Advanced Information Systems

Dr. Md. Rakibul Hoque

University of Dhaka
 Enhancing Decision Making

 What are the different types of decisions and how does

the decision-making process work? How do
information systems support the activities of managers
and management decision making?
 How do business intelligence and business analytics
support decision making?
 How do different decision-making constituencies in an
organization use business intelligence? What is the
role of information systems in helping people working
in a group make decisions more efficiently?
 Decision Making and
Information Systems

 Business value of improved decision-making

 Improving hundreds of thousands of “small” decisions adds
up to a large annual value for the business
 Types of decisions:
 Unstructured: The decision maker must provide judgment,
evaluation, and insight to solve the problem
 Structured: Repetitive and routine; involve definite
procedure for handling so they do not have to be treated
each time as new
 Semi-structured: Only part of the problem has a clear-cut
answer provided by the accepted procedure
 INFORMATION REQUIREMENTS OF KEY DECISION-MAKING GROUPS
IN A FIRM

FIGURE 12-1 Senior managers, middle managers, operational managers, and employees have different types of
decisions and information requirements.
 Decision Making and
Information Systems

• Senior managers:
– Make many unstructured decisions
– For example: Should we enter a new market?

• Middle managers:
– Make more structured decisions but these may include unstructured
components
– For example: Why is order fulfillment report showing decline in
Minneapolis?

• Operational managers, rank and file

employees
– Make more structured decisions
– For example: Does customer meet criteria for credit?
 The Decision-Making Process

The decision-making
process is broken
down into four
stages.
 The Decision-Making Process

• The four stages of the decision-making process

1. Intelligence
• Discovering, identifying, and understanding the problems
occurring in the organization
2. Design
• Identifying and exploring solutions to the problem
3. Choice
• Choosing among solution alternatives
4. Implementation
• Making chosen alternative work and continuing to monitor
how well solution is working
 Managers and Decision
Making

• Managerial Roles
• Information systems can only assist in some of
the roles played by managers
• Classical model of management: five functions
– Planning, organizing, coordinating, deciding, and controlling
• More contemporary behavioral models
– Actual behavior of managers appears to be less systematic,
more informal, less reflective, more reactive, and less well
organized than in classical model
 Managers and Decision
Making

 Mintzberg’s 10 managerial roles

 Interpersonal roles
1. Figurehead
2. Leader
3. Liaison
 Informational roles
4. Nerve center
5. Disseminator
6. Spokesperson
 Decisional roles
7. Entrepreneur
8. Disturbance handler
9. Resource allocator
10. Negotiator
 Managers and Decision
Making

• Real-World Decision Making

• Three main reasons why investments in information
technology do not always produce positive results
1. Information quality
• High-quality decisions require high-quality information
2. Management filters
• Managers have selective attention and have variety of
biases that reject information that does not conform to
prior conceptions
3. Organizational inertia and politics
• Strong forces within organizations resist making decisions
calling for major change
 Managers and Decision
Making

 High-velocity automated decision making

 Made possible through computer algorithms precisely
defining steps for a highly structured decision
 Humans taken out of decision
 For example: High-speed computer trading programs
 Trades executed in 30 milliseconds
 Responsible for “Flash Crash” of 2010
 Require safeguards to ensure proper operation and
regulation
 Business Intelligence and
Decision Making
 Business Intelligence (BI) is an umbrella term that
combines architectures, tools, databases, analytical tools,
applications and methodologies. BI’s major objective is to
enable interactive access (sometimes in real-time) to data,
to enable manipulation of data, and to give business
managers and analysts the ability to conduct appropriate
analysis.
 Business intelligence
 Infrastructure for collecting, storing, analyzing data

produced by business
 Databases, data warehouses, data marts
 The Business Intelligence Environment

Business intelligence
and analytics requires
a strong database
foundation, a set of
analytic tools, and an
involved management
team that can ask
intelligent questions
and analyze data.

Management Information System (MIS) 3. Decision Support System (DSS)

4. Executive Information System (EIS)
 The Business Intelligence
Environment
Six elements in the business intelligence
environment
 Data from the business environment

 Business intelligence infrastructure

 Business analytics toolset

 Managerial users and methods

 Delivery platform—M I S, D S S, E S S

 User interface

 Data visualization tools

 Business Intelligence
Capabilities

• Business intelligence capabilities

– Goal is to deliver accurate real-time information to
decision makers
– Main functionalities of BI systems
1. Production reports
2. Parameterized reports
3. Dashboards/scorecards
4. Ad hoc query/search/report creation
5. Drill down
6. Forecasts, scenarios, models
 Business Intelligence
Capabilities

 Production reports
 Most widely used output of BI suites
 Common predefined, prepackaged reports
 Sales: Forecast sales; sales team performance
 Service/call center: Customer satisfaction; service cost
 Marketing: Campaign effectiveness; loyalty and attrition
 Procurement and support: Supplier performance
 Supply chain: Backlog; fulfillment status
 Financials: General ledger; cash flow
 Human resources: Employee productivity; compensation
 Business Intelligence
Users

Casual users are consumers of BI output, while intense power users are the producers of reports,
new analyses, models, and forecasts.
 Business Intelligence
Users
• Business intelligence users
– 80 percent are casual users relying on production reports
– Senior executives
• Use monitoring functionalities
– Middle managers and analysts
• Ad-hoc analysis
– Operational employees
• Prepackaged reports
• For example: sales forecasts, customer satisfaction, loyalty
and attrition, supply chain backlog, employee productivity
 Decision support for Operational
and Middle Management

 Operational and middle managers

 Use MIS (running data from TPS) for:
 Routine production reports
 Exception reports
 “Super user” and business analysts
 Use DSS for:
 More sophisticated analysis and custom reports
 Semistructured decisions
 Decision support for Operational
and Middle Management

 Decision support systems: Support for

semistructured decisions
 Use mathematical or analytical models
 Allow varied types of analysis
 “What-if” analysis
 Sensitivity analysis
 Backward sensitivity analysis
 Multidimensional analysis / OLAP
 For example: pivot tables
 SENSITIVITY ANALYSIS

This table displays the results of a sensitivity analysis of the effect of changing the sales price of a
necktie and the cost per unit on the product’s break-even point. It answers the question, “What
happens to the break-even point if the sales price and the cost to make each unit increase or
decrease?”
 A PIVOT TABLE THAT EXAMINES CUSTOMER REGIONAL DISTRIBUTION AND ADVERTISING SOURCE

In this pivot table, we

are able to examine
where an online
training company’s
customers come from
in terms of region and
advertising source.
 Support for Senior
Management

• ESS: decision support for senior management

– Help executives focus on important performance
information
– Balanced scorecard method:
• Measures outcomes on four dimensions:
1. Financial
2. Business process
3. Customer
4. Learning and growth
• Key performance indicators (KPIs) measure each
dimension
 THE BALANCED SCORECARD FRAMEWORK

FIGURE 12-7

In the balanced scorecard framework, the firm’s

strategic objectives are operationalized along
four dimensions: financial, business process,
customer, and learning and growth. Each
dimension is measured using several KPIs.
 Support for Senior
Management

 Decision support for senior management (cont.)

 Business performance management (BPM)
 Translates firm’s strategies (e.g., differentiation, low-
cost producer, scope of operation) into operational
targets
 KPIs developed to measure progress toward targets
 Data for ESS
 Internal data from enterprise applications
 External data such as financial market databases
 Drill-down capabilities
 Management strategies for BI

 Two main management strategies for

developing BI capabilities
1. One-stop integrated solution
– Hardware firms sell software that run optimally on
their hardware
– Makes firm dependent on single vendor—switching
costs
2. Multiple best-of-breed solution
– Greater flexibility and independence
– Potential difficulties in integration
– Must deal with multiple vendors
 Group decision support
systems

• Group decision support systems (GDSS)

– Interactive system to facilitate solution of unstructured
problems by group
– Specialized hardware and software; typically used in
conference rooms
• Overhead projectors, display screens
• Software to collect, rank, edit participant ideas and responses
• May require facilitator and staff
– Enables increasing meeting size and increasing
productivity
– Promotes collaborative atmosphere, anonymity
– Uses structured methods to organize and evaluate ideas
 Contemporary Business
Intelligence Infrastructure

A contemporary business intelligence infrastructure features capabilities and tools to manage and
analyze large quantities and different types of data from multiple sources. Easy-to-use query and
reporting tools for casual business users and more sophisticated analytical toolsets for power users are
included.
 Data Warehouse
 A data warehouse is a large store of data accumulated from
a wide range of sources within a company and used to guide
management decisions.
 It is a database that stores current and historical data of
potential interest to decision makers throughout the company.
A data warehouse is a collection of data drawn from other
databases used by the business.
 Billing systems (systems printing bills)
 Reminder systems (systems sending out reminders, if customers do
not pay on time, and credit scores)
 Debt collection systems (status on cases that were outsourced for
external collection)
 Data Warehouse

 Customer relationship management (CRM) systems (systems for storing

history about customer meetings and calls)
 Product and purchasing information (which products and services a customer
has purchased over time)
 Customer information (names, addresses, opening of accounts, cancellations,
special contracts, segmentations, etc.)
 Corporate information (industry codes, number of employees, accounts figures)
 Campaign history (who received which campaigns and when)
 Web logs (information about customer behavior on our portals)
 Social network information (e.g., Facebook and Twitter)
 Various questionnaire surveys carried out over time
 Human resources (HR) information (information about employees, time sheets,
their competencies, and history)
 Architecture and Processes
in a Data Warehouse
Data floats from source systems to the BI Portal
 Data Mart
 The data mart is a subset of the data warehouse and is
usually oriented to a specific business line or team. Whereas
data warehouses have an enterprise-wide depth, the
information in data marts pertains to a single department.
 A data mart represents the specific data from a data
warehouse which a user needs.
 It is a subset of data warehouse in which a summarized or
highly focused portion of the organization’s data is placed
in a separate database for a specified function or group of
users.
 Data Mining
• Data mining is a complex process of examining large sets
of data for identifying patterns and then using them for
valuable business insights.
• Data mining is focused on better understanding of
characteristics and patterns among variables in large
databases using a variety of statistical and analytical tools.
• Data mining is the process of employing one or more
computer learning techniques to automatically analyze
and extract knowledge from data contained within a
database.
 Data Mining
 The business wants information and knowledge,
while analysts conduct data mining and provide
both statistics and tables based on data.
 Where statistics is a hypothesis driven process with the
aim of creating knowledge.
 Data mining is more of a data driven process with the
aim of finding actionable patterns in the data.
 Data mining analysts will typically let the algorithms
find the optimum model, without any major
theoretical restrictions.
 Example
 This means that we scan the data for patterns and we
evaluate the quality of the decision support the process
generates via testing the model on an unknown data set.
In statistics we evaluate the quality of the decision support
via monitor the level of significance and screen for whether
it is a relevant test in the first place.
 Data mining is typically used to give decision support on
questions like:
 Which of our engines will break down when and why?
 Which customers will leave us when and why?
 Which customers will buy what and when?
 Which customers have high credit risk?
 What is the price of our products next year?
 Data Mining
 Data mining: Data mining technology allows a digital firm
to get more information than ever before from its data.
Finds hidden patterns, relationships in datasets
 Example: customer buying patterns
 Infers rules to predict future behavior
 Types of information obtainable from data mining:
 Associations
 Sequences
 Classification
 Clustering
 Forecasting
 Text Mining
 Text mining: Text mining tools help scrub text files to find
data or to discern patterns and relationships.
 Extracts key elements from large unstructured data

sets
 Stored e-mails
 Call center transcripts
 Legal cases
 Patent descriptions
 Service reports, and so on
 Sentiment analysis software
 Mines e-mails, blogs, social media to detect opinions
 Web Mining
 Web mining
 Discovery and analysis of useful patterns and
information from Web
– Understand customer behavior
– Evaluate effectiveness of Web site, and so on
 Web content mining
 Mines content of Web pages
 Web structure mining
 Analyzes links to and from Web page
 Web usage mining
 Mines user interaction data recorded by Web server
 CRISP-DM methodology
Centre for Research in Schemes and Policies
 CRISP-DM stands for cross-industry process for
data mining. The CRISP-DM methodology provides
a structured approach to planning a data mining
project. It is a robust and well-proven methodology.
This model is an idealized sequence of events. In
practice many of the tasks can be performed in a
different order and it will often be necessary to
backtrack to previous tasks and repeat certain
actions.
 Proposed in 1990s by a European consortium
 Composed of six consecutive steps
 What is CRISP DM?

The Cross Industry Standard Process for Data Mining (CRISP-DM) is a process model
that serves as the base for a data science process.
It has six sequential phases:
1.Business understanding – What does the business need?
2.Data understanding – What data do we have/need? Is it clean?
3.Data preparation – How do we organize the data for modeling?
4.Modeling – What modeling techniques should we apply?
5.Evaluation – Which model best meets the business objectives?
6.Deployment – How do stakeholders access the results?
CRISP-DM methodology
 CRISP-DM methodology

 Step 1: Business Understanding  Accounts for


 Step 2: Data Understanding  ~85% of total
 Step 3: Data Preparation  project time

 Step 4: Model Building
 Step 5: Testing and Evaluation
 Step 6: Deployment
 CRISP-DM methodology
 Business Understanding: Problem Definition
 Understanding the project objectives and requirements
from a business perspective, and then converting this
knowledge into a data mining problem definition, and a
preliminary project plan designed to achieve the objectives.
 It is always important to fully understand the socioeconomic
climate, business goals, and underlying issues.
 Situational context, specific objectives, project schedule,
deliverables
 Who is the end user?
 What is the end benefit?
 How will it be deployed?
 What is the champion?
 What are the issues with the champion?
CRISP-DM methodology
 CRISP-DM methodology
 Data Understanding
 Collecting raw data, preliminary results,
potential hypotheses
 What data do you need?
 What data is available?

 Where is the data?

 What are the privacy norms to comply with?

 CRISP-DM methodology
 Data Preparation
 Record and variable selection, data
reduction, wrangling and cleaning, data
transformation
 The most time consuming step
 Data Quality

 Data transformation

 Clean data

 Format data
 CRISP-DM methodology
 Model Building
 Selection and execution of data mining
techniques and models, convert to
formats/types needed for certain analyses,
document assumptions, cross-validation
 Choose appropriate technique
 Build Model

 Assess Model
 CRISP-DM methodology
 Testing and Evaluation: Evaluate performance
of competing models, review and interpret
results, develop recommendations.
 Deployment: Develop a set of actionable
insights and a strategy for
deployment/monitoring/feedback
 Decision Engineering

 Implementation

 Maintenance
Thank
You