Question one

a) Describe any two categories of business intelligence systems. (10)

i.
Reporting systems

Provide an excellent method of controlling and keeping track

of data and as a source of business intelligence
ii.

Data mining systems

Provide ways of collecting, sieving and adding value to data

Question two
a) Describe the following two types of decisions.
i)
Programmed (structured) decisions (4)
Programmed decisions are those that a manager has
encountered and made in the past. The decision the manager
made was correct because she used the assistance of company
policies, computations or a set of decision-making guidelines. In
addition to being well structured with predetermined rules
regarding the decision-making process, programmed decisions
may also be repetitive or routine as their outcome was successful
in the past. It generally does not take a manager as long to come
to a conclusion when faced with a business-related programmed
decision because the challenge faced is not new. As a result,
programmed decisions allow a manager to make streamlined and
consistently effective choices.
Individuals naturally make programmed decisions on a daily basis. For
example, in an emergency, most people automatically decide to call 9-1-1.
From a business perspective, a company may create a standard routine
for handling technical issues, customer service problems or disciplinary
matters. An employees duties may become routine with repetition, like
the process a mechanic uses to troubleshoot problems with a customers
car.

Programmed decision are decisions that have made so many time in the past that
managers have developed rules or guideline to be applied when certain situation are
expected to occur. In certain situation, manager and employees do not really have to
make decision; it is already programmed for them in term of rule, policy and
procedure.
The example of programmed decision is used when an inventory manager of
restaurant decides to order beef stock because the stock are three-quarter empty.
Most programmed decisions are related to daily activities.
On the other hand, non-decision programmed decisions are made in respond to
unusual opportunity or threats. Basically, these situations are unique, are poorly
defined and largely unstructured. It requires conscious thinking, information
gathering and careful consideration of alternatives.
For example, in 2005, Mc Donalds became aware of a need to respond to growing
customer concerns regarding foods high in fat and calories. This is non-programmed
decision because for several decades, customers of fast food restaurant were more
concerned with the taste and the price rather than healthiness. In response, Mc
Donalds decide to offer healthier alternatives such as substituting apple slices in
Happy Meals for French Fries and discontinuing the use of trans-fats.

Programmed decision making are usually made in accordance with some establishment
habit, rule or procedures while the nature of problem that requires a nonprogrammed decision is unstructured and something different. It requires higher level
management participation.

iii-

In programmed decision making, there will be no error in the decisions because it

is a routine and managers usually have the information they need to create rules and
guidelines to be followed by others. However, the non-programmed decisions are
likely to have error because it causes more problems for managers and is inherently
challenging. Sometimes, programmed decision can caused error but it is minor to
non-programmed decision.

ii)

Non programmed ( unstructured) decisions (4)

Unprogrammed decisions involve scenarios that are new or novel
and for which there are no proven answers to use as a guide. In
such a case, a manager must make a decision that is unique to
the situation and results in a tailored solution. Unprogrammed
decisions generally take longer to make because of all the
variables an individual must weigh; and the fact that the
information available is incomplete, so a manager cannot easily
anticipate the outcome of his decision.
Examples of Unprogrammed Decisions
An individual may make an unprogrammed decision when she
visits a new restaurant, is unfamiliar with the menu and the
menu is in a language she does not understand. In the business
world, the makers of the earliest personal computers had to
make unprogrammed decisions regarding the type of marketing
to use to attract customers who possibly had never used a
computer in the past. Fast-food companies also had to make an
unprogrammed decision regarding consumer concerns about
high fat contents and lack of healthy menu options.

b) Differentiate between the following Business intelligence tools

versus business intelligent application and versus business
intelligent system (9)
Business intelligence (BI) is a broad category of applications and technologies for
gathering, storing, analyzing, and providing access to data to help enterprise users
make better business decisions.
BI applications include the activities of decision support systems, query and reporting,
online analytical processing (OLAP), statistical analysis, forecasting and data mining.
Business intelligence applications can be:

- Mission-critical and integral to an enterprise's operations or occasional to meet a

special requirement
- Enterprise-wide or local to one division, department
- Centrally initiated or driven by user demand
This term was used as early as September, 1996, when a Gartner Group report said:
By 2000, Information Democracy will emerge in forward-thinking enterprises, with
Business Intelligence information and applications available broadly to employees,
consultants, customers, suppliers, and the public. The key to thriving in a competitive
marketplace is staying ahead of the competition. Making sound business decisions
based on accurate and current information takes more than intuition. Data analysis,
reporting, and query tools can help business users wade through a sea of data to
synthesize valuable information from it - today these tools collectively fall into a
category called "Business Intelligence."

A business intelligence tool is a computer that iplements the logic of a particular

procedure or process. This is software that are used to retrieve, analyse, sort, filter,
processand report data fro business intelligence solution. These tools read raw data
that is stored in a data warehouse or datamart or information cube or tables in a
database. E.g. spread sheets, OLAP, GIS, data mining, software for reporting and
query display.
Business intelligence application uses BI tools on a particular type of data for a
particular purpose.
A BI system is an information system that has all five componants ( hardware,
software, data, procedure, people) that delivers the results of a BI application to user.
BIS process, store and provide useful information to users who need it, when they
need it. Its an information system that employs BI tool to produce and deliver
information.

c) Statistical tests are used to validate machine learning models and to

evaluate machine learning algorithms. Elucidate. (8)

Machines learn when they change their behaviour in a way that

makes them perform better in the future.
We require techniques for finding and describing structural patterns
in data as a tool for helping to explain that data and make
predictions from it.
In machine learning uses standard statistical methods:
-visualization of data,
-selection of attributes,
-Discarding,
- outliers
Statistical tests are used to validate machine learning models and
to evaluate machine learning algorithms.

Question 3
a) Explain how the following techniques are used in business intelligent
i)

systems.
Data mining (3)

Data mining is the process of discovering patterns in data.

It is about solving problems by analyzing data already present in
databases.
the data is stored electronically in data warehouse and the
search is automated by computer algorithms.
Data Mining is the top layer of Business Intelligence Pyramid. It is a powerful
tool for business executives to make them analyze consumer behavior based on
the historical records and past purchasing behavior of the customers. These
findings help the business executives to take intelligent decisions which will help
to increase revenues, identify business opportunities and to decrease expenses.

Data mining used complex mathematical techniques to interpret the patterns of

consumer behaviors. This tool is used since the decade of 1980s. Especially it is
used in academic, medical and scientific research world, as well as in retail,
banking, insurance, travel and hospitality industries.

Organizes and employs information and knowledge from databases

Statistical, mathematical, artificial intelligence, and machine-learning techniques

Automatic and fast

Tools look for patterns

Simple models

Intermediate models

Complex Models

Data mining application classes of problems

Classification

Clustering

Association

Sequencing

Regression

Forecasting

Others

Hypothesis or discovery driven

Iterative

Scalable

Data mining

ii)

Statistical methods

Decision trees

Case based reasoning

Neural computing

Intelligent agents

Genetic algorithms

Text Mining

Hidden content

Group by themes

Determine relationships

Data visualisation (3)

Data visualization is a general term used to describe any technology

that lets corporate executives and other end users see data in
order to help them better understand the information and put it in a
business context.
Data visualization is a general term that describes any effort to help people understand the
significance of data by placing it in a visual context. Patterns, trends and correlations that

might go undetected in text-based data can be exposed and recognized easier with data
visualization software.
Today's data visualization tools go beyond the standard charts and graphs used in Excel
spreadsheets, displaying data in more sophisticated ways such as infographics, dials and
gauges, geographic maps, sparklines, heat maps, and detailed bar, pie and fever charts. The
images may include interactive capabilities, enabling users to manipulate them or drill into
the data for querying and analysis. Indicators designed to alert users when data has been
updated or predefined conditions occur can also be included.
Most business intelligence software vendors embed data visualization tools into their
products, either developing the visualization technology themselves or sourcing it from
companies that specialize in visualization.
The use of visual representations to explore, make sense of, and communicate data. As such,
data visualization is a core and usually essential means to perform data analysis, and then,
once the meanings have been discovered and understood, to communicate those meanings to
others.
Helps users create advanced graphical representations of data via simple
user interfaces. The ability to visualize information in a graphical format (as
opposed to words or numbers) can help users understand data in a more
insightful way. In addition, new interactive tools can provide teams the
ability to both analyze and manipulate reports in real-time.

iii)

Geographic Information Systems (3)

Geographical information systems (GISs) make up a category of business

intelligence functionality that spans multiple categories. The simplest
way to understand GIS technology is to consider the concept of maps.
You could, for example, do querying in a tabular manner and show
product sales by country. Those sales are divided into product sales by
territory and then broken down into product sales by increasingly smaller
groupings, down to product sales by department in each store, for
example.

One business planner made the profound statement, Our

business is geographically based why cant I see our key
information on a map? GISs do just that: They provide a way of
viewing information based on presenting that information by
using maps.
Suppose that all countries colored in red indicate that sales
revenue is lower in the most recent quarter than it was in the
preceding quarter. If you click your mouse on any of those
countries, another map appears, which is divided into sales
territories and again color-coded. Clicking on a red-colored
territory displays another map (a U.S. map by state, for
example) with additional levels of detail.
When you use GIS technology, data isnt just managed in a
hierarchy such as this:
Departmentsstoresstatesterritoriescountries
The data is also managed spatially in a manner thats
sensitive to on-screen layout. For example, when you click a
map of Pennsylvania, the GIS would know that you want to
see sales in Pittsburgh, without your having to type or otherwise
select that city from a drop-down list or other on-screen control.

Computerized system for managing and manipulating data with

digitized maps
a.
b.
c.
d.
iv)

Geographically oriented
Geographic spreadsheet for models
Software allows web access to maps
Used for modeling and simulations

Data warehousing (3)

Data Warehouse contains the data, which can be used as
information through querying. This data, either transaction or
non-transaction, is used for reporting and different analyses.
Data Warehouse provides the basic foundation for the further
intelligent analysis for taking intelligent business decisions
A DW comprises of any number of duplicate transaction and / or
non transaction information that have been changed in a fashion
that they are appropriate for reporting, querying and other data
analysis. It can be related as the memory of a company. It is a

public impression that the present application of the DW will be

vanished in forth coming period. It works as a data warehouse
and is particularly employed for trade research. For example,
emphasize on data flow is the foundation of day by day growing
online analysis. A new concept has been presented as
Information Provision In Time
v)

Intelligent techniques (3)

b) Outline the Apriori Algorithm for data mining a frequent itemsets.

Apriori algorithm uses knowledge of frequent itemset priorities. It
employs an iterative approach known as alevel wise search, where k
item sets are used to explore (k+1) item sets. First, the set of frequent
k item sets is found by scanningthe database to accumulate the
count for each item and collecting those items that satisfy both
min_sup and min_conf. the resulting set is denoted L1, next L1 is used
to find L2, the set of 2_item sets, which is used to find L3 and so on
until no more frequent k items can be found. The founding of each Lk
requires one full scan of the database. To improve the efficiency of the
generation of frequent itemsets,
Question 4
a) Decision analysis is the method for structuring and analysing
managerial decision problems in the face of uncertainty, in a
systematic and rational manner. Expand (10)
b) ..
Question 5
a) List any five optimisation techniques. (5)

Constrained quadratic optimization

Gradient descent
Sequential minimal optimization
Particle swarm optimisation
Simulated annealing
Tabu search
Genetic algorithms
b) Explain the four types of errors in sensitivity analysis illustrated in
fig 5.1 (8)
bias refers to deviations that are not due to chance alone. The simplest example occurs with
a measuring device that is improperly calibrated so that it consistently overestimates (or
underestimates) the measurements by X units. has a net direction and magnitude so that
averaging over a large number of observations does not eliminate its effect. In fact, bias can
be large enough to invalidate any conclusions. Increasing the sample size is not going to
help. In human studies, bias can be subtle and difficult to detect. Even the suspicion of bias
can render judgment that a study is invalid. Thus, the design of clinical trials focuses on
removing known biases.

Drift errors are caused by deviations in the performance of the measuring

instrument (measurement system) that occur after calibration. Major causes are
the thermal expansion of connecting cables and thermal drift of the frequency
converter within the measuring instrument. These errors may be reduced by
carrying out frequent calibrations as the ambient temperature changes or by
maintaining a stable ambient temperature during the course of a measurement.

c) Queuing models and inventory models are tools and techniques that
assist in understanding the behaviour of business systems. Defend.
(12)
Question 6

a) Clarify that knowledge based decision support systems (KBDSS) are

hybrid systems of DSS and ES that help solve broad range of
business intelligence problems.