continual improvement is the norm

can use the EIS as an early warning system pointing to issues that have
not yet reached the crisis point, but are perhaps the most important areas
on which to focus management attention and learning. Organisations
with a culture of continuous improvement already have an appetite for
the sort of data an EIS can provide, and thus will exhibit less resistance.

Team Work vs Hierarchy: An EIS has the potential to substantially

disrupt an organisation that relies upon adherence to a strict chain of
command. The EIS provides senior managers with the ability to micro-
manage details at the lowest levels in the organisation. A senior manger
with an EIS report who is surprised at the individual results of a front-
line worker might call that person directly to understand why the result

127
MBA 757 DECISION SUPPORT SYSTEM

is unusual. This could be very threatening for the managers between the
senior manager and the front-line worker. An EIS can also provide
lower level managers with access to information about peer performance
and even the performance of their superiors.

Organisations that are familiar with work teams, matrix managed

projects and other forms of interaction outside the chain of command
will find an EIS less disruptive. Senior managers in these organisations
have learned when micro-management is appropriate and when it is not.
Middle managers have learned that most interactions between their
superiors and their staff are not threatening to their position. Workers
are more comfortable interacting with senior managers when the need
arises, and know what their supervisor expects from them in such an
interaction.

Data-based Decisions vs Decisions in a Vacuum: The total quality

movement, popular in many organisations today, emphasises a set of
tools referred to as Statistical Process Control (SPC). These analytical
tools provide managers and workers with methods of understanding a
problem and finding solutions rather than allocating blame and passing
the buck. Organisations with training and exposure to SPC and
analytical tools will be more open to an EIS than those who are
suspicious of numerical measures and the motives of those who use
them.

It should be noted that data-based decision making does not deny the
role of intuition, experience, or negotiation amongst a group. Rather, it
encourages decision-makers to probe the facts of a situation further
before coming to a decision. Even if the final decision contradicts the
data, chances are that an exploration of the data will help the decision-
maker to understand the situation better before a decision is reached. An
EIS can help with this decision-making process.

Information Sharing vs Information Hoarding: Information is power

in many organisations, and managers are motivated to hoard information
rather than to share it widely. For example, managers may hide
information about their own organisational performance, but jump at
any chance to see information about performance of their peers.

A properly designed EIS promotes information sharing throughout the

organisation. Peers have access to information about each other's
domain; junior managers have information about how their performance
contributes to overall organisational performance. An organisation that
is comfortable with information sharing will have developed a set of
"good manners" for dealing with this broad access to information. These
behavioural norms are key to the success of an EIS.

128
MBA 757 DECISION SUPPORT SYSTEM

Specific Objectives vs Vague Directions: An organisation that has

experience developing and working toward Specific, Measurable,
Achievable and Consistent (SMAC) objectives will also find an EIS to
be less threatening. Many organisations are uncomfortable with specific
performance measures and targets because they believe their work to be
too specialised or unpredictable. Managers in these organisations tend to
adopt vague generalisations and statements of the exceedingly obvious
in place of SMAC objectives that actually focus and direct
organisational performance. In a few cases, it may actually be true that
numerical measures are completely inappropriate for a few aspects of
the business. In most cases, managers with this attitude have a poor
understanding of the purpose of objective and target-setting exercises.
Some business processes are more difficult to measure and set targets
for than others. Yet almost all business processes have at least a few
characteristics that can be measured and improved through
conscientious objective setting. (See the following section on EIS and
Organisational Objectives.)

3.4 EIS and Organisational Objectives

A number of writers have discovered that one of the major difficulties

with EIS implementations is that the information contained in the EIS
either does not meet executive requirements, or meets executive
requirements, but fails to guide the organisation towards its objectives.
As discussed earlier, organisations that are comfortable in establishing
and working towards Specific, Measurable, Achievable, and Consistent
(SMAC) objectives will find it easier to create an EIS that actually
drives organisational performance. Yet even these organisations may
have difficulty because their stated objectives do not represent all of the
things that are important.

Crockett (1992) suggests a four step process for developing EIS

information requirements based on a broader understanding of
organisational objectives. The steps are:

(1) Identify critical success factors and stakeholder expectations,

(2) Document performance measures that monitor the critical success
factors and stakeholder expectations,
(3) Determine reporting formats and frequency, and
(4) Outline information flows and how information can be used.

Crockett begins with stakeholders to ensure that all relevant objectives

and critical success factors are reflected in the EIS.

Kaplan and Norton (1992) suggest that goals and measures need to be
developed from each of four perspectives: financial, customer, internal

129
MBA 757 DECISION SUPPORT SYSTEM

business, and innovation and learning. These perspectives help

managers to achieve a balance in setting objectives, and presenting them
in a unified report exposes the tough tradeoffs in any management
system. An EIS built on this basis will not promote productivity while
ignoring quality, or customer satisfaction while ignoring cost.

Meyer (1994) raises several questions that should be asked about

measurement systems for teams. Four are appropriate for evaluating
objectives and measures represented in an EIS. They are:

•Are all critical organisational outcomes tracked?

•Are all "out-of-bounds" conditions tracked? (Conditions that are
serious enough to trigger a management review.)
•Are all the critical variables required to reach each outcome tracked?
•Is there any measure that would not cause the organisation to change its
behaviour?

In summary, proper definition of organisational objectives and measures

is a helpful precondition for reducing organisational resistance to an EIS
and is the root of effective EIS use. The benefits of an EIS will be fully
realised only when it helps to focus management attention on issues of
true importance to the organisation.

4.0 CONCLUSION

Though executive information system is an excellent tool to aid decision

making, the success depends so much on how to effectively implement
it. Culture, technical issues and organisational goals go a long way to
determine the effectiveness of adopting EIS in an organisation.

5.0 SUMMARY

• An EIS is a tool that provides direct on-line access to relevant

information about aspects of a business that are of particular interest
to the senior manager.
• The primary purpose of an Executive Information System is to
support managerial learning about an organisation, its work
processes, and its interaction with the external environment.
• There are many ways in which an EIS can fail. Dozens of high
profile, high cost EIS projects have been cancelled, implemented and
rarely used, or implemented and used with negative results
• Issues of organisational behaviour and culture are perhaps the most
deadly barriers to effective Executive Information Systems.
• Flexibility is important because an EIS has such a powerful ability to
direct attention to specific issues in an organisation.
• EIS projects that succeed do so because at least one member of the

130
MBA 757 DECISION SUPPORT SYSTEM

senior management team agrees to champion the project.

• A number of writers have discovered that one of the major
difficulties with EIS implementations is that the information
contained in the EIS either does not meet executive requirements, or
meets executive requirements, but fails to guide the organisation
towards its objectives.

6.0 TUTOR-MARKED ASSIGNMENT

1. In what ways does an EIS differ from traditional information

systems?
2. Discuss briefly the involvement of information systems department
as a characteristic of a successful EIS implementation

7.0 REFERENCES/FURTHER READING

Agor, Weston H. (1986). How Top Executives Use Their Intuition To

Make Important Decisions. Business Horizons. January-February
1986, pp. 49-53.

Anderson, Joseph V. (1993). Mind Mapping: A Tool for Creative

Thinking. Business Horizons. January-February 1993, pp. 41-46.

Argyris, Chris (1991). Teaching Smart People How to Learn. Harvard

Business Review. May-June 1991, pp. 99-109.

Barrow, Craig (1990). Implementing an Executive Information System:

Seven Steps for Success. Journal of Information Systems
Management. Spring 1990, pp. 41-46.

Bird, Jane (1993). A System for the Perplexed. Management Today.April

1993, pp. 71-74.

Carroll, Chris and Larkin, Chris (1992). Executive Information

Technology: A Strategic Necessity at Motorola Codex.
Information Systems Management. Summer 1992, pp. 21-29.

Cook, Gary J. and Swain, Monte R. (1993). A Computerised Approach

to Decision Process Tracing for Decision Support System
Design. Decision Sciences. Volume 24, pp. 931-952.

Cooper, Robin and Kaplan, Robert S. (1991). Profit Priorities from

Activity-Based Costing. Harvard Business Review. May-June
1991, pp. 130-135.

Crockett, Fess (1992). Revitalising Executive Information Systems.

131
MBA 757 DECISION SUPPORT SYSTEM

Sloan Management Review. Summer 1992, pg 39-47.

Daft, Richard L. and Lengel, Robert H. (1986). Organisational

Information Requirements, Media Richness and Structural
Design. Management Science. Volume 32, pp. 554-571.

Davenport, Thomas H., Eccles, Robert G., and Prusak, Laurence.

(1992). Information Politics. Sloan Management Review. Fall
1992, pp. 53-65.

Dearden, John. (1966). Myth of Real-Time Management Information.

Harvard Business Review. May-June 1966, pp. 123-132.

Denton, Keith D. (1991). What's Wrong With these Employees?

Business Horizons. September-October 1991, pp. 45-49.

Fisher, Marshall L., Hammond, Janice H., Obermeyer, Walter R., and
Raman, Anath. (1994). Making Supply Meet Demand in an
Uncertain World. Harvard Business Review. May-June 1994, pp.
83-93.

Forgionne, Guisseppi A. (1991). Decision Technology Systems: A Step

toward Complete Decision Support. Information Systems
Managemen. Fall 1991, pp. 34-43.

Grant, Rebecca A., Higgins, Christopher A., and Irving, Richard H.

(1988). Computerised Performance Monitors: are They Costing
You Customers? Sloan Management Review. Spring 1988, pp.
39-45.

Huseman, Richard C.; Miles, Edward W. (1988). Organisational

Communication in the Information Age: Implications of
Computer-Based Systems. Journal of Management. 14(2), pp.
181-204.

Jones, Jack William, and McLeod, Raymond Jr. (1986). The Structure
of Executive Information Systems: An Exploratory Analysis.
Decision Sciences. Volume 17, pp. 220-249.

Kallman, Ernest A. and McKinnon, William P. (1989). Case Study:

Evaluating Is By Using An Executive Information System.
Journal of Information Systems Management. Fall 1989,
pp58-68.

Kaplan, Robert S., and Norton, David P. (1992). The Balanced

Scorecard - Measures That Drive Performance. Harvard
Business Review. January-February 1992, pp. 71-79.

132
MBA 757 DECISION SUPPORT SYSTEM

Keen, Peter G.W. (1980). Decision Support Systems: Translating

Analytic Techniques into Useful Tools. Sloan Management
Review. Spring 1980, pp. 33-44.

Kelly, Floyd (1992a). Program Implementation: Measures of Success.

Working Paper, Canadian Ministry of Housing. December 9,
1992.

King, William R., Premkumar, G., and Ramamurthy, K. (1990). An

Evaluation of the Role and Performance of a Decision Support
System in Business Education. Decision Sciences. Volume 21, pp.
642-659.

Knight, Charles F. (1992). Emerson Electric: Consistent Profits,

Consistently. Harvard Business Review. January-February 1992,
pp. 57-70.

Krachenberg, A. Richard, Henke, John W. Jr., and Lyons, Thomas F.

(1993). The Isolation of Upper Management. Business Horizons.
July-August 1993, pp. 41-47.

Leventhal, Laura Marie, Teasley, Barbee Mynatt, Instone, Keith,

Rohlman, Diane Schertler, and Farhat, John. (1993). Sleuthing in
Hyperhomes: an Evaluation of using Hypertext vs. A Book to
Answer Questions. Behaviour and Information Technology.
Volume 12, pp. 149-164.

McKinnon, Sharon M., and Bruns, William J. Jr. (1992). The

Information Mosaic, Harvard Business School Press. Boston MA.

McLeod, Raymond Jr., and Jones, Jack W. (1986). Making Executive

Information Systems More Effective. Business Horizons.
September-October 1986, pp. 29-37.

Meyer, Christopher. (1994). How The Right Measures Help Teams

Excel. Harvard Business Review. May-June 1994, pp. 95-103.

O'Shea, Timothy J. (1989). Low-Cost Approaches To Executive

Information Systems. Journal of Information Systems
Management. Spring 1989, pp34-41.

Osborne, David, and Gaebler, Ted. (1992). Reinventing Government.

Addison-Wesley, Reading MA.

Posner, Bruce G., and Rothstein, Lawrence R. (1994). Reinventing the

business of government: An Interview with Change Catalyst

133
MBA 757 DECISION SUPPORT SYSTEM

David Osborne. Harvard Business Review. May-June 1994, pp.

132-143.

Preece, Jenny, Rogers, Yvonne, Sharp, Helen, Benyon, David, Holland,

Simon, and Carey, Tom (1994). Human Computer Interaction.
Addison-Wesley. Wokingham, England.

Rockart, John F. and DeLong, David W. (1986). Identifying the

Attributes of Successful Executive Support System
Implementation. Transactions of the Sixth International
Conference on Decision Support Systems.

Rockart, John F. and Treacy, Michael E. (1982). The CEO Goes On-
Line. Harvard Business Review. January-February, 1982.

Rodgers, T. J. (1990). No Excuses Management. Harvard Business

Review.July-August 1990, pp. 84-98.

Sabourin, Helen (1992). Resource Management Information. Defence

2000 Achievements Report, pp. 44-47.

Schaffer, Robert H. (1974). Demand Better Results - And Get Them.

Harvard Business Review. November-December 1974.

Scott, Derek. (1993). Visual Search in Modern Human-Computer

Interfaces. Behaviour and Information Technology. Volume 12,
pp. 174-189.

Stevenson, Mark (1994). He Sees All, He Knows All. Canadian

Business. Spring 1994, pp. 30-35.

Tan, Joseph K. H. and Benbasat, Izak. (1993). The Effectiveness Of

Graphical Presentation for Information Extraction: A
Cumulative Experimental Approach. Decision Sciences. Volume
24, pp. 167-191.

Umanath, Narayan S., Scamell, Richard W., and Das, Sidhartha R.

(1990). An Examination of Two Screen/Report Design Variables
in an Information Recall Context. Decision Sciences. Volume 21,
pp. 216-240.

Vandenbosch, Betty. (1993). Executive Support Systems Impact Viewed

from a Learning Perspective. Doctoral Dissertation, University of
Western Ontario.

Determining Information Requirements. Information Systems

134
MBA 757 DECISION SUPPORT SYSTEM

Management. Spring 1992, pp. 37-43.

Watson, Hugh J.; Rainer, R. Kelly Jr. (1991). A Manager's Guide to

Executive Support Systems. Business Horizons. March-April
1991, pp. 44-50.

MODULE 3

135
MBA 757 DECISION SUPPORT SYSTEM

Unit 1 Geographic Information System

Unit 2 Expert Systems
Unit 3 Artificial Intelligence

UNIT 1 GEOGRAPHIC INFORMATION SYSTEM

CONTENTS

1.0 Introduction
2.0 Objectives
3.0 Main Content
3.1 History of Development
3.2 Components of GIS
3.3 Implementing GIS
3.4 Techniques used in GIS
4.0 Conclusion
5.0 Summary
6.0 Tutor-Marked Assignment
7.0 References/Further Reading

1.0 INTRODUCTION

A geographic information system (GIS), also known as a

geographical information system, is an information system for
capturing, storing, analysing, managing and presenting data which are
spatially referenced (linked to location).

In the strictest sense, it is any information system capable of integrating,

storing, editing, analysing, sharing, and displaying geographically
referenced information. In a more generic sense, GIS applications are
tools that allow users to create interactive queries (user created
searches), analyse spatial information, edit data, maps, and present the
results of all these operations. Geographic information science is the
science underlying the geographic concepts, applications and systems,
taught in degree and GIS Certificate programs at many universities.

Geographic information system technology can be used for scientific

investigations, resource management, asset management, environmental
impact assessment, urban planning, cartography, criminology,
geographic history, marketing, and logistics to name a few. For
example, GIS might allow emergency planners to easily calculate
emergency response times in the event of a natural disaster, GIS might
be used to find wetlands that need protection from pollution, or GIS can

136
MBA 757 DECISION SUPPORT SYSTEM

be used by a company to site a new business location to take advantage

of a previously under-served market.

2.0 OBJECTIVES

At the end of this unit, the students should be able to:

• define geographic information systems (GIS)

• identify the major components of GIS
• explain the steps to take in developing an effective GIS
• evaluate the development and history of the concept of GIS
• identify and understand the various techniques adopted in GIS
execution.

3.0 MAIN CONTENT

3.1 History of Development

About 15,500 years ago, on the walls of caves near Lascaux, France,
Cro-Magnon hunters drew pictures of the animals they hunted.
Associated with the animal drawings are track lines and tallies thought
to depict migration routes. While simplistic in comparison to modern
technologies, these early records mimic the two-element structure of
modern geographic information systems, an image associated with
attribute information.

The year 1962 saw the development of the world's first true operational
GIS in Ottawa, Ontario, Canada by the Federal Department of Forestry
and Rural Development. Developed by Dr. Roger Tomlinson, it was
called the "Canada Geographic Information System" (CGIS) and was
used to store, analyse, and manipulate data collected for the Canada
Land Inventory (CLI).

By the early 1980s, M&S Computing (later Intergraph), Environmental

Systems Research Institute (ESRI) and CARIS (Computer Aided
Resource Information System) emerged as commercial vendors of GIS
software, successfully incorporating many of the CGIS features,
combining the first generation approach to separation of spatial and
attribute information with a second generation approach to organising
attribute data into database structures.

137
MBA 757 DECISION SUPPORT SYSTEM

3.2 Components of GIS

The basic components of a GIS are software, data and hardware.

GIS Software

As with other information technology, GIS must be implemented in a

manner that easily allows applications to support your organisation's
workflows and business requirements.

How to Choose

By following the 10-stage implementation process outlined here, you

should have a good idea of what GIS software best meets your needs.
The software you choose depends on the information products you want,
your data requirements, and the functionality requirements you
discovered during the Determine Technology Requirements stage.
Basic things to consider include:

• Will I be successful if I use this software from this vendor?

• Is the software based on common IT standards?
• Will support be adequate from the vendor?

What Every GIS Platform Should Have

GIS software can be increasingly thought of as IT infrastructure for

assembling large, sophisticated multi-user systems. Look for a GIS
platform that provides all the capabilities necessary to support this
vision:

• Geographic database to store and manage all geographic objects

• A Web-based network for distributed geographic information
management and sharing
• Desktop and server applications for;
• Data compilation
• Information query
• Spatial analysis and geo-processing
• Cartographic production
• Image visualisation and exploitation
• GIS data management
• Modular software components (engines) to embed GIS logic in
other applications and build custom applications
• Geographic information services for multitier and centralised GIS
systems
• A comprehensive GIS platform that meets all geographic
requirements

138
MBA 757 DECISION SUPPORT SYSTEM

GIS Data

The backbone of GIS is good data. Inaccurate data can result in

inaccurate models and maps, skewing the results of your analysis and
ultimately resulting in poor decisions. "Garbage in, garbage out," as the
adage says.

The past 10 years has seen an explosion in the amount of data available,
much of it free, with the advent of the Internet and proliferation of
commercial sources of data. Internet mapping and Web services
technology has made it possible for anyone anywhere to share or access
data from around the globe.

This wide availability makes it critical to understand what GIS data is,
how it is used, and how to select the right data for your needs.

Data Types: Geography data comes in

three basic forms:

1. Map data. Map data contains the

location and shape of geographic
features. Maps use three basic
shapes to present real-world
features: points, lines, and areas
(called polygons).

2. Attribute data. Attribute (tabular) data is the descriptive data that

GIS links to map features. Attribute data is collected and compiled
for specific areas like states, census tracts, cities, and so on and often
comes packaged with map data. When implementing a GIS, the most
common sources of attribute data are your own organisation's
databases combined with data sets you buy or acquire from other
sources to fill in gaps.

3. Image data. Image data ranges from satellite images and aerial
photographs to scanned maps (maps that have been converted from
printed to digital format).

Using Data in GIS

GIS stores information about the world as a collection of themed layers

that can be used together. A layer can be anything that contains similar
features such as customers, buildings, streets, lakes, or postal codes.
This data contains either an explicit geographic reference, such as a
latitude and longitude coordinate, or an implicit reference such as an
address, postal code, census tract name, forest stand identifier, or road
name.

139
MBA 757 DECISION SUPPORT SYSTEM

To work, a GIS requires explicit references. A GIS can create these

explicit references from implicit references by an automated process
called geo-coding—tying an implicit reference like an address to a
specific point on the earth.

Find Data

Data is free or fee-based and comes from your own organisation;

commercial, nonprofit, educational, and governmental sources; and
other GIS software users.

The following links provide a good start for finding data for your needs.

• ESRIData

Data created by experts and designed to fit your business needs.

• Geodata.gov

Geodata.gov is part of the Geospatial One-Stop E-Gov initiative

providing access to geospatial data and information.

• Geography Network

The Geography Network is a collaborative, multi-participant system for

publishing, sharing, and using digital geographic information on the
Internet.

• GISDataDepot

This site offers free data from all over the world, or you can pay a fee
for a custom-cut CD.

Hardware—GIS Infrastructure

Hardware is really a simplistic term used to describe the technology

infrastructure needed to support your GIS implementation. The
infrastructure you develop depends on the system requirements you
determined you needed during that phase of implementation planning.
Using Web services for your GIS needs requires minimal investment in
infrastructure, while an enterprise GIS implementation requires careful
planning and a fairly significant investment in computer equipment,
network technology, database connectivity, and whatever else is
required.

140
MBA 757 DECISION SUPPORT SYSTEM

GIS is very much part of the information technology (IT) infrastructure

for any organisation, not a separate or niche technology. Your IT group
will help you determine the infrastructure you need and ensure that it is
compatible with the overall IT infrastructure for the organisation.
Depending on the scale of your implementation, your IT group will help
you determine how to address issues such as security, data integrity,
compatibility with other critical IT infrastructure and applications, and
so on. Partnering early on with your IT group in planning the
implementation of your GIS will significantly increase the success of
your implementation and use of GIS.

3.3 Implementing GIS

Careful planning is the key to successfully implementing GIS in the

enterprise.
Implementing GIS presents a unique set of challenges. Even the most
well-funded projects can fail because of poor planning.

Here we outline a 10-stage process for successfully deploying GIS.

3. Consider the strategic purpose.

4. Plan for the planning.
5. Determine technology requirements.
6. Determine the end products.
7. Define the system scope.
8. Create a data design.
9. Choose a data model.
10. Determine system requirements.
11. Analyse benefits and costs.
12. Make an implementation plan.

All deployment situations are unique. To ensure the greatest chance of

success, it is important that you understand all the stages outlined before
adapting the methodology to your needs.

Consider the Strategic Purpose

When planning for a successful GIS, you must think first about what
you want from it. Everything else you do come from that vision to
ensure that the GIS will ultimately work towards serving some useful
and important purpose.

Start by considering the strategic purpose of the organisation within

which the system will be developed. What are its goals, objectives, and
mandates?

141
MBA 757 DECISION SUPPORT SYSTEM

This stage of the planning ensures that the process and the final system
fit within organisational context and truly support the strategic
objectives of the organisation. This stage also allows you to assess how
information created by the GIS will impact the business strategy of the
organisation.

Plan for the Planning

GIS planning should not be taken lightly.

Forget about actually implementing a
GIS for the moment. Just planning a GIS
takes a commitment of resources and
people.

Before you begin, you need to know that

your organisation understands the
distinction between planning and
implementing and that it is prepared to provide the resources needed to
make the planning happen. Making the case means understanding what
needs to be done and what it will take to get it done. The end result of
this stage is a project proposal that makes that case and explicitly seeks
approval to launch the formal planning process.

Commitment to the planning process is essential to a successful GIS

implementation, especially in municipal government agencies and other
public-sector organisations. The project proposal helps to secure the
political commitment to the planning process. This is the moment to
introduce the GIS planning process to the most senior executives of your
organisation. Arrange to keep them fully informed of the planning
progress. If you receive approval for your planning project and a
commitment of resources at this point, your chances of having a
successful GIS are high.

Determine Technology Requirements

Conduct a Technology Seminar

Once you have the approval for your

project plan, the in-house GIS planning
team can be activated. Defining the
specific GIS requirements is the primary
task in the planning process. You must
meet with your customers or clients (those
who will use the system or use the output

142
MBA 757 DECISION SUPPORT SYSTEM

from the system) to begin gathering specifics about the actual

requirements from the user's perspective.

A highly effective method of soliciting input on the needs of your

organisation is to hold one or more in-house technology seminars.

In addition to its information-gathering purpose, the technology seminar

is also an ideal opportunity for you to explain to key personnel the
nature of GIS, its potential benefits, and the planning process itself. By
involving stakeholders at this early stage, you help to ensure
participation in the subsequent planning work ahead so that all
participants will appreciate the scope of the planning process. The
technology seminar is also the place where initial identification of
information products begins.

Knowing what you want to get out of your GIS is the key to a successful
implementation. The "stuff" you get from your GIS can be described in
the form of "information products."

This stage must be carefully undertaken. You'll need to talk to the users
about what their job involves and what information they need to perform
their tasks. Ultimately, you need to determine things like how the
information products should be made and how frequently, what data is
needed to make them, how much error can be tolerated, and the benefits
of the new information produced.
This stage should result in a document that includes a description of all
the information products that can be reasonably foreseen, together with
details of the data and functions required to produce these products.

Define the System Scope

Once the information products have been described, you can begin to
define the scope of the entire system. This involves determining what
data to acquire, when it will be needed, and the data volumes that need
to be handled. This includes assessing the probable timing of the
production of the information products. It may become clear that it will
be possible to use one input data source to generate more than one
information product, and this can now be built into your development
programme. Each refinement helps clarify your needs and increases
your chance of success.

Create a Data Design

In GIS, data is a major factor because spatial data is a relatively

complicated thing. In the conceptual system design phase of the

143
MBA 757 DECISION SUPPORT SYSTEM

planning process, you review the requirements identified in the earlier

stages and use them to begin developing database design.

A good GIS project plan includes collaboration and an iterative

approach to database design. Designing the conceptual, logical, and
physical structure of the database will involve input from key people
including project managers, subject matter experts, and technical
resources.

Choose a Logical Data Model

A logical data model describes those parts of the real world that concern
your organisation. The database may be simple or complex but must fit
together in a logical manner so that you can easily retrieve the data you
need and efficiently carry out the analysis tasks required.

There are several options available for your system's database design.
You should also consider data accuracy, update requirements, error
tolerance, and data standards at this stage, as these issues will affect
system design.

Determine System Requirements

The system requirements stage is where you examine the system

functions and user interface needed, along with the interface,
communications, hardware, and software requirements. This should be
the first time in the planning process that you examine software and
hardware products.

By reviewing the information product descriptions, you will summarise

the functions needed to produce them. Issues of interface design,
effective communications (particularly in distributed systems), and
appropriate hardware and software configurations should also be
considered during this planning phase. Plan your system carefully.

GIS Cost Waterfall

Cost of a change:

$1 – in the requirements stage

$10 – in the design stage
$100 – in the construction stage
$1000 – in the implementation stage

Source: Database Programming & Design, October, 1996, p. 57-64

144
MBA 757 DECISION SUPPORT SYSTEM

Analyse Benefits and Costs

Following conceptual system design, you need to work out the best way
to implement the system you have designed. This is where you plan how
the system will be taken from the planning stage to actual
implementation. You may also need to conduct a benefit-cost analysis to
make your business case for the system.

Until now, the focus of the planning methodology has been on what you
need to put in place to meet your requirements. The focus at this stage
switches to how to put the system in place—an acquisition plan. Issues
such as institutional interactions, legal matters, existing legacy hardware
and software, security, staffing, and training are addressed at this stage.

The acquisition plan that results from this stage of the planning process
will contain your implementation strategy and benefit-cost analysis.
This plan can be used both to secure funding for your system and as a
guide for the actual implementation of the system.

Make an Implementation Plan

The final report equips you with all the information you need to
implement a successful GIS. It will become your GIS planning book to
help you through the implementation process. Developing the final
report should be the result of a process of communication between the
GIS team and management, so that no parts of the report come as a
surprise to anyone.

The report should contain a review of the organisation's strategic

business objectives, the information requirements study, details of the
conceptual system design, recommendations for implementation, time
planning issues, and funding alternatives.

3.4 Techniques used in GIS

Data Creation

Modern GIS technologies use digital information, for which various

digitised data creation methods are used. The most common method of
data creation is digitisation, where a hard copy map or survey plan is
transferred into a digital medium through the use of a computer-aided
design (CAD) program, and geo-referencing capabilities. With the wide
availability of ortho-rectified imagery (both from satellite and aerial

145
MBA 757 DECISION SUPPORT SYSTEM

sources), heads-up digitising is becoming the main avenue through

which geographic data is extracted. Heads-up digitising involves the
tracing of geographic data directly on top of the aerial imagery instead
of through the traditional method of tracing the geographic form on a
separate digitising tablet.

Relating Information from Different Sources

If you could relate information about the rainfall of your state to aerial
photographs of your country, you might be able to tell which wetlands
dry up at certain times of the year. A GIS, which can use information
from many different sources in many different forms, can help with such
analyses. The primary requirement for the source data consists of
knowing the locations for the variables. Location may be annotated by
x, y, and z coordinates of longitude, latitude, and elevation, or by other
geo-code systems like ZIP Codes or by highway mile markers. Any
variable that can be located spatially can be fed into a GIS. Several
computer databases that can be directly entered into a GIS are being
produced by government agencies and non-government organisations.
Different kinds of data in map form can be entered into a GIS.

Data Representation

GIS data represents real world objects (roads, land use, elevation) with
digital data. Real world objects can be divided into two abstractions:
discrete objects (a house) and continuous fields (rain fall amount or
elevation). There are two broad methods used to store data in a GIS for
both abstractions: Raster and Vector.

Raster: A raster data type is, in essence, any type of digital image.
Anyone who is familiar with digital photography will recognise the
pixel as the smallest individual unit of an image. A combination of these
pixels will create an image, distinct from the commonly used scalable
vector graphics which are the basis of the vector model. While a digital
image is concerned with the output as representation of reality, in a
photograph or art transferred to computer, the raster data type will
reflect an abstraction of reality. Aerial photos are one commonly used
form of raster data, with only one purpose, to display a detailed image
on a map or for the purposes of digitisation. Other raster data sets will
contain information regarding elevation, a DEM, or reflectance of a
particular wavelength of light, LANDSAT.

146
MBA 757 DECISION SUPPORT SYSTEM

Digital elevation model, map (image), and vector data

Raster data type consists of rows and columns of cells, with each cell
storing a single value. Raster data can be images (raster images) with
each pixel (or cell) containing a color value. Additional values recorded
for each cell may be a discrete value, such as land use, a continuous
value, such as temperature, or a null value if no data is available.

Vector: A simple vector map, using each of the vector elements: points
for wells, lines for rivers, and a polygon for the lake.

In a GIS, geographical features are often expressed as vectors, by

considering those features as geometrical shapes. Different geographical
features are expressed by different types of geometry.

Advantages and Disadvantages: There are advantages and

disadvantages to using a raster or vector data model to represent reality.
Raster data sets record a value for all points in the area covered which
may require more storage space than representing data in a vector format
that can store data only where needed. Raster data also allows easy
implementation of overlay operations, which are more difficult with
vector data. Vector data can be displayed as vector graphics used on
traditional maps, whereas raster data will appear as an image that,
depending on the resolution of the raster file, may have a blocky
appearance for object boundaries. Vector data can be easier to register,
scale, and re-project. This can simplify combining vector layers from
different sources. Vector data are more compatible with relational
database environment. They can be part of a relational table as a normal
column and processes using a multitude of operators.

The file size for vector data is usually much smaller for storage and
sharing than raster data. Image or raster data can be 10 to 100 times

147
MBA 757 DECISION SUPPORT SYSTEM

larger than vector data depending on the resolution. Another advantage

of vector data is that it can be easily updated and maintained.

Non-Spatial Data: Additional non-spatial data can also be stored

besides the spatial data represented by the coordinates of vector
geometry or the position of a raster cell. In vector data, the additional
data are attributes of the object. For example, a forest inventory polygon
may also have an identifier value and information about tree species. In
raster data the cell value can store attribute information, but it can also
be used as an identifier that can relate to records in another table.

There is also software being developed to support spatial and non-spatial

decision-making. In this software, the solutions to spatial problems are
integrated with solutions to non-spatial problems. The end result it is
hoped, with these Flexible Spatial Decision-Making Support Systems
(FSDSS) will be that non experts can use GIS and spatial criteria with
their other non spatial criteria to view solutions to multi-criteria
problems that will support decision making.

Data Capture

Data capture—entering information into the system—consumes much of

the time of GIS practitioners. There are a variety of methods used to
enter data into a GIS where it is stored in a digital format.

Existing data printed on paper or PET film maps can be digitised or

scanned to produce digital data. A digitiser produces vector data as an
operator traces points, lines, and polygon boundaries from a map.
Scanning a map results in raster data that could be further processed to
produce vector data.

Survey data can be directly entered into a GIS from digital data
collection systems on survey instruments using a technique called
Coordinate Geometry (COGO). Positions from a Global Positioning
System (GPS), another survey tool, can also be directly entered into a
GIS.

Remotely sensed data also plays an important role in data collection and
consist of sensors attached to a platform. Sensors include cameras,
digital scanners and LIDAR, while platforms usually consist of aircraft
and satellites.

Satellite remote sensing provides another important source of spatial

data. Here satellites use different sensor packages to passively measure
the reflectance from parts of the electromagnetic spectrum or radio
waves that were sent out from an active sensor such as radar. Remote

148
MBA 757 DECISION SUPPORT SYSTEM

sensing collects raster data that can be further processed using different
bands to identify objects and classes of interest, such as land cover.

Raster-to-Vector Translation

Data restructuring can be performed by a GIS to convert data into

different formats. For example, a GIS may be used to convert a satellite
image map to a vector structure by generating lines around all cells with
the same classification, while determining the cell spatial relationships,
such as adjacency or inclusion.

4.0 CONCLUSION

Geographic information systems have come of age as a very important

tool in decision making in environmental sciences and weather
forecasting. GIS combines computerised maps and databases to organise
and analyse location-specific information. It assists in assessing and
forecasting property damage and co-ordinating relief efforts in cases of
natural disaster as in Hurricanes and Tornados.

5.0 SUMMARY

• A geographic information system (GIS), also known as a

geographical information system, is an information system for
capturing, storing, analysing, managing and presenting data which
are spatially referenced (linked to location).
• About 15,500 years ago, on the walls of caves near Lascaux, France,
Cro-Magnon hunters drew pictures of the animals they hunted.
Associated with the animal drawings are track lines and tallies
thought to depict migration routes.
• The basic components of a GIS are software, data and hardware.
• Careful planning is the key to successfully implementing GIS in the
enterprise. Implementing GIS presents a unique set of challenges.
Even well-funded projects can fail because of poor planning.
• A GIS can also convert existing digital information, which may not
yet be in map form, into forms it can recognise and use.
• Modern GIS technologies use digital information, for which various
digitised data creation methods are used.
• GIS data represents real world objects (roads, land use, elevation)
with digital data. Real world objects can be divided into two
abstractions: discrete objects (a house) and continuous fields (rain
fall amount or elevation).
• Satellite remote sensing provides another important source of spatial
data. Here satellites use different sensor packages to passively
measure the reflectance from parts of the electromagnetic spectrum
or radio waves that were sent out from an active sensor such as radar.

149
MBA 757 DECISION SUPPORT SYSTEM

• There are advantages and disadvantages to using a raster or vector

data model to represent reality.

6.0 TUTOR-MARKED ASSIGNMENT

2. List the 10 stages to successfully deploy GIS.

3. Discuss briefly data capture as a technique used in GIS.

7.0 REFERENCES/FURTHER READING

GIS.com (2008). The Guide to Geographical Information Systems,

Implementing GIS.

UNIT 2 EXPERT SYSTEMS

CONTENTS

150
MBA 757 DECISION SUPPORT SYSTEM

1.0 Introduction
2.0 Objectives
3.0 Main Content
3.1 Overview
3.2 Prominent Expert Systems and Languages
3.3 The Study of Expert Systems
3.4 Expert Systems Topics
3.5 Application of Expert Systems
3.6 Advantages and Disadvantages
3.7 Types of Problems Solved by Expert Systems
4.0 Conclusion
5.0 Summary
6.0 Tutor-Marked Assignment
7.0 References/Further Reading

1.0 INTRODUCTION

An expert system is a software system that attempts to reproduce the

performance of one or more human experts, most commonly in a
specific problem domain, and is a traditional application and/or subfield
of artificial intelligence. A wide variety of methods can be used to
simulate the performance of the expert.

However common to most or all are:

1) The creation of a so-called "knowledgebase" which uses some

knowledge representation formalism to capture the subject matter
experts (SME) knowledge,
2) A process of gathering that knowledge from the SME and
codifying it according to the formalism, which is called
knowledge engineering and
3) Expert systems may or may not have learning components but a
third common element is that once the system is developed it is
proven by being placed in the same real world problem solving
situation as the human SME, typically as an aid to human
workers or a supplement to some information system.

As a premiere application of computing and artificial intelligence, the

topic of expert systems has many points of contact with general systems
theory, operations research, business process reengineering and various
topics in applied mathematics and management science.

Two illustrations of actual expert systems can give an idea of how they
work. In one real world case at a chemical refinery a senior employee
was about to retire and the company was concerned that the loss of his

151
MBA 757 DECISION SUPPORT SYSTEM

expertise in managing a fractionating tower would severely impact

operations of the plant. A knowledge engineer was assigned to produce
an expert system reproducing his expertise saving the company the loss
of the valued knowledge asset. Similarly a system called Mycin was
developed from the expertise of best diagnosticians of bacterial
infections whose performance was found to be good as or better than the
average clinician. An early commercial success and illustration of
another typical application (a task generally considered overly complex
for a human) was an expert system fielded by DEC in the 1980s to
quality check the configurations of their computers prior to delivery.
The eighties were the time of greatest popularity of expert systems and
interest lagged after the onset of the AI Winter.

2.0 OBJECTIVES

At the end of this unit, the students should be able to:

• define the concept of expert systems

• explain some major expert systems and languages of the shelf
• identify the topical issues related to expert systems
• explain the various applications of expert systems
• evaluate the advantages and disadvantages associated with expert
systems.

3.0 MAIN CONTENT

3.1 Overview

The most common form of expert system is a computer program, with a

set of rules that analyses information (usually supplied by the user of the
system) about a specific class of problems, and recommends one or
more courses of user action. The expert system may also provide
mathematical analysis of the problem(s). The expert system utilises what
appears to be reasoning capabilities to reach conclusions.

A related term is wizard. A wizard is an interactive computer program

that helps a user to solve a problem. Originally the term wizard was used
for programs that construct a database search query based on criteria
supplied by the user. However, some rule-based expert systems are also
called wizards. Other "Wizards" are a sequence of online forms that
guide users through a series of choices, such as the ones which manage
the installation of new software on computers, and these are not expert
systems.
3.2 Prominent Expert Systems and Languages

152
MBA 757 DECISION SUPPORT SYSTEM

• ART,- An early general-purpose programming language used in the

development of expert systems.
• CADUCEUS (expert system) - Blood-borne infectious bacteria.
• CLIPS - Programming language used in the development of expert
systems
• Drools - An open source offering from JBOSS labs
• Dendral - Analysis of mass spectra
• Dipmeter Advisor - Analysis of data gathered during oil exploration
• Jess - Java Expert System Shell. A CLIPS engine implemented in
Java used in the development of expert systems
• KnowledgeBench – expert system for building new product
development applications
• MQL 4 - MetaQuotes Language 4, a customised language for
financial strategy programming
• Mycin - Diagnose infectious blood diseases and recommend
antibiotics (by Stanford University)
• NETeXPERT - A mission-critical Operational Support Systems
framework with rules, policies, object modeling, and adapters for
Network Operations Center automation
• NEXPERT Object - An early general-purpose commercial
backwards-chaining inference engine used in the development of
expert systems
• Prolog - Programming language used in the development of expert
systems
• Forth - Programming language used in the development of expert
systems
• R1/Xcon - Order processing
• SHINE Real-time Expert System - Spacecraft Health Inference
Engine
• STD Wizard - Expert system for recommending medical screening
tests
• PyKe - Pyke is a knowledge-based inference engine (expert system)

3.3 The Study of Expert Systems

Knowledge Representation

Knowledge Representation is an issue that arises in both cognitive

science and artificial intelligence. In cognitive science, it is concerned
with how people store and process information. In artificial intelligence
(AI) the primary aim is to store knowledge so that programs can process
it and achieve the verisimilitude of human intelligence. AI researchers
have borrowed representation theories from cognitive science. Thus
there are representation techniques such as frames, rules and semantic
networks which have originated from theories of human information

153
MBA 757 DECISION SUPPORT SYSTEM

processing. Since knowledge is used to achieve intelligent behaviour,

the fundamental goal of knowledge representation is to represent
knowledge in a manner as to facilitate inference i.e. drawing conclusions
from knowledge.

Knowledge Engineer

Knowledge engineers are concerned with the representation chosen for

the expert's knowledge declarations and with the inference engine used
to process that knowledge. He / she can use the knowledge acquisition
component of the expert system to input the several characteristics
known to be appropriate to a good inference technique, including:

• A good inference technique is independent of the problem domain.

• In order to realise the benefits of explanation, knowledge
transparency, and reusability of the programs in a new problem
domain, the inference engine must not contain domain specific
expertise.
• Inference techniques may be specific to a particular task, such as
diagnosis of hardware configuration. Other techniques may be
committed only to a particular processing technique.
• Inference techniques are always specific to the knowledge structures.
• Successful examples of rule processing techniques are forward
chaining and backward chaining.

3.4 Expert Systems Topics

Chaining

There are two main methods of reasoning when using inference rules:
backward chaining and forward chaining.

Forward chaining starts with the data available and uses the inference
rules to conclude more data until a desired goal is reached. An inference
engine using forward chaining searches the inference rules until it finds
one in which the if-clause is known to be true. It then concludes the
then-clause and adds this information to its data. It would continue to do
this until a goal is reached. Because the data available determines which
inference rules are used, this method is also called data driven.

Backward chaining starts with a list of goals and works backwards to

see if there is data which will allow it to conclude any of these goals. An
inference engine using backward chaining would search the inference
rules until it finds one which has a then-clause that matches a desired
goal. If the if-clause of that inference rule is not known to be true, then it

154
MBA 757 DECISION SUPPORT SYSTEM

is added to the list of goals. For example, suppose a rule base contains
two rules:

(1) If Fritz is green then Fritz is a frog.

(2) If Fritz is a frog then Fritz hops.

Suppose a goal is to conclude that Fritz hops. The rule base would be
searched and rule (2) would be selected because its conclusion (the then
clause) matches the goal. It is not known that Fritz is a frog, so this "if"
statement is added to the goal list. The rule base is again searched and
this time rule (1) is selected because its then clause matches the new
goal just added to the list. This time, the if-clause (Fritz is green) is
known to be true and the goal that Fritz hops is concluded. Because the
list of goals determines which rules are selected and used, this method is
called goal driven.

Certainty Factors

One advantage of expert systems over traditional methods of

programming is that they allow the use of "confidences" (or "certainty
factors"). When a human reasons he does not always conclude things
with 100% confidence. He might say, "If Fritz is green, then he is
probably a frog" (after all, he might be a chameleon). This type of
reasoning can be imitated by using numeric values called confidences.
For example, if it is known that Fritz is green, it might be concluded
with 0.85 confidence that he is a frog; or, if it is known that he is a frog,
it might be concluded with 0.95 confidence that he hops. These numbers
are similar in nature to probabilities, but they are not the same. They are
meant to imitate the confidences humans use in reasoning rather than to
follow the mathematical definitions used in calculating probabilities.

Expert System Architecture

The following general points about expert systems and their architecture
have been illustrated.

1. The sequence of steps taken to reach a conclusion is dynamically

synthesised with each new case. It is not explicitly programmed
when the system is built.
2. Expert systems can process multiple values for any problem
parameter. This permits more than one line of reasoning to be
pursued and the results of incomplete (not fully determined)
reasoning to be presented.
3. Problem solving is accomplished by applying specific knowledge
rather than specific technique. This is a key idea in expert
systems technology. It reflects the belief that human experts do

155
MBA 757 DECISION SUPPORT SYSTEM

not process their knowledge differently from others, but they do

possess different knowledge. With this philosophy, when one
finds that their expert system does not produce the desired results,
work begins to expand the knowledge base, not to re-program the
procedures.

There are various expert systems in which a rule base and an inference
engine cooperate to simulate the reasoning process that a human expert
pursues in analysing a problem and arriving at a conclusion. In these
systems, in order to simulate the human reasoning process, a vast
amount of knowledge needed to be stored in the knowledge base.
Generally, the knowledge base of such an expert system consisted of a
relatively large number of "if then" type of statements that were
interrelated in a manner that, in theory at least, resembled the sequence
of mental steps that were involved in the human reasoning process.

Because of the need for large storage capacities and related programs to
store the rule base, most expert systems have, in the past, been run only
on large information handling systems. Recently, the storage capacity of
personal computers has increased to a point where it is becoming
possible to consider running some types of simple expert systems on
personal computers.

In some applications of expert systems, the nature of the application and

the amount of stored information necessary to simulate the human
reasoning process for that application is just too vast to store in the
active memory of a computer. In other applications of expert systems,
the nature of the application is such that not all of the information is
always needed in the reasoning process. An example of this latter type
application would be the use of an expert system to diagnose a data
processing system comprising many separate components, some of
which are optional. When that type of expert system employs a single
integrated rule base to diagnose the minimum system configuration of
the data processing system, much of the rule base is not required since
many of the components which are optional units of the system will not
be present in the system. Nevertheless, earlier expert systems require the
entire rule base to be stored since all the rules were, in effect, chained or
linked together by the structure of the rule base.

When the rule base is segmented, preferably into contextual segments or

units, it is then possible to eliminate portions of the rule base containing
data or knowledge that is not needed in a particular application. The
segmenting of the rule base also allows the expert system to be run with
systems or on systems having much smaller memory capacities than was
possible with earlier arrangements since each segment of the rule base
can be paged into and out of the system as needed. The segmenting of

156
MBA 757 DECISION SUPPORT SYSTEM

the rule base into contextual segments requires that the expert system
manage various intersegment relationships as segments are paged into
and out of memory during execution of the program. Since the system
permits a rule base segment to be called and executed at any time during
the processing of the first rule base, provision must be made to store the
data that has been accumulated up to that point so that at some time later
in the process, when the system returns to the first segment, it can
proceed from the last point or rule node that was processed. Also,
provision must be made so that data that has been collected by the
system up to that point can be passed to the second segment of the rule
base after it has been paged into the system and data collected during the
processing of the second segment can be passed to the first segment
when the system returns to complete processing that segment.
The user interface and the procedure interface are two important
functions in the information collection process.

End User

The end-user usually sees an expert system through an interactive

dialogue, an example of which follows:

Q. Do you know which restaurant you want to go to?

A. No
Q. Is there any kind of food you would particularly like?
A. No
Q. Do you like spicy food?
A. No
Q. Do you usually drink wine with meals?
A. Yes
Q. When you drink wine, is it French wine?
A. Why

As can be seen from this dialogue, the system is leading the user through
a set of questions, the purpose of which is to determine a suitable set of
restaurants to recommend. This dialogue begins with the system asking
if the user already knows the restaurant choice (a common feature of
expert systems) and immediately illustrates a characteristic of expert
systems; users may choose not to respond to any question. In expert
systems, dialogues are not pre-planned. There is no fixed control
structure. Dialogues are synthesised from the current information and
the contents of the knowledge base. Because of this, not being able to
supply the answer to a particular question does not stop the consultation.

Explanation System(move up to next page)

157
MBA 757 DECISION SUPPORT SYSTEM

Another major distinction between expert systems and traditional

systems is illustrated by the following answer given by the system when
the user answers a question with another question, "Why", as occurred
in the above example. The answer is:

A. I am trying to determine the type of restaurant to suggest. So far

Chinese is not a likely choice. It is possible that French is a likely
choice. I know that if the diner is a wine drinker, and the preferred
wine is French, then there is strong evidence that the restaurant
choice should include French.

It is very difficult to implement a general explanation system (answering

questions like "Why" and "How") in a traditional computer program. An
expert system can generate an explanation by retracing the steps of its
reasoning. The response of the expert system to the question WHY is an
exposure of the underlying knowledge structure. It is a rule; a set of
antecedent conditions which, if true, allow the assertion of a consequent.
The rule references values, and tests them against various constraints or
asserts constraints onto them. This, in fact, is a significant part of the
knowledge structure. There are values, which may be associated with
some organising entity. For example, the individual diner is an entity
with various attributes (values) including whether they drink wine and
the kind of wine. There are also rules, which associate the currently
known values of some attributes with assertions that can be made about
other attributes. It is the orderly processing of these rules that dictates
the dialogue itself.

Expert Systems versus Problem-Solving Systems

The principal distinction between expert systems and traditional

problem solving programs is the way in which the problem related
expertise is coded. In traditional applications, problem expertise is
encoded in both program and data structures.
In the expert system approach all of the problem related expertise is
encoded in data structures only; none is in programs. This organisation
has several benefits.

An example may help contrast the traditional problem solving program

with the expert system approach. The example is the problem of tax
advice. In the traditional approach data structures describe the taxpayer
and tax tables, and a program in which there are statements representing
an expert tax consultant's knowledge, such as statements which relate
information about the taxpayer to tax table choices. It is this
representation of the tax expert's knowledge that is difficult for the tax
expert to understand or modify.

158
MBA 757 DECISION SUPPORT SYSTEM

In the expert system approach, the information about taxpayers and tax
computations is again found in data structures, but now the knowledge
describing the relationships between them is encoded in data structures
as well. The programs of an expert system are independent of the
problem domain (taxes) and serve to process the data structures without
regard to the nature of the problem area they describe. For example,
there are programs to acquire the described data values through user
interaction, programs to represent and process special organisations of
description, and programs to process the declarations that represent
semantic relationships within the problem domain and an algorithm to
control the processing sequence and focus.

The general architecture of an expert system involves two principal

components: a problem dependent set of data declarations called the
knowledge base or rule base, and a problem independent (although
highly data structure dependent) program which is called the inference
engine.

Individuals involved with Expert Systems

There are generally three individuals having an interaction with expert

systems. Primary among these is the end-user; the individual who uses
the system for its problem solving assistance. In the building and
maintenance of the system there are two other roles: the problem
domain expert who builds and supplies the knowledge base providing
the domain expertise, and a knowledge engineer who assists the experts
in determining the representation of their knowledge, enters this
knowledge into an explanation module and who defines the inference
technique required to obtain useful problem solving activity. Usually,
the knowledge engineer will represent the problem solving activity in
the form of rules which is referred to as a rule-based expert system.
When these rules are created from the domain expertise, the knowledge
base stores the rules of the expert system.

User Interface

The function of the user interface is to present questions and information

to the user and supply the user's responses to the inference engine.

Any values entered by the user must be received and interpreted by the
user interface. Some responses are restricted to a set of possible legal
answers, others are not. The user interface checks all responses to ensure
that they are of the correct data type. Any responses that are restricted to
a legal set of answers are compared against these legal answers.
Whenever the user enters an illegal answer, the user interface informs
the user that his answer was invalid and prompts him to correct it.

159
MBA 757 DECISION SUPPORT SYSTEM

3.5 Application of Expert Systems

Expert systems are designed and created to facilitate tasks in the fields
of accounting, medicine, process control, financial service, production,
human resources etc. Indeed, the foundation of a successful expert
system depends on a series of technical procedures and development
that may be designed by certain technicians and related experts.

A good example of application of expert systems in banking area is

expert systems for mortgages. Loan departments are interested in expert
systems for mortgages because of the growing cost of labour which
makes the handling and acceptance of relatively small loans less
profitable. They also see in the application of expert systems a
possibility for standardised, efficient handling of mortgage loan, and
appreciate that for the acceptance of mortgages there are hard and fast
rules which do not always exist with other types of loans.

While expert systems have distinguished themselves in AI research in

finding practical application, their application has been limited. Expert
systems are notoriously narrow in their domain of knowledge—as an
amusing example, a researcher used the "skin disease" expert system to
diagnose his rust bucket car as likely to have developed measles—and
the systems were thus prone to making errors that humans would easily
spot. Additionally, once some of the mystique had worn off, most
programmers realised that simple expert systems were essentially just
slightly more elaborate versions of the decision logic they had already
been using. Therefore, some of the techniques of expert systems can
now be found in most complex programs without any fuss about them.

An example and a good demonstration of the limitations of, an expert

system used by many people is the Microsoft Windows operating
system troubleshooting software located in the "help" section in the
taskbar menu. Obtaining expert / technical operating system support is
often difficult for individuals not closely involved with the development
of the operating system. Microsoft has designed their expert system to
provide solutions, advice, and suggestions to common errors
encountered throughout using the operating systems.

Another 1970s and 1980s application of expert systems — which we

today would simply call AI — was in computer games. For example, the
computer baseball games Earl Weaver Baseball and Tony La Russa
Baseball each had highly detailed simulations of the game strategies of
those two baseball managers. When a human played the game against
the computer, the computer queried the Earl Weaver or Tony La Russa
Expert System for a decision on what strategy to follow. Even those

160
MBA 757 DECISION SUPPORT SYSTEM

choices where some randomness was part of the natural system (such as
when to throw a surprise pitch-out to try to trick a runner trying to steal
a base) were decided based on probabilities supplied by Weaver or La
Russa. Today we would simply say that "the game's AI provided the
opposing manager's strategy."

3.6 Advantages and Disadvantages

Advantages

• Provides consistent answers for repetitive decisions, processes and

tasks
• Holds and maintains significant levels of information
• Encourages organisations to clarify the logic of their decision-
making
• Never "forgets" to ask a question, as a human might.

Disadvantages

• Lacks common sense needed in some decision making

• Cannot make creative responses as human expert would in unusual
circumstances
• Domain experts not always able to explain their logic and reasoning
• Errors may occur in the knowledge base, and lead to wrong decisions
• Cannot adapt to changing environments, unless knowledge base is
changed.

3.7 Types of Problems Solved by Expert Systems

Expert systems are most valuable to organisations that have a high-level

of know-how experience and expertise that cannot be easily transferred
to other members. They are designed to carry the intelligence and
information found in the intellect of experts and provide this knowledge
to other members of the organisation for problem-solving purposes.

Typically, the problems to be solved are of the sort that would normally
be tackled by a medical or other professional. Real experts in the
problem domain (which will typically be very narrow, for instance
"diagnosing skin conditions in human teenagers") are asked to provide
"rules of thumb" on how they evaluate the problems, either explicitly
with the aid of experienced systems developers, or sometimes implicitly,
by getting such experts to evaluate test cases and using computer
programs to examine the test data and (in a strictly limited manner)
derive rules from that. Generally, expert systems are used for problems
for which there is no single "correct" solution which can be encoded in a
conventional algorithm — one would not write an expert system to find

161
MBA 757 DECISION SUPPORT SYSTEM

shortest paths through graphs, or sort data, as there are simply easier
ways to do these tasks.

Simple systems use simple true/false logic to evaluate data. More

sophisticated systems are capable of performing at least some
evaluation, taking into account real-world uncertainties, using such
methods as fuzzy logic. Such sophistication is difficult to develop and
still highly imperfect.

4.0 CONCLUSION

Expert systems describe computer programs which allow users to

benefit from expert knowledge and information, and also advice. It is an
offshoot of a much broader field of artificial intelligence. The specialist
applications of expert systems are usually intended to widen the
knowledge of a computer user who is already an expert in his field,
rather than to provide information to a non-expert and novice. But
presently non-experts are beginning to hook unto expert systems to
proffer some level of solution to their problems.

5.0 SUMMARY

• An expert system is a software system that attempts to reproduce the

performance of one or more human experts, most commonly in a
specific problem domain, and is a traditional application and/or
subfield of artificial intelligence.
• The most common form of expert system is a computer program,
with a set of rules, that analyses information (usually supplied by the
user of the system) about a specific class of problems, and
recommends one or more courses of user action.
• Knowledge representation is an issue that arises in both cognitive
science and artificial intelligence. In cognitive science, it is
concerned with how people store and process information.
• There are two main methods of reasoning when using inference
rules: backward chaining and forward chaining.
• Expert systems are designed and created to facilitate tasks in the
fields of accounting, medicine, process control, financial service,
production, human resources etc. Indeed, the foundation of a
successful expert system depends on a series of technical procedures
and development that may be designed by certain technicians and
related experts.

6.0 TUTOR-MARKED ASSIGNMENT

1. Mention 5 characteristics of good inference techniques as used by

knowledge engineers.

162
MBA 757 DECISION SUPPORT SYSTEM

2. Provide 5 disadvantages of expert systems.

7.0 REFERENCES/FURTHER READING

James Ignizio, (1991). Introduction to Expert Systems. ISBN:

0-07-909785-5.

Joseph C. Giarratano, Gary Riley (2005). Expert Systems, Principles

and Programming. ISBN: 0-534-38447-1.

Peter Jackson (1998). Introduction to Expert Systems. ISBN:

0-201-87686-8.

WALKER, Adrian et al (1990). Knowledge Systems and Prolog.

Addison-Wesley. ISBN: 0-201-52424-4.

UNIT 3 ARTIFICIAL INTELLIGENCE

CONTENTS

1.0 Introduction
2.0 Objectives
3.0 Main Content
3.1 Components of AI
3.2 Why Business is interested in AI

163
MBA 757 DECISION SUPPORT SYSTEM

3.3 Tools of AI Research

3.4 Specialised Languages
3.5 Evaluating Artificial Intelligence
3.6 Competitions and Prizes
3.7 Applications of Artificial Intelligence
4.0 Conclusion
5.0 Summary
6.0 Tutor-Marked Assignment
7.0 References/Further Reading

1.0 INTRODUCTION

What is Artificial Intelligence

Organisations are using artificial intelligence (AI) to capture individual

and collective knowledge and to codify and internalise their knowledge
base.

AI can be defined as the effort to develop computer-based system (both

hardware and software) that behaves as humans. Such systems will be to
learn natural languages, accomplish coordinated physical tasks
(robotics), use perceptual apparatus that inform their physical behaviour
and language (oral and visual perception systems), and emulate human
expertise and decision making (expert systems). Such systems also
exhibit logic, reasoning, intuition, and the just-plain-common-sense
qualities that we associate with human beings. Another important
element is intelligence machines, the physical hardware that performs
these tasks.

Successful AI systems are based on human expertise, knowledge and

selected reasoning patterns, but they do not exhibit the intelligence of
human beings. Existing intelligence systems do not come up with new
and novel solutions to problems. Existing systems extend power of
experts but in no way substitute for them or capture much of their
intelligence. Briefly, existing systems lack the common sense and
generality of naturally intelligent human beings.

2.0 OBJECTIVES

At the end of this unit, the students should be able to:

• define and understand the concept of artificial intelligence

• explain the major sub-field of artificial intelligence (AI)
• outline the development and history of AI
• identify AI characteristics that appeal to business functions
• identify the various tools used in the field of AI

164
MBA 757 DECISION SUPPORT SYSTEM

• evaluate the major applications of AI in lifegenerally.

• .

3.0 MAIN CONTENT

3.1 Components of AI

ARTIFICIAL
INTELLIGENCE

Natural Robotics Perspective Expert

Intelligent
Languages Systems Systems Machines

Figure 1: Components of Artificial Intelligence

3.2 Why Business is interested in AI

Although AI applications are much more limited than human

intelligence, they are of great interest to business for the following
reasons:

• To preserve expertise that might be lost through the retirement,

resignation, or death of an acknowledged expert.
• To store information in an active form- to create an organisational
knowledge base- that many employees can examine, much like
electronic textbook or manual so that other may learn rules of thumb
not found in the textbooks.
• To create a mechanism that is not subject to human feelings such as
fatigue and worry. This may be especially useful when jobs may be
environmentally, physically, or mentally dangerous to humans.
These systems may also be useful advisers in times of crisis.
• To eliminate routine and unsatisfying jobs held by people.
• To enhance the organisation’s knowledge base by suggesting
solutions to specific problems that are too massive and complex to
be analysed by human beings in a short period of time.

3.3 Tools of AI Research

165
MBA 757 DECISION SUPPORT SYSTEM

In the course of 50 years of research, AI has developed a large number

of tools to solve the most difficult problems in computer science. A few
of the most general of these methods are discussed below.

Search and Optimisation

Many problems in AI can be solved in theory by intelligently searching

through many possible solutions: Reasoning can be reduced to
performing a search. For example, logical proof can be viewed as
searching for a path that leads from premises to conclusions, where each
step is the application of an inference rule. Planning algorithms search
through trees of goals and sub goals, attempting to find a path to a target
goal, a process called means-ends analysis. Robotics algorithms for
moving limbs and grasping objects use local searches in configuration
space. Many learning algorithms use search algorithms based on
optimisation.

Simple exhaustive searches are rarely sufficient for most real world
problems: the search space (the number of places to search) quickly
grows to astronomical numbers. The result is a search that is too slow or
never completes. The solution, for many problems, is to use "heuristics"
or "rules of thumb" that eliminate choices that are unlikely to lead to the
goal (called "pruning the search tree"). Heuristics supply the program
with a "best guess" for what path the solution lies on.

A very different kind of search came to prominence in the 1990s, based

on the mathematical theory of optimisation. For many problems, it is
possible to begin the search with a form of a guess and then refine the
guess incrementally until no more refinements can be made. These
algorithms can be visualised as blind hill climbing: we begin the search
at a random point on the landscape, and then, by jumps or steps, we
keep moving our guess uphill, until we reach the top. Other optimisation
algorithms are simulated annealing, beam search and random
optimisation.

Evolutionary computation uses a form of optimisation search. For

example, they may begin with a population of organisms (the guesses)
and then allow them to mutate and recombine, selecting only the fittest
to survive each generation (refining the guesses). Forms of evolutionary
computation include swarm intelligence algorithms (such as ant colony
or particle swarm optimisation) and evolutionary algorithms (such as
genetic algorithms and genetic programming.

Logic

Logic was introduced into AI research by John McCarthy in his 1958

Advice Taker proposal. The most important technical development was

166
MBA 757 DECISION SUPPORT SYSTEM

J. Alan Robinson's discovery of the resolution and unification algorithm

for logical deduction in 1963. This procedure is simple, complete and
entirely algorithmic, and can easily be performed by digital computers.
However, a naive implementation of the algorithm quickly leads to a
combinatorial explosion or an infinite loop. In 1974, Robert Kowalski
suggested representing logical expressions as Horn clauses (statements
in the form of rules: "if p then q"), which reduced logical deduction to
backward chaining or forward chaining. This greatly alleviated (but did
not eliminate) the problem.

Logic is used for knowledge representation and problem solving, but it

can be applied to other problems as well. For example, the satplan
algorithm uses logic for planning, and inductive logic programming is a
method for learning.

There are several different forms of logic used in AI research.

•Propositional or sentential logic is the logic of statements which can be

true or false.
•First-order logic also allows the use of quantifiers and predicate and
can express facts about objects, their properties, and their relations with
each other.
•Fuzzy logic, a version of first-order logic which allows the truth of a
statement to be represented as a value between 0 and 1, rather than
simply True (1) or False (0). Fuzzy systems can be used for uncertain
reasoning and have been widely used in modern industrial and consumer
product control systems.
•Default logics, non-monotonic logics and circumscription are forms of
logic designed to help with default reasoning and the qualification
problem.
•Several extensions of logic have been designed to handle specific
domains of knowledge, such as: description logics; situation calculus,
event calculus and fluent calculus (for representing events and time)
causal calculus; belief calculus; and modal logics.

Probabilistic Methods for Uncertain Reasoning

Many problems in AI (in reasoning, planning, learning, perception and

robotics) require the agent to operate with incomplete or uncertain
information. Starting in the late 80s and early 90s, Judea Pearl and
others championed the use of methods drawn from probability theory
and economics to devise a number of powerful tools to solve these
problems[120].

Bayesian networks are very general tool that can be used for a large
number of problems: reasoning (using the Bayesian inference
algorithm), learning (using the expectation-maximisation algorithm),

167
MBA 757 DECISION SUPPORT SYSTEM

planning (using decision networks) and perception (using dynamic

Bayesian networks).

Probabilistic algorithms can also be used for filtering, prediction,

smoothing and finding explanations for streams of data, helping
perception systems to analyse processes that occur over time[126] (e.g.,
hidden Markov models and Kalman filters).

Planning problems have also taken advantages of other tools from

economics, such as decision theory and decision analysis, information
value theory, Markov decision processes, dynamic decision networks
game theory and mechanism design.

Classifiers and Statistical Learning Methods

The simplest AI applications can be divided into two types: classifiers

("if shiny then diamond") and controllers ("if shiny then pick up").
Controllers do however also classify conditions before inferring actions,
and therefore classification forms a central part of many AI systems.

Classifiers are functions that use pattern matching to determine a closest

match. They can be tuned according to examples, making them very
attractive for use in AI. These examples are known as observations or
patterns. In supervised learning, each pattern belongs to a certain
predefined class. A class can be seen as a decision that has to be made.
All the observations combined with their class labels are known as a
data set.

When a new observation is received, that observation is classified based

on previous experience. A classifier can be trained in various ways;
there are many statistical and machine learning approaches.

A wide range of classifiers are available, each with its strengths and
weaknesses. Classifier performance depends greatly on the
characteristics of the data to be classified. There is no single classifier
that works best on all given problems; this is also referred to as the "no
free lunch" theorem. Various empirical tests have been performed to
compare classifier performance and to find the characteristics of data
that determine classifier performance. Determining a suitable classifier
for a given problem is however still more an art than science.

The most widely used classifiers are the neural network, kernel methods
such as the support vector machine, k-nearest neighbor algorithm,
Gaussian mixture model, naive Bayes classifier, and decision tree. The
performances of these classifiers have been compared over a wide range
of classification tasks [139] in order to find data characteristics that
determine classifier performance.

168
MBA 757 DECISION SUPPORT SYSTEM

Neural Networks

A neural network is an interconnected group of nodes, akin to the vast

network of neurons in the human brain.

The study of artificial neural networks began in the decade before the
field AI research was founded. In the 1960s Frank Rosenblatt developed
an important early version, the perceptron. Paul Werbos developed the
back propagation algorithm for multilayer perceptrons in 1974, which
led to a renaissance in neural network research and connectionism in
general in the middle 1980s. The Hopfield net, a form of attractor
network, was first described by John Hopfield in 1982.

Common network architectures which have been developed include the

feedforward neural network, the radial basis network, the Kohonen self-
organising map and various recurrent neural networks. Neural networks
are applied to the problem of learning, using such techniques as Hebbian
learning, competitive learning and the relatively new field of
Hierarchical Temporal Memory which simulates the architecture of the
neocortex.

3.4 Specialised Languages

AI researchers have developed several specialised languages for AI

research:

•IPL, one of the first programming languages, developed by Alan

Newell, Herber Simon and J. C. Shaw.
•Lisp was developed by John McCarthy at MIT in 1958. There are many
dialects of Lisp in use today.
•Prolog, a language based on logic programming, was invented by
French researchers Alain Colmerauer and Phillipe Roussel, in
collaboration with Robert Kowalski of the University of Edinburgh.
•STRIPS, a planning language developed at Stanford in the 1960s.
•Planner developed at MIT around the same time.

AI applications are also often written in standard languages like C++

and languages designed for mathematics, such as Matlab and Lush.

3.5 Evaluating Artificial Intelligence

How can one determine if an agent is intelligent? In 1950, Alan Turing

proposed a general procedure to test the intelligence of an agent now
known as the Turing test. This procedure allows almost all the major
problems of artificial intelligence to be tested. However, it is a very

169
MBA 757 DECISION SUPPORT SYSTEM

difficult challenge and at present all agents fail.

Artificial intelligence can also be evaluated on specific problems such as

small problems in chemistry, hand-writing recognition and game-
playing. Such tests have been termed subject matter expert Turing tests.
Smaller problems provide more achievable goals and there are an ever-
increasing number of positive results.

The broad classes of outcome for an AI test are:

•optimal: it is not possible to perform better

•strong super-human: performs better than all humans
•super-human: performs better than most humans
•sub-human: performs worse than most humans

For example, performance at checkers (draughts) is optimal,

performance at chess is super-human and nearing strong super-human
and performance at many everyday tasks performed by humans is sub-
human.

3.6 Competitions and Prizes

There are a number of competitions and prizes to promote research in

artificial intelligence. The main areas promoted are: general machine
intelligence, conversational behaviour, data-mining, driverless cars,
robot soccer and games.

3.7 Applications of Artificial Intelligence

Artificial intelligence has been used in a wide range of fields including

medical diagnosis, stock trading, robot control, law, scientific discovery
and toys.

Many practical applications are dependent on artificial neural networks,

networks that pattern their organisation in mimicry of a brain's neurons,
which have been found to excel in pattern recognition.
Artificial
Intelligence

Cognitive Robotic Natural

Science Applications Interface
Application
-Expert Systems -Virtual Recognition
-Learning Systems - Tactility - Natural Languages
-Fuzzy Logic - Dexterity - Speech Recognition
-170
Genetic Algorithms - Locomotion - Multi-sensory
- Neural Networks - Virtual Rea
- Intelligent Agent
MBA 757 DECISION SUPPORT SYSTEM

Figure 2: The major Application Areas of Artificial Intelligence

Computer Science

AI researchers have created many tools to solve the most difficult

problems in computer science. Many of their inventions have been
adopted by mainstream computer science and are no longer considered a
part of AI. According to Russell & Norvig (2003, p. 15), all of the
following were originally developed in AI laboratories:

•time sharing
•interactive interpreters
•graphical user interfaces and the computer mouse
•rapid development environments
•the linked list data type
•automatic storage management
•symbolic programming
•functional programming
•dynamic programming
•object-oriented programming

Business

Banks use artificial intelligence systems to organise operations, invest in

stocks, and manage properties. In August 2001, robots beat humans in a
simulated financial trading competition.
Financial institutions have long used artificial neural network systems to
detect charges or claims outside of the norm, flagging these for human
investigation.

Medical Clinics

A medical clinic can use artificial intelligence systems to organise bed

schedules, make a staff rotation, and provide medical information.

They may also be used for medical diagnosis.

Artificial neural networks are used for medical diagnosis (such as in

Concept Processing technology in EMR software), functioning as

171
MBA 757 DECISION SUPPORT SYSTEM

machine differential diagnosis.

Heavy Industry

Robots have become common in many industries. They are often given
jobs that are considered dangerous to humans. Robots have proven
effective in jobs that are very repetitive which may lead to mistakes or
accidents due to a lapse in concentration and other jobs which humans
may find degrading. General Motors uses around 16,000 robots for tasks
such as painting, welding, and assembly. Japan is the leader in using and
producing robots in the world. In 1995, 700,000 robots were in use
worldwide; over 500,000 of which were from Japan.

Toys and Games

The 1990s saw some of the first attempts to mass-produce domestically

aimed types of basic Artificial Intelligence for education, or leisure. This
prospered greatly with the Digital Revolution, and helped introduce
people, especially children, to a life of dealing with various types of AI,
specifically in the form of Tamagotchis and Giga Pets, the Internet
(example: basic search engine interfaces are one simple form), and the
first widely released robot, Furby. A mere year later an improved type of
domestic robot was released in the form of Aibo, a robotic dog with
intelligent features and autonomy.

Aviation

The Air Operations Division AOD, uses for the rule based expert
systems. The AOD has use for artificial intelligence for surrogate
operators for combat and training simulators, mission management aids,
support systems for tactical decision making, and post processing of the
simulator data into symbolic summaries.
The use of artificial intelligence in simulators is proving to be very
useful for the AOD. Airplane simulators are using artificial intelligence
in order to process the data taken from simulated flights. Other than
simulated flying, there is also simulated aircraft warfare. The computers
are able to come up with the best success scenarios in these situations.
The computers can also create strategies based on the placement, size,
speed, and strength of the forces and counter forces. Pilots may be given
assistance in the air curing combat by computers. The artificial
intelligent programs can sort the information and provide the pilot with
the best possible manoeuvres, not to mention getting rid of certain
manoeuvres that would be impossible for a sentient being to perform.
Multiple aircraft are needed to get good approximations for some
calculations so computer simulated pilots are used to gather data. These
computer simulated pilots are also used to train future air traffic
controllers.

172
MBA 757 DECISION SUPPORT SYSTEM

The system used by the AOD in order to measure performance was the
Interactive Fault Diagnosis and Isolation System, or IFDIS. It is a rule
based expert system put together by collecting information from TF-30
documents and the expert advice from mechanics that work on the
TF-30. This system was designed to be used for the development of the
TF-30 for the RAAF F-111C. The performance system was also used to
replace specialised workers. The system allowed the regular workers to
communicate with the system and avoid mistakes, miscalculations, or
having to speak to one of the specialised workers.

The AOD also uses artificial intelligence in speech recognition software.

The air traffic controllers are giving directions to the artificial pilots and
the AOD wants the pilots to respond to the ATC’s with simple
responses. The programs that incorporate the speech software must be
trained, which means they use neural networks. The program used, the
Verbex 7000, is still a very early program that has plenty of room for
improvement. The improvements are imperative because ATCs use very
specific dialogue and the software needs to be able to communicate
correctly and promptly every time.

The Artificial Intelligence supported Design of Aircraft, or AIDA, is

used to help designers in the process of creating conceptual designs of
aircraft. This program allows the designers to focus more on the design
itself and less on the design process. The software also allows the user to
focus less on the software tools. The AIDA uses rule based systems to
compute its data. This is a diagram of the arrangement of the AIDA
modules. Although simple, the program is proving effective.

In 2003, NASA’s Dryden Flight Research Center, and many other

companies, created software that could enable a damaged aircraft to
continue flight until a safe landing zone can be reached. The Intelligent
Flight Control System was tested on an F-15, which was heavily
modified by NASA. The software compensates for all the damaged
components by relying on the undamaged components. The neural
network used in the software proved to be effective and marked a
triumph for artificial intelligence.

The Integrated Vehicle Health Management system, also used by

NASA, on board an aircraft must process and interpret data taken from
the various sensors on the aircraft. The system needs to be able to
determine the structural integrity of the aircraft. The system also needs
to implement protocols in case of any damage tothe vehicle.

4.0 CONCLUSION

173
MBA 757 DECISION SUPPORT SYSTEM

Artificial Intelligence (AI) is the concept that computers can be

programmed to carry out certain logical processes which are normally
associated with human intelligence rather than with machines, such as
learning, adaptation and self-correction. The application of AI is
numerous and cuts across all works and life. It is one other good thing
that has happened to human development. Many businesses have
adopted the concept to enhance their productivity and efficiency.

5.0 SUMMARY

• Organisations are using artificial intelligence (AI) to capture

individual and collective knowledge and to codify and internalise
their knowledge base. AI can be defined as the effort to develop
computer-based system (both hardware and software) that behaves as
humans.
• Successful AI systems are based on human expertise, knowledge and
selected reasoning patterns, but they do not exhibit the intelligence of
human beings.
• Although AI applications are much more limited than human
intelligence, they are of great interest to business.
• In the course of 50 years of research, AI has developed a large
number of tools to solve the most difficult problems in computer
science.
• AI researchers have developed several specialised languages for AI
research.
• In 1950, Alan Turing proposed a general procedure to test the
intelligence of an agent now known as the Turing test. This
procedure allows almost all the major problems of artificial
intelligence to be tested.
• There are a number of competitions and prizes to promote research
in artificial intelligence.
• Artificial intelligence has been used in a wide range of fields
including medical diagnosis, stock trading, robot control, law,
scientific discovery and toys.

6.0 TUTOR-MARKED ASSIGNMENT

1. Give 5 reasons why business community favour Artificial

Intelligence.
2. Mention 5 areas in computer science that Artificial Intelligence
research has helped to create tools for problem solving.

7.0 REFERENCES/FURTHER READING

Russell, Stuart J. & Norvig, Peter (2003). Artificial Intelligence: A

Modern Approach (2nd ed.). Upper Saddle River, NJ: Prentice

174
MBA 757 DECISION SUPPORT SYSTEM

Hall, ISBN 0-13-790395-2.

Nordlander, Tomas Eric (2001). AI Surveying: Artificial Intelligence in

Business. (MS Thesis), De Montfort University.

Norton, Peter (1995). Introduction to Computers. Macmillan/McGraw-

Hill.

175