Business

Analytics
Module 1
 • Howard Dresner of the Gartner Group, in
1989 coined the term BI He defined BI as
• “a set of concepts and methodologies to
improve decision making in business
through use of facts and fact based
Business systems”
• Business intelligence (BI) is an umbrella
Intelligence term that combines architectures, tools,
databases, analytical tools, applications,
Definition and methodologies.
• BI is a content-free expression, so it means
different things to different people
• BI's major objective is to enable easy access
to data (and models) to provide business
managers with the ability to conduct
analysis
 • Business Intelligence (BI) is about
getting the right information, to the
right decision makers, at the right time.
• BI is an enterprise-wide platform that
Business supports reporting, analysis and
Intelligence decision making.
Definition
Business
Intelligence
Definition
 • BI is…
• Fact-based decision making

• Single version of truth

• 360 degrees perspective on

Business your business
Intelligence
• Virtual team members on the
same page

• Visibility into enterprise

performance
Types of
decisions
supported by
Business
Intelligence
 • BI is an evolution of decision support
concepts over time
• Then: Executive Information
A Framework System
for • Now: Everybody’s Information
System (BI)
Business • BI systems are enhanced with
Intelligence (BI) additional visualizations, alerts, and
performance measurement capabilities
• The term BI emerged from industry
 • The term BI was coined by the Gartner
Group in the mid-1990s
• However, the concept is much older
• 1970s - MIS reporting - static/periodic
reports
• 1980s - Executive Information Systems
A Brief History (EIS)
• 1990s - OLAP, dynamic, multidimensional,
of BI ad-hoc reporting -> coining of the term
“BI”
• 2010s - Inclusion of AI and Data/Text
Mining capabilities; Web-based
Portals/Dashboards, Big Data, Social
Media, Analytics
• 2020s - yet to be seen
The Evolution
of BI
Capabilities
 • A BI system has four major
components
• a data warehouse, with its source
data
The • business analytics, a collection of
tools for manipulating, mining, and
Architecture of analyzing the data in the data
BI warehouse
• business performance management
(BPM) for monitoring and analyzing
performance
• a user interface (e.g., dashboard)
 Data Warehouse Business Analytics Performance and
Environment Environment Strategy
Data Technical staff Business users Managers / executives
Sources Built the data warehouse Access
Data
ü Organizing Warehouse BPM strategy
A High-Level ü Summarizing Manipulation
ü Standardizing Results
Architecture
of BI
User Interface
Future component - browser
intelligent systems - portal
- dashboard
 • Customer segmentation
• Propensity to buy
Business Value
• Customer profitability
of BI Analytical • Fraud detection
Applications • Customer attrition
• Channel optimization
 • Similarities and differences?
• Similar architectures, data focus, …
• Direct vs. indirect support
• Different target audiences – DSS Analyst
Oriented & BI Executive & Strategy
oriented(BPM & Dashboard)
• Commercially available systems versus in-
DSS-BI house development of solutions
• BI commercially available tools and components
Connections that are fitted to the needs of organizations.
• DSS the interest may be in constructing solutions to
very unstructured problems, Hence more
programming required
• Origination – Industry vs. Academia
• So, is DSS = BI ?
• For example, data mining and predictive analysis
are core tools in both areas.
 • Analytics?
• Something new or just a new name for …
• A Simple Taxonomy of Analytics
(proposed by INFORMS)
Analytics • Descriptive Analytics
• Predictive Analytics
Overview • Prescriptive Analytics

• Analytics or Data Science?

Analytics
Overview
 BASIS FOR
Business Intelligence Business Analytics
COMPARISON

Analyses past and present to Analyses past data to drive current

Definition
drive current business needs business

To run current business To change business operations and

Usage
operations improve productivity

Ease of
BI vs BA Operations
For current business operations For future business operations

SAP Business Objects, Word processing, Google docs, MS

Tools
QlikSense, TIBCO, PowerBI etc., Visio, MS Office Tools etc.,

Apply to all large-scale Applies to companies where

Applications companies to run current future growth and productivity as
business operations its goal

Contains Data warehouse,

Field Comes under Business Analytics
information management etc.,
 Transaction
Processing Vs
Analytical
Processing
 • OLTP (Online Transactional
Processing) is a category of data
processing that is focused on
transaction-oriented tasks.
OLTP(Online
• OLTP typically involves inserting,
Transaction updating, and/or deleting small
Processing) amounts of data in a database.
• OLTP mainly deals with large
numbers of transactions by a
large number of users.
 • Search for a particular customer’s
record.
• Retrieve the product description
and unit price of a particular
Queries that an product.
OLTP System • Filter all products with a unit price
can Process equal to or above $25.
• Filter all products supplied by a
particular supplier.
• Search and display the record of a
particular supplier.
 • Simplicity –It is designed typically for
use by clerks, cashiers, clients, etc.
Advantages of • Efficiency –It allows its users to read,
write and delete data quickly.
an OLTP • Fast query processing –It responds to
System user actions immediately and also
supports transaction processing on
demand.
 • Security –An OLTP system requires
concurrency control (locking) and
recovery mechanisms (logging).
Challenges of • OLTP system data content not
an OLTP suitable for decision making
• A typical OLTP system manages the
System current data within an enterprise/
organization.
• This current data is far too detailed to
be easily used for decision making.
 • The super market store is deciding on
introducing a new product.
• The key questions they are debating are:
“Which product should they introduce?”
and “Should it be specific to a few
The Queries customer segments?”
that OLTP • The super market store is looking at
offering some discount on their year-
Cannot Answer end sale.
• The questions here are: “How much
discount should they offer?” and “Should it
be different discounts for different
customer segments?”
 • OLAP differs from traditional databases
in the way data is conceptualized and
stored
OLAP(Online • In OLAP data is held in the dimensional
form rather than the relational form
Analytical
• OLAP’s life blood is multi dimensional
Processing) data OLAP tools are based on the multi
dimensional data model
• The multi dimensional data model
views data in the form of a data cube
OLAP Cube
 • What will be the future trend for
“Accessories” in the “Kids” Section?
Queries that • Given the customer buying pattern,
OLAP system will it be profitable to launch product
“XYZ” in the “kids” section?
can process • What impact will a 5% increase in price
of products have on the customers?
 • Multi dimensional data representation

• Consistency of information

Advantages of • “What if” analysis

an OLAP
System • Provides a single platform for all
information and business needs
planning, budgeting, forecasting,
reporting and analysis

• Fast and interactive ad hoc exploration

OLTP
and
OLAP
OLTP vs. OLAP
OLTP vs. OLAP
OLAP
Operations
OLAP
Operations
OLAP
Operations
OLAP
Operations
OLAP
Operations
OLAP
Operations
OLAP
Operations
 • The entity-relationship (E-R) model is
the classic, fully normalized relational
schema used in many online
transaction processing (OLTP) systems.
Data Models • The relationships between tables
signify relationships between data, not
for OLTP necessarily business relationships.
• E-R models are designed to minimize
data storage redundancy and optimize
data updates.
 • It is a graphical representation of an
information system.
• ER diagram shows the relationship
Data Models between objects, places, people,
events etc. within that system.
for OLTP • It is a data modelling technique which
helps in defining the business process.
• It used for solving the design problems.
E-R Diagram
E-R Model
E_R Model
 • Dimensional models are designed to
enhance understandability and to optimize
query performance.
• A dimensional schema is a de-normalized
schema that follows the business model.
• Dimensional schemas contain dimension
Data Models tables, which contain attributes of the
for OLAP business, and fact tables, which contain
individual records with a few facts and
foreign keys to each of the dimension
tables.
• Two types of Dimensional Models are:
1. Star Schema
2. Snowflake Schema
 • A star schema is a dimensional schema
with a single fact table that has foreign
key relationships with several
dimension tables.
• The dimension tables model the
business and contain columns with
Star Schema descriptive attributes, such as Product,
Size, and Colour in the sample
Products dimension.
• Dimension tables also have a key
column (or columns) that uniquely
identifies each row in the table.
Star Schema
Star Schema
 • The fact table has a multipart primary key,
often made up of the foreign key
references to the dimension tables.
• The fact table also contains all the
measures, or facts, used to measure
business performance.
Star Schema • The lowest level of detail stored is the
granularity of the fact table.
• Information at higher levels of
aggregation is either calculated from the
detail level records or precomputed and
stored in separate aggregate fact tables,
resulting in a multiple-star schema.
 • A snowflake schema is a dimensional
schema where one or more of the
dimensions are normalized to some
extent.
• The difference between the type of
Snowflake normalization in a snowflake schema
and in an E-R schema is that the
Schema snowflake normalization is based on
business hierarchy attributes.
• The tables snowflaked off the
dimensions have parent-child
relationships with each other that
mimic the dimensional hierarchies.
Snowflake
Schema
Snowflake
Schema
Snowflake
Schema