Overview of

Business
Analytics
Dr. Shweta Agarwal
Assistant Professor
SOB, UPES, Kandoli Campus
What is Data Analytics?
 The term data analytics refers to the process
of examining datasets to draw conclusions
about the information they contain.
 Encompasses a broad category of
applications, technologies and processes for
gathering, storing, accessing data.
 It involves use of analytical methods to derive
relationships from data.
 Applied and Basic Business
analytics
 Applied business analytics
 conducted to address a specific business decision for a
specific firm or organization.
 Example:
 Should McDonald’s add Italian pasta dinners to its menu?
 Which health insurance plan should a business provide for its
employees?

1–3
 Applied and Basic Business
analytics
 Basic business analytics (also called pure analytics)
• conducted without a specific decision in mind that usually does not address the
needs of a specific organization.
 Attempts to expand the limits of knowledge in general.
 Not aimed at solving a pragmatic problem.

• Example:
 Do consumers experience cognitive dissonance in low-involvement situations?
 Does employee tenure with a company influence productivity?

1–4
 The Scientific Method

 Scientific Method
 The way analysts go about using knowledge and evidence to reach objective
conclusions about the real world.
 The analysis and interpretation of empirical evidence (facts from observation or
experimentation) to confirm or disprove prior conceptions

1–5
 A Summary of the Scientific
Method

1–6

©2013 Cengage Learning. All Rights Reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part.
Managerial Value of
Business analytics
 There are only a few business orientations:
 Product-oriented – prioritizes decision making in a way that
emphasizes technical superiority in the product.
 Production-oriented- prioritizes efficiency and effectiveness of the
production processes in making decisions.
 Marketing-oriented- all decisions are made with a conscious
awareness of their effect on the customer.

1–7
Managerial Value of
Business analytics
 The decision-making process associated with the development
and implementation of a business strategy involves four
interrelated stages:
1. Identifying problems and opportunities
2. Diagnosing and assessing problems or opportunities
3. Selecting and implementing a course of action
4. Evaluating the course of action

1–8
 When is Business analytics
Needed?
 The determination of the need for analytics centers on:
1. Time constraints
2. The availability of data
3. The nature of the decision to be made
4. Benefits versus costs (the value of the analytics information in relation to
costs)
 Will the payoff or rate of return be worth the investment?
 Will the information improve the quality of the managerial decision enough to
warrant the expenditure?
 Is the expenditure the best use of the available funds?

1–9
Harley-Davidson Goes
Abroad
 Consumers in different countries
have different preferences.
 Even if consumers want it,
government regulations can make
it prohibitive (e.g., India).
 Harley is pursuing the U.S.
women’s market for bikes.

1-10
 Business analytics in the
21st Century
 Communication Technologies
 Always “connected”—time, place, and distance are irrelevant.
 Decreases in information acquisition, storage, access, and transmission costs.

1–11
 Business analytics in the
21st Century
 Global Business analytics
 Business analytics is increasingly global.
 Must understand the nature of particular markets.
 Cross-validation
 Verify that the empirical findings from one culture also exist and behave similarly in
another culture.

1–12
“Jacques” Daniels

 analytics findings:
 Japanese use JD as a
dinner beverage
 Australian’s drink
distilled spirits at
home
 British like to drink at
bars and restaurants
 Chinese prefer “knock-
offs” to save money
and enjoy it with green
tea

1-13
Why Analytics?
 Data analytic techniques enable businesses to
take raw data and uncover patterns to extract
valuable insights from it.
 Big data analytics helps organizations
harness their data and use it to identify new
opportunities.
 This leads to smarter business moves, more
efficient operations, higher profits and
happier customers.
 Improved Decision Making
 Cost reduction
 Better Customer Service
 Efficient Operations
Data Analytics Lifecycle

 Data discovery
 Data preparation
 Model Designing
 Model building
 Result Communication and
Publication.
 Measuring of Effectiveness.
Data Discovery Steps

1: Problem or Opportunity Identification

 The process of business analysis starts with the problem

or opportunity identification.
 Actually, the management of the company identifies the
problem or opportunity in the organization or in the
environment. The management can identify the symptoms
or the effects of the problem, but to understand the
reasons of the problems, a systematic analysis has to be
adopted.
 This required analysis should either be executed by a
business analysis firm or a business analyzer.
 2: Defining the Management Problem and
Subsequently the analysis Problem

 The management problem is concerned with the

decision maker and is action oriented in nature. For
example, the management problem offers a
psychological pricing to enhance the quantum of
sales. This management problem focuses on the
symptoms.
 The analysis problem is somewhat information
oriented and focuses mainly on the causes and not on
the symptoms. This is to determine the consumer’s
opinion on psychological pricing and to estimate their
purchase behaviour for the psychological price being
offered.
 Step 3: Formal analysis Proposal and
Introducing the Dimensions to the
Problem
 Now, the analyzer prepares a formal proposal of the
analysis and develops the approaches to the analysis
problem. The first part is to develop a theoretical model
to quantify an attitude.
 For example, to estimate the “buying intentions” for a
particular product, first, the analyzer has to prepare a
theoretical model to measure an attitude like buying
intentions.
Phase 2: Data Preparation and
Processing
 The stage encompasses the collection, processing, and cleansing of
the accumulated data.
 During this phase’s initial stage, the team gathers valuable information
and proceeds with the business ecosystem’s lifecycle. Various data
collection methods are used for this purpose, such as
1) Data Entry – Collecting recent data using manual data entry
techniques or digital systems within the organization
2) Data Acquisition – Gathering data from external sources
3) Signal Reception – Capturing data from digital devices, including
the Internet of Things and control systems.
Data cleaning
 Thisexercise is undertaken by any
analyst to deal with the problem of
missing data and illogical or
inconsistent entries.
 Data cleaning helps ensure that
information always matches the correct
fields while making it easier
for business intelligence tools to interact
with data sets to find information more
efficiently.
 Data cleaning involves two stages:
 handling missing data
 checking data for illogical or inconsistent
entries.
 Followingare some of the
guidelines to deal with missing
data.
Leaving the missing data and
performing the analysis
Substituting a mean value
Case-wise deletion
 Principally,
no missing is an ideal
situation, but practically it is rare
in a research.
Outliers
 An outlier is a data point that
differs significantly from other
observations. An outlier may be due
to variability in the measurement or
it may indicate experimental error;
the latter are sometimes excluded
from the data set.
Outlier Detection
 Sorting Your Data
 Boxplots, histograms, and
scatterplots
 Using Z-scores
 Using the Interquartile Range
Phase 3: Design a Model

 After cleaning the data, the team determines the

techniques, methods, and workflow for building a model
in the next phase.
 The team explores the data, identifies relations between
data points to select the key variables, and eventually
devises a suitable model.
Theoretical model to measure the buying intention
 Step 4: Framing Hypotheses

 Hypothesis 1: “Brand image” has a significant linear

impact on the buying intention.
 Hypothesis 2: “Brand awareness” has a significant linear
impact on the buying intention.
 Hypothesis 3: “Price” has a significant linear impact on
the buying intention.
 Hypothesis 4: “Availability” has a significant linear impact
on the buying intention.
 Hypothesis 5: “After-sales services” has a significant
linear impact on the buying intention.
  The analyzer can also test the combined
impact of these five variables on the
buying intention. The proposed multiple
regression model will be

 Hypothesis 6: All the five factors in combination have a

significant linear impact on the buying intention.
Phase 4: Model Building

 In this phase, the team develops testing, training, and

production datasets.
 Further, the team builds and executes models
meticulously as planned during the model planning phase.
 They test data and try to find out answers to the given
objectives.
 They use various statistical modeling methods such as
regression techniques, decision trees, random forest
modeling, and neural networks and perform a trial run to
determine whether it corresponds to the datasets.
Phase 5: Result Communication and
Publication
 Steps in communicating the findings of the data analysis:
 Interpreting the business research results
 Describing the implications
 Drawing the appropriate conclusions for managerial decisions
 Reporting requirements
 Conclusions fulfill the deliverables promised in the business
research proposal
 Consider the varying abilities of people to understand the research
results
 A clearly-written, understandable summary of the research
findings
Phase 6: Measuring of Effectiveness

 In this final phase, the data is moved to a live environment and

monitored to measure the analysis’s effectiveness.
 If the findings are in line with the objective, the results and reports
are finalized.
 On the other hand, if they deviate from the set intent, the team
moves backward in the lifecycle to any previous phase to change the
input and get a different outcome.
 Evaluating the Course of
Actions
 Evaluation analytics
 The formal, objective measurement and appraisal of the extent a given activity,
project, or program has achieved its objectives.
 Performance Monitoring analytics
 analytics that regularly, sometimes routinely, provides feedback for evaluation and
control of business activity.

1–33