21 Business Analytics - DKU

Course Title: Business Analytics and Intelligence
Term: Term III, PGP 2018-20
Course Instructor: U Dinesh Kumar, QMIS Group
Introduction:
Successful companies have better understanding of their customer, have better insights about the
business and as a result create innovative business strategies to compete in the market. Business
analytics is a powerful toolbox that helps organizations to get meaningful insights using data
across various activities of the organization. Business Analytics consists of several analytical
techniques that can be used to solve business problem by improving the underlying business
processes in different business and functional areas. Business analytics tools provide the ability
to acquire Business Intelligence and create capability for companies to compete in the market.
Business Analytics uses mathematical, statistical, operations research and management tools to
drive business performance. In a recent article1 based on a survey of nearly 3000 executives,
MIT Sloan Management Review reported that there is striking correlation between an
organization’s analytics sophistication and its competitive performance. The biggest obstacle to
adopting analytics is the lack of knowhow about using it to improve business performance.
Business Analytics uses statistical, operations research and management tools to drive business
performance.
This course is designed to provide in depth knowledge of business analytic techniques
and their applications in improving business processes and decision making. The focus of this
course will be on Predictive and Prescriptive Analytics. Two consulting assignments undertaken
by the instructor will be discussed to understand practical aspects in implementing analytics
solutions.
Course objectives:
The primary course objectives are:

1. Understand the role of business analytics within an organization. Understand the role of
predictive and prescriptive analytics.
1
M S Hopkins, S LaValle, F Balboni, N Kruschwitz and R Shockley, “10 Insights: A First look at The New Intelligence
Enterprise Survey on Winning with Data”, MIT Sloan Management Review, Vol. 52, No. 1, 21–31.
2. Analyse data using statistical techniques and understand relationships between the
underlying business processes of an organization.
3. Understand the analytics tools used in different functional areas such as Decision
Making, Finance, New Product Development, Marketing and Operations.
4. Manage business processes using analytical and management tools.
5. To develop ability to use analytics in various functional areas of management.
6. Understand issues in implementing analytics output.
Course Contents:
Predictive Analytics: Classification and Discrete Choice Problems
Analysis of transactional data using binary logistic and multinomial logistic regression models
and their applications in different functional areas: Customer classification, Customer churn
prediction; Discrete choice models: Logit and multinomial logit, Wald test, Hosmer Lemshow
test, area under ROC curve, Gini co-efficient, Non-linear regression.
Discriminant Analysis; Factor Analysis (FA) and Principal Component Analysis (PCA)
Classification Trees: chi-squared automatic interaction detection (CHAID), Classification and

Regression Tree (CART).
Forecasting: Trend and Seasonality Estimation, Auto-Regressive Integrated Moving Average

(ARIMA) Models
Cases: Micro-Mortgage Analytics, German Bank credit rating, In-play betting in football,
Forecasting demand for spare parts
Analytics in Practice: Credit Rating of small and medium enterprises
Predictive Analytics: Marketing, Retail and Operations Analytics
Markov Chain Models in Marketing: Modelling customer relationship as a Markov chain; Brand
Switching; Market Share Estimation; Markov model for customer retention; Customer Lifetime
Value (CLV) estimation: applications of CLV, effectiveness of promotions and strategy; Markov
decision process and their application in optimizing customer lifetime value; policy iteration and
value iteration algorithms. Hidden Markov Models with applications in retail.
Poisson and compound Poisson process; procurement and asset management decisions, survival
analysis and warranty management.
Recommender Systems: Collaborative Filtering, Cosine Similarity, Jaccard coefficient.

Case(s): Promotions effectiveness in retail, Recommender system for online grocery system.
Prescriptive Analytics:
Multi-criteria decision making: Analytic Hierarchy Process; Data Envelopment Analysis and
their applications in Operations, Marketing and Finance.
Six Sigma methodologies for problem solving: DMAIC methodology for problem solving and
process improvement; DMADV methodology for design and development of new process and
products. Idea to product; idea selection and concept screening using Pugh matrix; Quality
function deployment (QFD) and its application in new product development; life cycle cost and
total cost of ownership models for evaluation of new products.
Case(s): Quality Management in Healthcare, Dosa King
Social Media Analytics and Big Data:
Analysis of unstructured data, Natural Language Processing, Sentiment analysis, Naïve Bayes
Algorithm
Big Data Technologies: Hadoop and Mapreduce; PIG and HIVE; Real time systems Kafka
Case(s): Social media analytics in Bollywood
Pedagogy:
Using interactive lectures and case discussions the students will be introduced to advanced
techniques in Business Analytics. The pedagogy is designed to provide real applications of
analytical tools using case studies.
Evaluation:
Mid-term exam: 40%

End-term exam: 40%
Two Group Assignments/Projects*: 20% (10% each)
(Each group can have maximum of 4 students. The students are required to show how analytics
can be used to solve emerging business problems)
Course Cap:
Maximum of number of student is 75

Attendance Required:
80% attendance is compulsory for this course. Students who fail achieve 80% attendance will be
penalized one grade point.
Session-wise Plan:
Session (only a plan!!!)

Predictive Analytics – Classification and Discrete Choice Models
1 Introduction to Business Analytics and Intelligence
Reading material(s): Chapter 1 from Davenport, T H., and Harris, J G., “Competing
on Analytics: The new Science of winning”, Harvard Business School Press, 2007.
Analytics: the New Path to values, “MIT Sloan Management Review”, Research
Report, 2010.
Dinesh Kumar, Sandhya Shenoy and Arun Pandit, “Data Driven Decision Making”,
CII Report 2014.
2 Logistic regression and its application
Reading material: Chapter 4 (Logistic Regression) from D T Larose, “Data Mining
Methods and Models”, John Wiley, 2007
Case-let: German credit applications – Classification of credit applicants
3 Binary Logistic Regression Diagnostics: LR test, wald’s test, hosmer lemshow test,
classification plots. ROC curve and Gini coefficient
4 Binary Logistic Regression Diagnostics, Dimension Reduction Using Factor Analysis
and Principal Component Analysis (PCA)
Case: Breaking Barriers Micro-Mortgage Analytics
5 Decision tress – CHAID & CART
6 Multinomial Logistic Regression & Discrete choice models
Case: A game of two halves: in-play betting in football
7 Analytics in Action – Developing Credit Scoring Model
8 Net Promoters Score (NPS) Prediction – Discriminant Analysis
Case-let: Hospital Feedback System
9 Forecasting: Trend and Seasonal Estimation; ARIMA (Auto-regressive integrated
moving average)
Case : Harmon Foods Inc
Case: Forecasting Demand for food at Apollo Hospitals
10 Forecasting: Trend and Seasonal Estimation; ARIMA (Auto-regressive integrated
moving average)
Prescriptive Analytics – Marketing, Retail and Operations Analytics
11 Introduction to Markov Chains
Reading material: Ross, S M, “Introduction to Probability Models”, Academic Press,
2006.
12 Applications of Markov chain in Marketing : Brand Switching and Market Share
estimation
Case: Consumer choice between national and store brand in detergent
purchases at Reliance Retail
Reading Material: Styan G P H and Smith, H, “Markov chains applied to Marketing”,
Journal of Marketing Research, 50-56, 1964.
13 Application of Markov Chain in estimation of customer retention probability and
customer life time value
Reading material: Ching, W. K., Ng, M K., and Wong, K K and Altman, E.,
“Customer lifetime value: Stochastic Optimization Approach”, The Journal of
Operational Research Society, Vol. 55 (8), 860-868, 2004.
14 Introduction to Markov Decision Process (MDP); policy and value iteration
algorithms.
Reading material: Ross, S M, “Introduction to Probability Models”, Academic Press,
2006.
15 Applications of MDP: Evaluating effectiveness of consumer and trade promotions
Labbi, A., and Berrospi, C., “Optimizing marketing planning and budgeting using
Markov decision process: Airline case study”, IBM Journal of Research and
Development, Vol 51, No.3-4, 422-433, 2007.
16 Prescriptive Analytics in action: Markov Chain Application at an Indian eTailer
17 Recommender System – Collaborative Filtering and Cosine Similarity; Hidden
Markov Model (HMM) – Viterbi Algorithm
Prescriptive Analytics
16 Introduction to Multi-criteria Decision Making: Analytical Hierarchy Process and
Data Envelopment Analysis
Case-let: Super Selector
Reading material: Saaty, T L., “How to make decisions: the analytic hierarchy
process”, Interfaces, Vol. 24, 19-43, 1994.
Wind, Y and Saaty, T L, “Marketing applications of Analytic Hierarchy Process”,
Management Science, Vol. 26, No. 7, 1980.
17 Six Sigma as a Problem Solving Methodology
Reading Material: Dinesh Kumar, U, “Six Sigma: Status and Trends”, in Handbook
of Performability Engineering (Ed. K B Misra)” Springer, 2008.
Case: Apollo Hospitals – Differentiation Through Hospitality
18 Design for Six Sigma
Case: Dosa King – Standardized Masala Dosa for Every Indian
19 Analytics in Action – Airline Industry
Social Media Analytics
20 Big Data and Social Media Analytics; Naïve Bayes Algorithm
Reading Material: R Prabowo and M Thelwall, “Sentiment Analysis a Combined
Approach”, Journal of Informatics, Vol 3, 143-157, 2009
Case: 1920 Evil Returns – Social Media Marketing in Bollywood
Course Reference Material:
1. Almquist, E and Wyner, G, “Boost your marketing ROI with experimental design”,
Harvard Business Review, 5-11, October 2001.
2. Ching, W. K., Ng, M K., and Wong, K K and Altman, E., “Customer lifetime value:
Stochastic Optimization Approach”, The Journal of Operational Research Society, Vol.
55 (8), 860-868, 2004.
3. Davenport, T H., and Harris, J G., “Competing on Analytics: The new Science of
winning”, Harvard Business School Press, 2007.
4. Dinesh Kumar, U, “Six Sigma: Status and Trends”, in Handbook of Performability
Engineering (Ed. K B Misra)” Springer, 2008.
5. Gujarati, D N, and Sangeetha, “Basic Econometrics”, 4th Edition, The McGraw Hill,
2008.
6. Hauser, J and Clausing, D. “House of Quality”, Harvard Business Review, May-June
1988.
7. Labbi, A., and Berrospi, C., “Optimizing marketing planning and budgeting using
Markov decision process: Airline case study”, IBM Journal of Research and
Development, Vol 51, No.3-4, 422-433, 2007.
8. Lin, S X., “Introductory Stochastic Analysis for Finance and Insurance”, Wiley-
Interscience, 2006.
9. Marker, J O, “Studying policy retention rate using Markov chains”,
10. Ross, S M, “An introduction to mathematical finance: Options and other topics”,
Cambridge University Press, 1999.
11. Ross, S M, “Introduction to Probability Models”, Academic Press, 2006.
12. Saaty, T L., “How to make decisions: the analytic hierarchy process”, Interfaces, Vol.
24, 19-43, 1994.
13. Styan G P H and Smith, H, “Markov chains applied to Marketing”, Journal of Marketing
Research, 50-56, 1964.
14. Wind, Y and Saaty, T L, “Marketing applications of Analytic Hierarchy Process”,
Management Science, Vol. 26, No. 7, 1980.

21 Business Analytics - DKU

Uploaded by

Copyright:

Available Formats

21 Business Analytics - DKU

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

21 Business Analytics - DKU

Uploaded by

Copyright:

Available Formats

Course Title: Business Analytics and Intelligence

Term: Term III, PGP 2018-20

Course Instructor: U Dinesh Kumar, QMIS Group

The primary course objectives are:

Predictive Analytics: Classification and Discrete Choice Problems

Classification Trees: chi-squared automatic interaction detection (CHAID), Classification and

Forecasting: Trend and Seasonality Estimation, Auto-Regressive Integrated Moving Average

Analytics in Practice: Credit Rating of small and medium enterprises

Predictive Analytics: Marketing, Retail and Operations Analytics

Recommender Systems: Collaborative Filtering, Cosine Similarity, Jaccard coefficient.

Case(s): Quality Management in Healthcare, Dosa King

Social Media Analytics and Big Data:

Case(s): Social media analytics in Bollywood

Mid-term exam: 40%

Maximum of number of student is 75

Session (only a plan!!!)

Course Reference Material:

You might also like