Business

Intelligence
and Analytics
(ITISA1-22
(2024))

Lecturer: ‘Banjo Aderemi

 Define the terms
business
intelligence (BI)
and analytics.
Objective
s of
Business Identify several
BI techniques
Intelligen and discuss how
they are used.
ce and
Analytics
(BIA) Define the term
self-service
analytics and
discuss its pros
and cons.
 Collaborative Case
Study
•Netflix Uses Analytics to Pick Winners

• Netflix users generate a large amount of detailed information about their

interests, tastes, and viewing habits. It uses this data and analytics to
generate viewing recommendations, which users appreciate because they
are usually right. Netflix also uses data and analytics to predict user
demand for the many productions it is considering adding to its lineup.
When Netflix cuts a deal with talent like Martin Scorsese, Ryan Reynolds,
or the Obamas, it is based on a data model that predicts the probability of
success of a certain combination of talent, likely plots, and other factors.
Not only can Netflix predict the probability of success, it can predict with a
high degree of accuracy which of its subscribers will watch a given series.

• Source: Stair, R. and Reynolds, G. 2020. Principles of Information Systems.

14th edition. UK: Cengage Learning.
• Questions:
• What tools and technologies might Netflix use to store and process all this
data?
• Why may have it been necessary to perform an ETL process on all this
data?
 Sources of
Big Data
•Big Data - data collections that
are so enormous and complex
that traditional data
management software,
hardware, and analysis
processes are incapable of
dealing with them.
• Sources of Big Data
• Organizations collect and use
data from a variety of
sources, including business
applications, social media,
sensors and controllers that
are part of the manufacturing
process etc
 BI involves the use of wide range of
applications, practices and technologies for
the extraction, transformation, integration,
visualisation, analysis, interpretation and
presentation of data (usually obtained from
multiple sources) to support improved
decision making.

Business The primary aim of BI is to obtain vital

information and present the analysis results
intelligen in a manner that is easy for the layman to
understand.
ce (BI)

Applications of BI include data

warehouses, data marts and data lakes.
 Reason for BI & A
• It helps organisation to analyse large amounts of data to
measure past and current performance as well as make future
predictions about business opportunities.
• The predictions help to improve business strategies, strengthen
business operations, and enrich decision making and thus,
enable organisation to become more competitive (outpace their
peers).
• Financial services use BI and analytics to understand their
customers in order to enhance service, create new and more
appealing products and better manage risk.
• It assists marketing managers to analyse data related to the
Web-surfing habits, past purchases, and even social media
activity of existing and potential customers to create highly
effective marketing programs that generate consumer interest
and increased sales.
• It enables health care professionals to improve the patient
experience to maximise reimbursements, lower costs and
ultimately deliver higher quality care for patients.
 Business analytics (BA)

• Business analytics is the extensive use of data

and quantitative analysis to support fact-based
decision making within organisations.

• It is used to understand current business

performance, reveal new business patterns and
relationships, explain why certain results
occurred, optimise current operations and forecast
future business results.
 Benefits/Importance of BI and
Analytics
• Detect fraud: Analytical software is used in special
investigations unit (SIU) to identify medical provider,
attorney and repair shop fraud.
• Improve forecasting: BI and A can assist
organisations to predict customer demand, visualize
inventory levels, adapt to user feedback and reduce
its overall inventory costs.
• Increase Sales: The BIA enables managers to
evaluate potential incentives, acquisition method
and improve sales.
• Optimise operations: Complex and constantly
changing industrial (such as petroleum industry and
financial services) operations can be simplified
using analytical system, in order to maximise profit.
• The BA can dramatically assist organisations to
minimise costs using analytics software.
Roles of a Data Scientist (DS) in BI & A
Data scientists are individuals who combine strong business
acumen, a deep understanding of analytics, and a healthy
appreciation of the limitations of their data, tools, and
techniques to deliver real improvements in decision making.
Functions include:
• Data scientists collect and report on data to present a
situation using appropriate data and tools.
• Data scientist provide valuable insights that can influence
organisational decisions and help organisations to achieve
competitive advantage.
• Data scientists continually ask questions, challenges
assumptions and existing processes.
• They have an ability to communicate their findings to
organisational leaders convincingly so that they are able to
strongly influence how an organisation approaches business
opportunities.
• Commonly used DS tools include SQL, Python, R and Java.
 Components Required for Effective BI and
Analytics

Existence of a solid data management program and data

governance.
• Data management is an integrated set of
functions that defines the processes by which
data is obtained, certified fit for use, stored,
secured, and processed in such a way as to
ensure that the accessibility, reliability and
timeliness of the data meet the needs of the data
users within an organisation
while
• Data governance is a core component of data
management that defines the roles,
responsibilities and processes for ensuring that
data can be trusted and used by the entire
organisation, with people who are responsible for
Components Required for Effective BI and
Analytics
Cont.
Creative data scientists—people who
understand the business, identify the
limitations of their data, tools, and techniques.
These are needed to deliver real improvements
in decision making with an organisation.
Organisation's management team must have a
strong commitment to data-driven decision
making. This will enable the organisation to
make quick superior decisions in uncertain and
changing situations so as to gain strong
competitive advantage.
 Business Intelligence and Analytics Tools

• Spreadsheets: Data can be imported into an excel

spreadsheet program, which can then be used to
perform operations on the data based on formulas
created by the end user. Spreadsheets are also used
to create reports and graphs based on that data.

• Reporting and Querying Tools: Some reporting

tools enable organisation's employees to get data
access, present that data in an easy-to-understand
way (via formatted data, graphs, and charts) so as
to solve a problem or identify an opportunity
without additional help from IT organisation. E.g.
Power BI, Whatagraph, Tableu etc.
Business Intelligence and Analytics Tools

• Data Visualisation Tools: Data visualisation is the

presentation of data in a pictorial or graphical format. This
will enhance human minds to understand better trends,
patterns and relationships of data than tabular data. E.g.
Google Charts, Tableau, Grafana, Chartist, FusionCharts,
Datawrapper, Infogram, and ChartBlocks etc

• Online Analytical Processing (OLAP): A software

technology you can use to analyze business data from
different points of view.

It is a method used to analyse multidimensional data from

many different perspectives. It enables users to identify
issues and opportunities as well as perform trend analysis.
Databases built to support OLAP processing consist of data
cubes that contain numeric facts called measures, which
are categorised by dimensions, such as time and geography.
• Drill-down analysis: It involves the interactive examination
of high-level summary data in increasing detail to gain
insight into certain elements— an act comparable to slowly
peeling off the layers of an onion. Drill-down analysis is a
powerful tool used to gain insight into details of business
data to better understand why something happened.

• Linear regression: A mathematical technique used to

predict the value of a dependent variable based on a single
independent variable and the linear relationship between the
two. It involves finding the best fitting straight line through a
set of observations of dependent andSee independent
page 393 of variables.
the
recommended textbook
The regression line is written as:

X = Observed value of the independent variable

Y = Predicted value of the dependent variable
a = Value of Y when X is zero, or the Y intercept
b = Slope of the regression line
= Error in predicting the value of Y, given a value of X
Criteria/Assumptions that must be
satisfied when using linear regression on a
dataset:

• A linear relationship between the independent (X)

and dependent (Y) variables must exist.
• Errors in the prediction of the value of Y are
distributed in a manner that approaches the
normal distribution curve.
• Errors in the prediction of the value of Y are all
independent of one another.
• Data Mining: A BI analytics tool used to explore large
amounts of data for hidden patterns
to predict future trends and
behaviours for use in
It enable organisations to make predictions about what will
happen so that managers can be proactive in capitalising
on opportunities and avoiding potential problems decision
making.
Most commonly used data mining techniques are:
1. Association analysis: A specialised set of algorithms that sorts
through data and forms statistical rules about relationships among
the items
2. Neural computing: Historical data is examined for patterns that are
then used to make predictions
3. Case-based reasoning: Historical if-then-else cases are used to
recognize patterns.

• Cross-Industry Process for Data Mining (CRISP-

DM): A six- phase structured approach used
for the planning and execution of a data
Goals for each phase of CRISP-DM

See Figure 9.7 of the recommended

textbook
 Goals for each phase of CRISP-DM cont’d.
Phase Goal

Business Clarify the business goals for the data mining project,
understanding convert the goals into a predictive analysis problem and
design a project plan to accomplish these objectives.

Data Gather data to be used (may involve multiple sources),

understanding familiarize with the data and identify missing/null data

Data Select a subset of data to be used, clean data to address

preparation quality issues, and transform data into form suitable for
analysis.

Modeling Apply selected modeling techniques

Evaluation Assess if the model achieves business goals.

Deployment Deploy the model into organization’s decision-making

process
See Table 9.1 of the
 Applications of data mining
• Based on past responses to promotional mailings,
identify those consumers most likely to take
advantage of future mailings.
• Examine retail sales data to identify unrelated
products that are frequently purchased.
• Monitor credit card transactions to identify likely
fraudulent requests for authorisation.
• Use hotel booking data to adjust room rates so as to
maximise revenue.
• Analyse demographic and behaviour data to identify
potential customers.
• Study demographic data about valuable employees to
help focus future recruiting efforts.
• Recognise how changes in individual’s DNA sequence
affect the risk of developing common diseases such
as Alzheimer’s or cancer.
the state of a process at a specific point in time in order to
help organisations run effectively.

Key performance indicators (KPIs) are metrics that

track progress in executing chosen strategies to attain
organizational objectives and goals. It consist of a
direction, measure, target and time frame.

Examples of well-defined KPIs:

• For a university: Increase (direction) the five-year
graduation rate for incoming freshmen (measure) to
at least 80 percent (target) starting with the
graduating class of 2022 (time frame).
• For a customer service department: Increase
(direction) the number of customer phone calls
answered within the first four rings (measure) to at
least 90 percent (target) within the next three months
(time frame).

• Options for displaying results in a dashboard

include: maps, gauges, bar
Category management Dashboard

See Figure 9.9 & 9.8 of the

recommended textbook
• Self-service analytics involves training, techniques and
Self-Service Analytics
processes that empower end users to work independently to
access data from approved sources to perform their own
analyses using an endorsed set of tools. It encourages
nontechnical end users to make decisions based on facts and
analyses rather than intuition and thus, eliminates decision-
making delays.

Refer to page 397 and 398 for details ….

• Steps to ensure an effective self-service analytics

program:
I. Data managers should collaborate with business units to
determine key metrics, agreed vocabulary, processes for
creating and publishing reports, define and implement
security and privacy policies.
II. Technology professionals should be allowed to retain data
control and governance while limiting information systems
staff involvement in routine tasks.
III. A self-service analytics tools must be intuitive, customisable
and easy to use.

• Commonly used BI software include: Autonomy IDOL (HP),

See Table
Cognos Business Intelligence (IBM), 9.2 of the(Information
WebFOCUS1 recommended
textbook
 Pros and cons associated with self-service
BI and analytics
Pros Cons
End users can easily get It can create the risk of erroneous
valuable data. analysis and reporting if not well
managed, and thus, can lead to
disastrous decisions within an
organisation.

Encourages non-technical end Different analyses can yield

users to make decisions based inconsistent conclusions, resulting in
on facts and analyses rather wasted time trying to explain the
than intuition. differences.

Accelerates and improves It can lead to over spending on

decision making. unapproved data sources and business
analytics tools.
Business user can access and It can worsen problems by removing
use the data they need for the checks and balances on data
decision making, without preparation and use (bad analysis).
consulting technology experts.
See Table 9.3 of the recommended
textbook
 Definition of Other Terms

• Word cloud: A visual depiction of a set of words that have been

grouped together because of the frequency of their occurrence.
• Conversion funnel: It is a graphical representation that
summarizes the steps a consumer takes in making the decision to
buy a product and become a customer. It provides a visual
representation of the conversion data between each step and
enables decision makers to see what steps are causing customers
confusion or trouble.

See Figure 9.2 of the recommended

textbook
 Definition of Terms [Cont’d]
• Data cube: A collection of data that contains
numeric facts called measures, which are categorised
by dimensions, such as time and geography.

See Figure 9.5 of the recommended

textbook

• It is important to note that data within a data cube

has been summarised at a given level and thus, data
cube cannot present a more detailed information.
Hence, Data cubes is restricted to only three
dimensions.
 Self-Assessment Test
1. The primary difference between business
intelligence and analytics is that _______________.
a. BI is used to analyze historical data to tell what
happened or is happening right now in your
business while analytics employs algorithms to
determine relationships among data to develop
predictions of what will happen in the future.
b. analytics employs techniques like optimization,
predictive analysis, and simulation while BI employs
descriptive analysis and text and visual analysis.
c. a data scientist is required to properly
employ analytics while an end user working with a
database administrator can employ BI.
d. organizations used to employ BI but now are
moving to greater use of analytics.
 Self-Assessment Test
2. _______________ is a measure of the quality of big data.
3. The fact that big data comes in many formats and may be
structured or unstructured is an indicator of its _______________.
4. Choosing what data to store and where and how to store the data
are two key challenges associated with big data. True or False?
5. _______________ is not a key challenge associated with big data.
a. How to derive value from the relevant data
b. Which format the data should be stored in
c. How to identify which data needs to be protected from unauthorized
access
d. How to find those nuggets of data that are relevant to the decision
making at hand
6. _______________ is a large database that holds business information
from many sources in the enterprise, covering all aspects of the
company’s processes, products, and customers.
a. relational database
b. data lake
c. data warehouse
 Self-Assessment Test
7. The goal of the _______________ step of the ETL process is to
take the source data from all the various sources and convert it
into a single format suitable for processing.
8. A _______________ database enables hundreds or even
thousands of servers to operate on the data, providing faster
response times for queries and updates.
a. NoSQL
b. normalized
c. SQL
d. relational
9. A _______________ differs from a _______________ in that it
provides a means to store and retrieve data that is modelled
using some means other than the simple two-dimensional tabular
relations.
a. data mart and NoSQL database
b. data mart and data warehouse
c. NoSQL database and relational database
 Self-Assessment Test

10. An individual who combines strong business

acumen, a deep understanding of analytics, and
a healthy appreciation of the limitations of their
data, tools, and techniques to deliver real
improvements in decision making is a(n)
_______________.
a. systems analyst
b. database administrator
c. data scientist
d. data steward
 Revision Questions

• What kinds of BI analytics tools and techniques is

recommended for a Fire department likely to use
in sifting through all data and determining a
building’s risk score?

• What are the key components that an

organisation must put into place to create an
environment for a successful BI and analytics
program.