Analytics

Post-Graduate Diploma in Management-Full Time
(PGDM- FT)
Area: Marketing
Course Title Marketing Analytics
Course Description:
In todays markets, the big story is BIG DATA. Technological advances (e.g., web,
communications, and devices) are expanding customer-to-firm and consumer-to-consumer contact
points, and enabling capture of rich and diverse transaction data at nearly every contact. Marketing
data stocks are exploding at a rate that defies Moores law (double every two years). Yet, on their
own, big data do not reveal big insights. Insights from big data require smart analytics.
Unfortunately, data stocks are increasing at a rate that is not matched by our capacity for smart
analysis and deep insights. The marketing analytics course is integrates theory (e.g., analytical
concepts) and practice (e.g., real life data based problems) with focus on skills for smart analytics.
It is meant for students who want to build analytics competency for managerial decision making,
and study applications of analytics for customer and marketing related problems in management.
Some of the typical application areas include consumer credit, new products, market segmentation,
and customer value.
Learning Objectives:
(a) Developing skills for analysing marketing data for making intelligent decisions about
marketing investments that create value and build competitive advantage.
(b) Build capabilities for marketing analytics using current concepts and tools.
Pedagogy:
The course will blend theoretical concepts with practical problems to provide a broad analytics base
for skill building. The course will also focus on informed use of marketing tools and on writing
syntax for those tools.
Every course day will involve Classroom Seminar and Lab/Tutorial sessions, delivered twice a
week on Tuesday and Fridays (on specified dates) from 10.30 AM to 1.15 PM. The class will begin
promptly at 10.30am.
Course Prerequisites and Requirements:

The course is intensely quantitative and students will be expected to (a) thoroughly understand their
Business Statistics curriculum and (b) be proficient in MS Excel. Many of these concepts will be
used right from the beginning of the course and students ill-prepared will fall behind.
SPSS will be used as the primary statistical tool, with emphasis on SPSS syntax. Class expectations
include (a) being prepared for each class by reading designated material and reviewing appropriate
analytic tools in advance, (b) submitting evidence-based reports that demonstrate application of
specific analytical tools to given marketing problems, and (c) making class presentations that build
skills for analytics based reasoning with emphasis on data visualization and evidence based insights
for marketing decisions.
Students will be provided readings for each class, with the expectation that they will review them in
advance. The purpose is to have better and more engaging class room discussions. It will be clear
during class if a student has not come prepared and participation points will be accordingly
deducted. During the lab/tutorial session, students will start work on their homework assignment for
the next class.
Evaluation:
There will be two exams and six assignments for the course, with the following weights and
schedule::
Components of Evaluation
Class Participation
Mid-Term
Assignments
Final
Total
Date
Weightage of Marks
(in percentage)
To be monitored for all

5
sessions
29th January
15
6 Assignments
50
3rd March
30
100
Note: No evaluation will be repeated. Missing an assignment deadline or a test will lead to the
student being awarded zero points for that evaluation.
Grading Notes:
Class Participation and Attendance. The following aspects will be considered in evaluating
students grade:
a. Preparedness and Attendance. Regular attendance and diligent preparation for the class is
indicative of student commitment to participate in a learning environment.
b. Active Engagement. Active participation in the class with thoughtful questions, sharing
alternative perspectives, and responding critically to class discussion
*Bonus Points for Presentation. You will earn bonus points if you are selected for presentation to
the class. To be invited for presentation, the student must perform significantly better than the
others in terms of (a) quality, (b) depth or (c) innovativeness demonstrated in the analytics
assignment. Bonus points could be upto 10% of the assignment grade.
Submission Requirements and Guidelines:

Typically, submission-feedback-rework will work as follows:
1. Assignments should be submitted in a power point format, address all requirements of the
assigned problem, and generally up to 20-25 slides of material. Text may be bulleted but
must be complete with details to be understood precisely. Be concise. All writing should be
original (meaning it should not overlap with anything on the internet or in prior published
form, or with other submitted assignments). Copy-and-paste is strongly discouraged.
Making smart and creative tables/figures to help visualize results is strongly encouraged.
Additional notes may be included to explain your work. The presentation will have an
Appendix section which will provide the supporting evidence, analysis and the syntax.
2. Assignments need to be prepared to be at par, in quality and content, with presentations to
global clients. This is important. Poorly prepared, organized, or proofed presentations will
be severely penalized as inadequate work.
3. An initial report for each assignment (given on Tuesday) must be submitted by
Wednesday midnight on the week of the assignment. Failure to submit a draft will result
in a 15% penalty on the corresponding assignment grade.
4. Feedback on your draft submission will be provided in the Friday class to address common
questions and errors. Students are encouraged to bring questions, concerns and problems
they encountered in developing their initial report to the class for discussion.
5. Final assignments will be due on Sunday 9.00 a.m.. No extensions permitted (see Late
Submissions below).
6. Feedback on the final draft of your assignment will be provided usually before Tuesday
class.
7. Based on the quality and creativity of your submission, the instructor may ask you to make a
presentation based on your assignment in the Tuesday class with the following guidelines:
a. 10 minute presentation
b. Focus on points highlighted in the feedback. Revise and sharpen your presentation
accordingly.
c. Polished and professional presentation. Assume you are presenting to a client.
Late Submissions: Late submission will result in a 1.5-point penalty (out of 10). That penalty is
one and a half point for each day (or part thereof) that the submission is late. If a submission must
be late due to circumstances beyond your control, contact the instructor. At his discretion and
based on his assessment of the actual degree of uncontrollability of the situation, he may permit a
special arrangement. The most typical special arrangement is for students who must miss class due
to extreme circumstances. They are often permitted to submit the assignment early. It is extremely
rare for the instructor to permit an extension of the due date.
Redos: Students are encouraged to go back to fix problems identified on their graded assignments
as this ensures that students complete the learning loop. In some instances, a redo may earn you a
portion of the original points, but often it may not. Redos that show students effort in addressing
the problem on their own, the nature of the problem and timely submission are all factors that go
into this decision. Additional points for redos are at the instructors discretion. The extra credit
will be upto 1 point maximum (10% of grade) and usually lower. Redos are intended to promote
learning and not as opportunities for making up the grade.
Changes: The instructor reserves the right to make changes to any aspect of syllabus that, to his
judgment, are needed to achieve the learning objectives of the course.
Academic Integrity:
All students in this course are expected to adhere to IMTs standards of academic integrity.
Cheating, plagiarism, and other forms of academic dishonesty will not be tolerated. This includes,
but is not limited to, consulting with another person during an exam, turning in written work that
was prepared by someone other than you, and making minor modifications to the work of someone
else and turning it in as your own. Unless properly referenced or quoted, submitted work is
assumed to be original contribution of the student.
Ignorance will not be permitted as an excuse. If you are not sure whether something you plan to
submit would be considered either cheating or plagiarism, it is your responsibility to ask for
clarification.
All submitted material will be run through anti-plagiarism software by the APOs office. A high
level of plagiarism detected by the software will lead to a failing grade in the course.
Course Dataset for Homework Assignments
Datasets and structured problems would be provided to the students for most of the course
assignments. The problems/case studies and dataset are provided for the purposes of coursework
and are copyrighted materials. You are asked to delete the materials and all associated data files
upon completion of the course.
Recommended Text Book

Hair, J. F., Jr., Black, W. C., Babin, B. J., & Anderson, R. E. 2010. Multivariate data analysis (7th
ed.). Pearson Education. (Referred as HBBA)
Other Readings:
Review material covered in a first-level graduate statistics course. Online materials are
available, usually free, for this purpose (e.g., http://davidmlane.com/hyperstat/;
http://onlinestatbook.com/2/index.html).
Familiarize yourself with the SPSS statistical software. SPSS has a useful tutorial (under
the Help tab in the main data screen). Many online resources are available
(http://www.hmdc.harvard.edu/projects/SPSS_Tutorial/spsstut.shtml,
http://www.ats.ucla.edu/stat/spss/modules/default.htm), and you can download a free
guidebook by visiting http://www.spsstools.net/ (use the link under purposes).
Course Outline: Session/Module/Reading Material

Session 1 (January 12): Data Mining & Dimension Analytics
Crosstabs, Chi-square Test, Association, Risk & Factor Analysis.

Sessions 1 (150 minutes)
30 minutes
Introduction to the
course
30 minutes
Conceptual
background
to
crosstabs and Chisquare test.
30 minutes
Tutorial:
Performing
Crosstabs and Chisquare test: Tutorial
30 minutes
Conceptual
background to factor
Analysis
30 minutes
Tutorial: Performing
Factor Analysis
Readings:
Chapters 2 and 3 of Text Book
Session 2 (January 15): Data Mining & Dimension Analytics
Crosstabs, Chi-square Test, Association, Risk & Factor Analysis.

30 minutes
Summary feedback on
assignments
submitted
after session I
45 minutes
Student queries based on the
feedback
75 minutes
Discussion on additional concepts and issues about
crosstabs, Chi-square test and factor Analysis
GUEST: Alumni Perspectives
Readings:
Session 3 (January 19): Predictive Analytics
Linear and Polynomial Regression, Interaction Effects, Multi-group Regression

30 minutes
Presentation of best student assignment
on
Crosstabs-Chi-square/Factor
Analysis
45 minutes
Conceptual
background
regression analysis
to
Tutorial:
analysis
75 minutes
Performing
regression
Readings:
Chapter 4 of the text-book
Session 4 (January 22): Predictive Analytics
Linear and Polynomial Regression, Interaction Effects, Multi-group Regression

30 minutes
Summary feedback on draft submission
on predictive analytics
45 minutes
Addressing queries raised by
students on feedback
Readings:
Session 5 (January 29): Mid Term Exam
75 minutes
Discussion on advanced topics of
regression.
Session 6 (February 2): Interactive Analytics
Big data, Web-site and Web-advertising Analytics, Attribution Modeling.

30 minutes
Presentation of best student
assignment
on
predictive
analytics
45 minutes
Introduction to big data, web
analytics
and
attribution
modeling
75 minutes
Tutorial: Practical applications
Interactive analytics
of
Session 7 (February 5): Interactive Analytics
Big data, Web-site and Web-advertising Analytics, Attribution Modeling.

30 minutes
Summary feedback on
submission
draft
45 minutes
More on big data, web
analytics
and
attribution
modeling
75 minutes
GUEST: Anshuman Gupta, Head,
Data Science Program, Cognizant
Session 8 (February 9): Conjoint Analytics
Part-worth Utilities, Multi-attribute Modeling

60 minutes
Introduction to conjoint analysis
90 minutes
Tutorial: Performing conjoint analysis
Readings:
Session 9 (February 12): Conjoint Analytics
Part-worth Utilities, Multi-attribute Modeling

30 minutes
Summary feedback on draft
submission of conjoint analysis
assignment
45 minutes
Addressing student queries based
on summary feedback
75 minutes
Discussion on advanced topics.
GUEST: Ujjyaini Mitra, Head
Analytics
and
Marketing
Intelligence, Bharti Airtel
Readings:
Session 10 (February 16): Positioning Analytics
Multi-Dimensional Scaling
30 minutes
assignment on conjoint analysis
45 minutes
Conceptual background to multidimensional scaling
Readings:
Chapters 10 of Text Book.
Session 11 (February 19): Positioning Analytics
Multi-Dimensional Scaling
75 minutes
Tutorial:
Performing
dimensional scaling
multi-

30 minutes
Summary feedback on draft submission
of assignment of multidimensional
scaling
45 minutes
Addressing student queries based on
summary feedback
75 minutes
GUEST: TBD
Readings:
Chapters 10 of Text Book.
Session 12 (February 23): Mixture Analytics: Cluster Analytics
Hierarchical Cluster Analysis, K-Means Cluster Analysis, Discriminant

Analysis
30 minutes
assignment on multi-dimensional
scaling
45 minutes
Introduction to segmentation using
cluster analysis
75 minutes
Tutorial: Performing cluster analysis
Readings:
Session 13 (February 26): Mixture Analytics: Cluster Analytics
Hierarchical Cluster Analysis, K-Means Cluster Analysis, Discriminant

Analysis
30 minutes
Summary
feedback
on
draft
submission of assignment on cluster
analysis
Readings:
45 minutes
Addressing student queries based on
summary feedback
75 minutes
GUEST: TBD
Course Assignments:
Assignment #1: Data Mining Analytics
This assignment involves two mini-assignments. Each indicates a different approach to dataminingone deductive, driven by a priori thinking, and the other inductive, driven by exploring
without any a-priori constraints.
Mini-Assignment 1A: Inductive Data Mining
An insurance company received more than usual number of fraudulent claims in 2008, and the
company is interested in examining possible causes. Claim history, background characteristics
(e.g., income) and past behavior of insurers are potential explanations but the company has no apriori data or industry evidence to provide insight. Ultimately, the company seeks insights to help
reduce the number of frauds and see if they should make any changes in their insurance policies.
Data: Insurance_Claims.SAV
In developing your client presentation (as a consultant), consider the following issues:
1. Do the fraudulent and non-fraud claims differ by types of claim, town size, or amount of
coverage?
2. Explore if there is any variable(s) that might influence the relationship between fraudulent/nonfraud claims and amount of coverage.
3. Challenge: Identify other patterns in the data that can provide insights into fraudulent claims.
Integrate results from your explorations to provide a clear recommendation to the insurance
company. You may need to conduct additional 3-way or 4-way cross-tabulations.
*** Hint: You will need to recode Amount of coverage into 3 categories:
a. Low coverage: Lower than 107
b. Moderate coverage: From 107 to 358
c. High coverage: Higher than 358
Mini-Assignment 1B: Deductive Data Mining
Bencare Insurance Company, a long standing firm for consumer insurance products worldwide, is
recently facing stiff global competition that is chipping away at its loyal customer base. Insurance
industry is tough business where price competitiveness of insurance products is matched by
customer needs for trusting relationships with firms of strong reputation (see
http://www.ey.com/GL/en/Industries/Financial-Services/Insurance/ey-2014-global-customerinsurance-survey).
To commission a survey of its customers, Bencare conducts a series of internal discussions among
its customer facing teams to key variables that should be include in the survey. These discussions
converge on 5 key variables which are later refined and reworded for inclusion in the customer
survey (specific survey question in parentheses:
1. Customers Trust in the Company Representative (Rep17 to Rep 20),
2. Customers Trust in the Company (Prac17 to Prac20),
3. Customer Satisfaction with Company products (Inter1 to Inter3),
4. Customers Value (benefits relative to costs) Assessment (Val1 to Val6)
5. Customer Loyalty (Loy1 to Loy8).
Subsequent to data collection, Bencare is curious if their conceptions of customer variables align
with how customers view the company, its products and their relationship with it. Use factor
analysis to identify, refine (as needed) and validate these key variables. Develop your report for
client presentation with a strong and complete technical appendix that supports your conclusions.
Data: Bencaref_raw.sav
Survey: Bencare_survey_excerpts_from_full_version.pdf
In developing your client presentation (as a consultant), consider the following issues:
4. What decision choices in Factor Analysis procedure are appropriate for this problem and data?
5. Obtain, tabulate and interpret the evidence for the validity of Bencares conceptions of key
customer variables.
6. Challenge: Are these variables useful managerially? Do they capture variations in different
customer segments (based on demographics)? Think about this last question again.
Assignment #2: Predictive Analytics

The basic goal of Bencare management in commissioning a global study is to understand factors
that predict customer loyalty and use these factors as levers of strategic investments. Consumers
are randomly drawn from company records in three marketsGermany, the Netherlands and
United Statesand surveyed with questions that measure Key Loyalty Predictors (KLPs) that
Bencare Senior Management believes are important including customer satisfaction (with current
products), trust (in the company and its insurance agents), value (benefits relative to costs from
customers point of view) and reputation (customers perception of firm reputation).
Several consumer demographic variables including age, gender and education are also obtained.
The overall goal of this assignment is to prepare a consultants report to Bencare with
recommendation for a Driving Loyalty Lift (DLL) strategy for enhancing the companys
competitive position in the customers mind. Support your recommendation with rigorous and
competent analytics that is summarized, tabulated and plotted for client review. Include a complete
technical appendix with syntax used in case Bencare wants to review more deeply.
Consider the following issues among others as you develop your recommendation.
1. Define and clarify the managerial problem which includes (a) relative impact of KLPs, (b)
nonlinear relationships, and (c) variation in relative impact of KLPs by country or other
customer variables.
Hint: KLPs can be defined on the basis of factor analysis conducted in Assignment #1. Use
average composites that correspond to stable factors for predictive analytics.
2. Test for regression assumptions and follow remedies as needed. Be sure to also screen data
for missing values and other concerns.
Hint: Do not be in a rush to drop variables or observations. The goal is to use as much of
the data possible to include full customer/variable representation.
3. Estimate and interpret the best predictive model for the aggregate data (across the three
countries). Interpret both the overall fit and individual coefficients. Plot results for clarity.
Hint: Include the effect of demographics. Test and account for influentials/outliers and
multicollinearity to ensure that your best model is robust.
4. Examine the variability due to country variable on the best aggregate model. Modify
predictive model specification as needed. Interpret, summarize, tabulate and plot your
results.
Hint: Are the aggregate results robust? What country-specific strategies can be
recommended? Do the differences (if any) make sense?
5. Summarize your results and overall recommendation for Bencares Driving Loyalty Up
initiative that addresses the problem you stated above.
Challenge: Test for distinct customer segments (within country) that respond differently to loyalty
predictors. Can you quantify the financial implications of the recommended DLL strategy using
industry/external data? Think again about this question. What are the implications of these
implications for a change strategy within Bencare?
Assignment #3: Conjoint Analysis
Two contrasting marketing themes define the almost $2,560 trillion global apparel industry
encompassing clothing, textiles, foot-wear and luxury goods. Conventionalists hold that fashion
must be expensive to be thought fashionable. Contemporarists assert that fashion needs to be
trendy and affordable (to customers pocketbook) without appearing cheap or everlasting (see
http://www.npr.org/2013/03/11/174013774/in-trendy-world-of-fast-fashion-styles-arent-made-tolast).
Little solid evidence exists for either view as credible explanation of customer decision rules.
Potentially decision rules likely change by segments and categories.
To understand how customers make trade-offs between fashion and price, a full profile conjoint
study is designed with the following attributes:
1. Fashion: two levels (Modern versus Traditional)
2. Quality: two levels (Low versus High)
3. Price: two levels (Lower versus Higher)
400 randomly selected customers from target segment are invited to complete the conjoint task by
rating each profile on a 1-5 likelihood to buy scale (1 = very unlikely, 5 = very likely).
Develop a report based on high quality analytics for the fashion company client to help them
develop marketing programs that take advantage of your insights to gain competitive advantage.
Data: Rating_Fashion.Sav
In preparing your report consider the following:
1. Outline how you will tackle the marketing problem to yield meaningful insights that go
beyond obvious statements about customer trade-offs. What makes your approach
distinctive (from other consultants)?
2. Execute your approach. Show your analytics, summarize, tabulate and plot your findings,
and interpret your interesting insights. What evidence would you provide to demonstrate
that your results are robust and valid?
3. Do your results support common rules of consumer trade-offs? If so, do they support
conventional or contemporary view? If not, how do consumer trade-off rules vary?
4. Challenge: Are there clear customer segments that differ in their trade-off rules? To what
extent are age and gender meaningful in defining these segments? Think again about these
questions.
Assignment #4: Positioning Analytics
(Chocolates are numbered from left to right as chocolate_1 to chocolate_16)

Chocolate is a US$50 billion industry worldwide, and aficionados consider taste, texture, cocoa
content, and shape as its essential qualities. For most customers, shape is the most accessible
attribute. A study focuses on 19 customers evaluations of 16 types of chocolates (see above). The
chocolates shapes are selected to represent many common and few experimental shapes. To obtain
customer evaluations, the 16 chocolates are displayed on a large computer screen with the
flexibility of moving them freely using a mouse. Each customer is asked to move the chocolates
around so as to place them in terms of their similarityclosely placed chocolates are similar to one
another, and distantly placed chocolates are dissimilar. The task can be conceptualized as having
customers project their own psychological spaces onto a two-dimensional plane (i.e., the computer
screen). A proximity matrix was derived for each customer by computing the Euclidean distances
between every pair of chocolate placed on the computer screen after the conclusion of task
(measured in pixels).
Using MDS and/or related approaches analyse proximity matrices to address the following:
a) How many dimensions are adequate to faithfully represent customers evaluations of
chocolate similarities at the aggregate level? Do different approaches provide consistent
evidence of dimensionality of similarities data? Interpret and discuss the evidence and
support your decision.
b) Are there individual outliers (weird cases) that significantly influence aggregate
perceptual map(s) of chocolate similarity data based on (a) above? Discuss your procedures,
evidence obtained and its implications for understanding chocolate similarities.
c) After accounting for individual outliers, develop a final solution for customers similarity
judgments. How and what would you label the dimensions of your final solution?
d) Interpret your final solution for managerial insights. What can you recommend to a
chocolate marketer for effectively appealing to customer preferences?
Challenge: Are there viable customer segments for chocolate shape preferences? Show evidence in
favour or against, and interpret its implications for marketing strategy.
Assignment #5: Mixture Analytics

Typically, marketers use demographic variables such as age, gender and education to identify
distinctive
segments
that
they
can
attract,
retain
and
win
loyalty
(http://www.experian.co.uk/assets/business-strategies/white-papers/wp-avoid-the-segmentationtrap.pdf). More often than not, demographic segmentation lacks insights and offers less useful
managerial guidelines.
In its continued effort to revamp its marketing strategy, Bencare wants to move away from
simplistic segmentation strategies to those that use variables that consumers actually use in making
choice decisions for insurance products. To explore if KCPs (i.e., customer satisfaction, price,
value and reputation) can be meaningfully used to define customer segments, Bencare has retained
you as a consultant.
The KCPs of interest are defined as follows:
Satisfaction:
SAT1 to SAT3
Pricing:
PRICE1 to PRICE3
Reputation:
REPU1 to REPU4
Short-term Value:
VAL1 to VAL3
Long-term Value:
VAL4 to VAL6
Develop an analytics-based report for Bencare to help them develop marketing programs that take
advantage of your segmentation insights to gain competitive advantage.
Data: BENCAREF_2013R1.sav
In preparing your report consider the following:
1. Outline how you will tackle the marketing problem to yield meaningful insights that go
beyond obvious statements about KCP based customer segments. What makes your
approach distinctive (from other consultants)?
2. Execute your approach. Show your analytics, summarize, tabulate and plot your findings,
and interpret your interesting insights. What evidence would your provide to demonstrate
that your results are robust and valid?
3. Provide clear recommendations to Bencare about the nature and usefulness of each segment
that you identified in your analytics. How do these segments differ? Are some segments
more loyal to Bencare than others? Which segment should Bencare target & why?
4. Challenge: Customers in Bencare data also differ in terms of cultural factors because the
data are collected in three different countries. Account for cultural differences in your
segmentation analytics. In what ways does consideration of cultural factors alter the nature
and usefulness of individual segments for Bencare. What do these results add to those
obtained from predictive analytics? What marketing strategy would you recommend by
considering both results?
Post Graduate Diploma in Management

(PGDM)
Area- Analytics
Course Title:
Business Analytics & Predictive Modelling
Institute of Management Technology, Ghaziabad
Course Description
Today the business organisations are is dealing with gigabytes of information due to the development of mathematical
and computer science technology. The human brain is not able to handle and examine more than a few dozens of
records manually at a time to solve a problem even from well-organized data. But the algorithms of predictive
modelling can analyse millions of data points with hundreds of variables to make a diagnosis or a prediction of the
stochastic variables. The objective of predictive modelling course is to provide an overview of statistical and
econometrics modelling techniques with the help of the most advance softwares such as SAS or R. Predictive
modelling is useful in the area of Finance, marketing, economics, healthcare etc.
The students of predictive modelling will gain practical experience of developing predictive models based on routinely
collected data using a standard statistical computer package such as SAS or R.
Course outcomes: After this course participants will be able to:
1.
2.
3.
4.
5.
6.
Identify the statistical models to be applied in the given situation. Understand the predictive modelling process
Prepare data for the purpose of predictive modelling
Appreciate the use and importance of multiple data sources, e.g. CMIE, Bloomberg etc.
Compare and contrast the underlying predictive modelling algorithms, e.g. Logistic Regression and
Classification Trees
Select appropriate predictive modelling approaches to identify those cases that are at high risk of an event
Apply these approaches using a suitable package such as SAS or R
Learning Objectives
(a)
(b)
(c)
(d)
To develop the analytical skills using statistical analysis using statistical softwares.
To develop smart presentation skills for persuasive communication across stakeholder relationships.
To critically analyse situations for forward thinking through innovation.
To demonstrate techno-savvy capabilities to manage integrated environments.
Teaching Pedagogy
The pedagogy will be a mix of lectures, critique of readings/articles, case discussion, assignments and data analysis
using SAS software. The course uses data and cases as the means to drive the contextual suitability of predictive
modeling. Besides the readings in the course pack, additional reading material will be distributed in the class from time
to time.
Course Requirements
i.
Prerequisite to this course is the learning derived from Business Statistics and Business Research
Methods courses.
ii.
Since much of the course material requires class discussion, it is important that you are prepared for the class
and present and defend your ideas. Preparation for class includes having read the assigned material.
iii.
The class will be divided into a number of groups and each group will have 4-5 students. For all projects and
assignments, each group will submit analysis report and power point presentation one day before scheduled
class.
iv.
Evaluation for this assignment will be done based on individual as well as group performance.
v.
Class participation will be based on the value you add to the class through your creating learning environment
in class by raising intelligent questions, relevant statements on questions raised by others, and maintaining
class decorum.
Evaluation
Students will be evaluated on the basis of case analysis, project, assignments, class participation, mid-term and endterm exam. The weightages given to each of these units is listed below:
Course Evaluation
Class Participation
Assignments (4)
Project report (1)
Quiz (best 1 out of 2)
End Term Exam
10
10
30
10
40
Project Evaluation
Specific
Method
Assessment
Group
Assessment
Methods
Group Project Proposal
Presentation
Group
Project
Presentation
Group Project Report
Submission
Group Case analysis
submission
Group Assignments
Individual Assessment
Methods
Mid Term Exam
End-term Exam
Group Project presentation

20
Group Project
Report submission
10
Weightage
Intended subject learning outcome to be assessed
30%
30%
40%
15%
15%
30%
40%
Guidelines for Group Project

The group project will be one of the most important learning tools of the course. Each group will comprise of 5
students.
The project work should preferably be a practical issue, which requires a high degree of analysis and tangible
recommendations. Your group is required to identify a company as well as project. Some projects are identified at the
end of this note. The deliverables of the project include:
1.
2.
3.
4.
Project proposal
Data Collection
Final Report along with data used (if applicable)
Presentation
Project Proposal Format

Your proposal should include following:
Introduction/Background of the project

Rational for taking the project
Objective of the study
Scope of the study
Methodology (provide flow diagram)
Expected outcome
Project schedule/ timeline of progress
Guidelines for Presentation
The presentation should cover both the analysis of primary and secondary data, as applicable.
Each presentation will be of 10 minutes with 8 minutes given to the group to highlight the key findings and 2
minutes for open discussion in the class.
Additional assignments would be given during the course.

Session 1 & 2: What is Business Analytics and why is it so interesting. Why reporting is not Analytics. How
to bring data together from across the business? What skills you need for the new age of analytics. Does the
recent recession put a greater business emphasis on business analytics? Application of Analytics in various
verticals, difference between tools and techniques, techniques using various statistical tools. What is
modeling, Scoring theory and application, Results of modeling, Databases and Types of Data & Variables in
Financial Services Domain, Concept of Data Dictionary (participants need to create one), Introduction to
Data types, Type of variables etc, Introduction to types of Data/Variables in the Financial Domain, Data
Modeling Techniques Overview Introduction to Linear, OLS and Logistic Regression, Collections Analytics,
Introduction to Time Series modeling, Introduction to Factor, Discriminant and Cluster Analysis.
Sessions 1 and 2 (150 minutes)

15 minutes
Introduction
predictive
analytics
20 minutes
20 minutes
20 minutes
Introduction to R software Econometrics vs data Practice

to and its use in predictive mining, Case study with
modeling, Scoring theory, R software
data types
Session 3 & 4: Linear Regression, Regression means going to the past. So what is it doing in the business?
Examples of different verticals requiring prediction, How does one determine factors affecting a business,
Difference between BI and Predictive modeling, Relating the data available with the business problem, How
to effectively determine a business problem and relate it to Analytics? Overview of Observation Window and
Performance Window

15 minutes
Linear
regression
20 minutes
20 minutes
Basic regression analysis, Assumptions

Bivariate and multivariate Regressions,
regression models,
property
of
20 minutes
OLS Case study

BLUE
Session 5 & 6: Regression Diagnostics: The Regression problem, Finding the best-fit straight line - OLS
Method, Sum of Square Errors, Base Line model, Co-efficient of Determination, Normality of residual,
Violations of the CLRM assumptions : Multicollinearity, Tolerance, VIF (to be discussed in Detail),
Homoscedasticity (White Test), Autocorrelation of residual (Durbin Watson Statistic), Correlation between
Independent variable and residual etc., Implications of Violation of BLUE properties, Overview of different
methods to alleviate Hateroscedasticity, Box Cox Transformation Residual Analysis, Its importance and
Implications: Cooks-D statistic, standardized residual values etc.
15 minutes
Problems
regression
analysis

20 minutes
20 minutes
20 minutes
Regression diagnostics, VIF, tolerance, Durbin Case study
Watson test, BP test using
in Multicollinearity,
R
autocorrelation,
heteroscedasticity
and
outlier testing
Session 7 & 8: Capping and Missing Imputations: Introduction to imputation techniques, A simple case
study wherein the values of the variables are missing and needs imputation, Incorporating Categorical Data:
Dummy Variable Coding, Dummy Variable Trap, Interpretation of Dummy Variable Coefficients, Structural
Breaks and testing of Seasonal behaviour anomaly, Model Building Variable selection, Interpretation of the
model, Prediction and scoring new data Model Performance (Goodness of Fit) & Tracking R2, Adjusted R2,
Performance Tracking through Split Samples.

20 minutes
20 minutes
20 minutes
Dummy Variable Coding, Model Building Variable Case study
Capping
and Dummy Variable Trap, selection, Interpretation of
Interpretation of Dummy the model, Prediction and
Missing
Variable Coefficients
scoring new data Model
Imputations:
Performance (Goodness
Introduction to
of Fit)
imputation
techniques
15 minutes
Session 9 & 10: Principal components analysis and remedies of regression problems: Unit root test, Principal
component analysis, KMO and Bartlett test, Varimax rotations, Eigen values, Factor loadings and factor
scores.
15 minutes
Remedies
of
regression problems,
unit root problem,
combining variables,
identifying
and
removing outliers
Sessions 9 and 10
20 minutes
Principal components
analysis and remedies
of
regression
problems: Unit root
test,
Principal
component analysis,
(150 minutes)
20 minutes
20 minutes
KMO and Bartlett test,

Varimax
rotations, Case study
Eigen values, Factor
loadings and factor
scores.
Session 11 & 12: Logistic Regression-1: The Classification problem, The joint probability prediction,
Sigmoid function, The logistic transformation, Likelihood function and Maximum Likelihood estimation,
Difference between OLS & MLE, Linear Probability Model, Variable selection, Interpretation of the model
through maximum likelihood estimates, Interpretation of the model through odds ratio estimates. Wald test,
Exponential Beta, Concordants and Sommer's D, Hosmer Lemeshow Test, Error/Confusion matrix, Receiver
operating characteristics
15 minutes
The
Classification
problem, The joint
probability
prediction, Sigmoid
function, The logistic
transformation,
Likelihood function

20 minutes
20 minutes
20 minutes
Variable
selection,
Interpretation of the Wald test, Exponential
model
through Beta, Concordants and
maximum likelihood Sommer's D, Hosmer
Lemeshow
Test,
estimates,
Interpretation of the Error/Confusion matrix, Case study
operating
model through odds Receiver
characteristics
ratio estimates.
and
Maximum
Likelihood
estimation
.
Session 13 & 14: Univariate forecasting using ARIMA forecasting, AR and MA components, identification
stages, Forecasting, ARIMAX, integrated series, forecasting accuracy, model testing. Making static and
dynamic predictions.
20 minutes
20 minutes
20 minutes
Identification stages,
Developed
forecasted
Forecasting,
Univariate
forecasting
using ARIMAX, integrated model testing. Making Case study
forecasting static and dynamic
ARIMA forecasting, series,
predictions.
AR
and
MA accuracy,
components,
15 minutes
Session 15 and 16: Project presentations
Post-Graduate Diploma in Management

(PGDM-FT)
Area: IT and Analytics

Course Title Business Intelligence and Big Data
Course Description:
Few Quick questions:
How many people knew Make interesting and meaning out of big Data before?
Do companies measure data? How many times? In TB? In Zeta/Zotta /Bronto Bytes? What are the
methods
What are knowledge knuggetts for firms? How do you measure and build intelligence in software?
Is BIG Data the next big thing? How it is different? What is Machine learning, MapReduce and
Hadoop?
What type of business rules Business analysts write? Are they relevant? What is a data scientist?
RBI, Shoppers Stop, LIC, ICICI, AIIMS, Airtel adopted BI why and how?
Where are Indian Analytics companies doing? Does the 1990 IT bubble is forming again in India in
analytics?
What is OLAP market? What opportunities exist? Have you heard of real time data warehouse, it is
required in big data? Why should we know data warehouse, when we read Big data?
Do you we do De-Normalization for using analytics to discover new information?
What is prescriptive, predictive, diagnostic and descriptive analytics?
What is the architecture for big data technology? Examples.
What is Python, PMML, ETL tools, ODS tools.
CRISP-DM Methodology: Cross-Industry Standard Process (CRISP) for Data Mining:

why do we should study this.CART, CHAID, Market Basket Analysis: Build models.
First and foremost and very important, the term analytics started from data bases and data mining. A decade ago,
data base specialists used to call BIG DATA AS VERY LARGE DATA BASES. You predict almost everything
if you have historical data, say starting from customer/employee churn analysis to life time value analysis, RFM,
retention techniques to CART or CHAID or conjoint analysis etc. So this course is a dissemination and
culmination of Data warehousing methods, data mining, BI, Business analytics and big data.
MOST IMPORTANTLY HANDS ON TRAINING ON STATISTICA WOULD BE GIVEN 6-8 HOURS
on model building.
Please note,
It is not theoretical
It is not about programming, dont bunk classes.
The business scenarios and problems look strange but interesting
You need to spend long topics/research discussions after class hours with me
I have to get my hands very dirty to make you business data analysts (!!??!!!)
The course is tough: assignment + exams + Research project;
Analytics- Promising in business, research and development
Big data Big money as said by McKinsey: many well paid positions (median $100k)
Business Intelligence (BI) and Data mining looks cool. For me, to you too !!!
To exactly understand what Indian Analytical industries are currently working on BIG data, or
Hadoop big data. For example, companies like MuSigma, Nabler, Absolute Data, and
Manthan Systems are all the hot Indian Analytics cases that we study
This is a unique course which prepares you for the world of work in analytics in companies. Students
having opted for this course in the previous years have found placement offers from leading companies,
the designations include Data analyst, Business development Manager, and Business Analyst and
research analyst. The course gives you a blend of industry knowledge, concepts and experiential
learning through collaborative teaching by industry experts.
To develop an understanding of the nature of BI, BD, BA and its role in business decisionmaking.
To prepare, comprehend and analyze business cases demonstrating both technical and
analytical capabilities.
To develop a working knowledge of and to demonstrate analytical skills
Pedagogy:
The pedagogy will be a mix of lectures, experience sharing, real life case discussion, assignments and
industry/research based projects. The course is focused on strategic issues with cases as the primary vehicle
for learning. In addition to the reading materials, additional readings and cases will be distributed in the
class from time to time. Students are also expected to prepare and analyze all the cases as class participation
is very important. There are four main pillars in the course pedagogy, namely, (a) lectures-cum-PPTs to
share the conceptual frameworks; (b) experience sharing through collaborative teaching by industry experts;
(c) hands-on Statistica Data mining tools, computer-lab based; and (d) case studies of leading organizations
selected from Harvard Cases and other sources. The course requires a high degree of interactions in the class
on part of the students and feedback on their hands-on work is provided by industry experts.
Course Requirements:
vi.
vii.
viii.
ix.
x.
xi.
Since much of the course material requires class discussion, it is important that you are prepared for
the class and present and defend your ideas. Preparation for class includes having read the assigned
material.
You must have basic statistics and mathematics background. Basic databases knowledge is must.
We will use a number of cases in this course. Cases are a great educational experience but they
absolutely require that you be ready for the class. When cases are assigned, you should come to
class ready to discuss the issues of the case. For each case, you should: a) identify the major
problem, b) give your recommendation to resolve this problem (both short and long term), and when
appropriate d) provide supporting analysis (both qualitative and quantitative) for your
recommendations. Answering the questions provided for each case should help in this effort.
The class will be divided into a number of groups and each group will have 5 students. For all
cases, each group will submit case analysis report and power point presentation one day before
scheduled class.
There will be several home assignments assigned throughout the Term along with a number of
unannounced quizzes. Late homework will not be accepted and there will be no make-up quizzes.
Class participation will be based on the value you add to the class through your questions,
statement, and comments. It is the quality of these that is more important than the quantity.
Evaluation
Course duration: 20 sessions plus Statistica hands-on with Statistica certification
Evaluation
End Term
Project
PPT
:
:
:
35%
40%
25%
CAUTION: I use EPHORUS and Turnitin software for Plagiarism detection. All your project
submissions should come to me after verification plagiarism. IMTG has procured Turnitin, FYI.
Check with our IT /APO department.
SpecificAssessmentMethod
GroupProject
Weight
35%
5*
CasesStudyAssignments*
EndTermExamination
40%
25%
Building Data Mining Applications for CRM : Alex Berson, Stephen Smith, Kurt Thearling, TMH
Data Mining : Tools and Techniques by Han and Kamber
Too Big to ignore: Big Data : John Wiley Indian edition
All articles books by Davenport.
Purba Rao books on Analytics.
Reference Journals (you will have to read compulsorily)

All journals related to Big data.
Inderscience journals and Elsevier journals on big data.
Business Intelligence based topics and Data Mining Business Cases at www.thearling.com,
www.dmreview.com, and also cases from Springer/IEEE
Analytics magazine India : please read many free articles,
Industrial Management and Data systems, Emerald Publications
Acronyms used: BA- Business Analytics, BI (business Intelligence), DM (Data Mining), DWM (Data
Warehousing) , CRISP-DM, ETL, ODS. BDA : Big data

Note:
All topics presented below would follow the following time distribution of topics:
Sessions 1 & 2 (150 minutes), Session 5 & 6 , Session 10,13,14
20 minutes
20 minutes
10 minutes
30 minutes
20 minutes
20 minutes
30 minutes
Sessions 11 & 12 (150 minutes), Session 15 & 16 , Session 3,4,7-9

30 minutes
10 minutes
10 minutes
20 minutes
20 minutes
Sessions
Topic / Session/ Lecture Name
1-2
IntroductionData Management Issues; Role of Analytics in Business;

Effective IT infrastructure; connecting MIS that you
learnt in first year; recall ESS, EIS, DSS.
Why Data mining and Data Warehousing; What is data
warehousing; Several market vertical examples
Why Data mining and Data warehousing more definitions.
20 minutes
40 minutes
Explanations and comments

Book: Han and Kamber Data
Mining:
concepts
and
Techniques. Pages 1-7
www.thearling.com
white papers on What is
data mining
Davenport articles.
What is data warehousing: Several market vertical examples

Data ware house-definitions, differences with databases,
OLAP technology, data models, Warehouse architecture,
data mart Data ware House Implementation, Data CubesExamples, delivery process, schema, STAR, SNOWFLAKE,
CONSTELLATION, DATA MARTS, ODS, meta data,
aggregations, ETL tools.
Mining:
concepts
and
Techniques Pages 7-39
Mining:
concepts
and
Techniques Pages105-49
Data mining origin, DM knowledge discovery process;

Examples applications, DM community.
Methods and Techniques in Data Mining, Data
Warehousing.
Announcement of Project group based.
Differentiating Business Intelligence and Analytics : IBM
downloaded material that I usually provide.
Understanding analytics triangle by IBM.

Mining:
concepts
and
Techniques Pages 7-39 --contd
TCS Global Big

report.
Case : BI at Shoppers Stop, BI at ICICI, AIIMS, LIC. Cross McKinsey report.
comparison.
4
5-6
7-8
IBM Big Insights.

An overview of analytics industry. Big data concepts
Hadoop , MapReduce, SNIA servers, hadoop labs.
Caselets: Indian Glob
Systems.
Caselet: MuSigma.
data
IBM articles and white

papers.
Ref. my
materials
latest
Xeroxed
Analytics company: Manthan Stick on to my slides with

references
of
different
research report web links that
I have given
TEXTMINING TOOLS.
9-10
Indian Analytics Industry, Big data opportunities.. Complete

presentation.
Prepared from McKinsey Global Report, Gartner, IBM,
IDC, Forbes Views, Surveys.
Gartner Reports; Forrester

Repost. McKinsey , IDC,
TCS reports.
Research papers, Refer
Hand book
Reports of PWC, CRICIL, Bloomberg on growth of data.

11-12
BIG Data, Hadoop Systems, Case study on Indian

companies:
Absolute Data.
PMML, Big data tools.
Hadoop and BIG Data: Rules for Big Data architecture in
companies.
When should a company think of Big data. Developing Big
data engine.
What is V3 and v4 and V7. Text mining role, methods, tools.
Sentiment analysis and twitter analytics.
Articles on : HOW BIG is BIG Data. Big data market
Stick on to my slides with

references
of
different
I have given
12-13
Data Life cycle, Data Mining Tools snapshots, BI Vendors

Real Time Business Intelligence, Oracle BAM.
SOCIAL CRM through Social Media analytics
Big Data in verticals.
Machine learning and AI : needed for BDA.
Big data in retail.

references
of
different
I have given
Big data in financial management:

All applications with examples.
Text mining : Twitter Analysis, Sentiment Analysis
14-15
Building predictive models, Market Basket Analysis, CART,

CHAID. Type of variables, Data cluster analysis,
hierarchical and partitioning methods with practical
examples.
Understand prediction and forecasting.
Understand Neural networks
Calculating the ROI of BI by Jonathan Wu,
BASE CONSUTLING GROUP, USA
CRISP-DM Methodology
Cross-Industry Standard Process (CRISP) for Data Mining:
Introduction and applications
FACEBOOK Success through BI discovered: case
Guest lectures Computer lab Building Model : for marketing Basket
analysis
Using Statistica Software
Guest lectures Computer lab Building Model : for decision trees
Guest lectures Computer lab Building Model : for predictive modeling
Guest lectures Computer lab Building Model : for CHAID, Clustering
methods
16-19
extra Project discussions, descriptions and presentations
sessions
for
presentations

references
of
different
I have given
Computer lab
Computer lab
Computer lab
Computer lab
.
As a business student when you join companies especially in BI arena, you need to sometimes unlearn some
thing which you have done theoretically in the class as there are several advanced tools emerging and your
company may just use that. For this sake, last 2 sessions would be :
BI Consultancy: consulting, training, development in Analytics.
Data Mart building
ROI of DWH, Size of DWH: need
PMML,CRISP-DM
Data de-normalization, ETL, Data cleaning tools, meta data tools.
Big data companies : career profiles understanding
The schedule for tests, submission of projects, presentations will be intimated time to time in as per rules of
IMT. You are free to contact, discuss and clear your doubts with me between office hours. I expect complete
discipline, dedication and sincerity from each student. My office phone number is 0120-3002219.
Group Project
The group project will be one of the most important learning tools of the course. Each group will comprise
of 5 students. Each team will develop a live project. This is a highly interactive real life project, which
requires a high degree of analysis and tangible recommendations. Your group is required to identify a
company as well as project.
Project will be based on topics given below. These topics are only suggestive. Students will go to the
various organizations depending on the need of project and gather the information. According they will plan
for development of project. It is expected that project will involve additional time outside of class and lab
time to complete.
Project Ideas
The dates for submitting the topics, phase wise progress report & final submission will be decided in the
class. The presentation time per group will be 15 minutes with not more than 7-10 slides. If the time exceeds
negative marks will be assigned. The marks will be awarded on group performance basis. The presentation &
code will be e-mailed to the professor in form of a write-up at the following e mail : [email protected]
within 48 hours of the presentation.
The deliverables of the project include:
5.
6.
7.
8.
Project proposal
Interim Report
Final Report
Presentation


Scope of the study
Expected outcome
Project schedule
Interim Report Format

Interim report is like progress report and should be about 10 pages (maximum). It should include following:
Introduction/Background of the study

Scope of the study
Existing System
Data collection
Data analysis
Final Report Format

The final report has to be prepared and submitted in the format encompassing the areas mentioned here under
the heading of Contents.
Executive Summary
Acknowledgements
List of Abbreviations
List of Tables
List of Figures
1. Introduction/Background of the study
2. Objective of the study
3.
4.
5.
6.
7.
8.
9.
Scope of the study

Existing System
Data collection
Data analysis
Proposed System
Recommendations
References
Appendix
Ground Rules
The entire report must be in the range of 30-40 pages.
The Final Report format as mentioned in the heading Contents is not sacrosanct. It is subject to
change depending on the sector specific requirements that need to be incorporated and highlighted so
as to improve the understanding of BA/BI. Please use Summer Project Guidelines as Style Manual
for writing the report.
Grading of the report will be done on the strength of the analysis and explanation therein.
No graphs, which is basically a reproduction of the data provided, are to be included as part of the
report.
Please incorporate diagrams wherever possible.
Please follow the guidelines of the summer project in terms of report submission.

(PGDM)
Area- Finance/Analytics
Course Title: Treasury and Risk Analytics
Course Description
The importance of the treasury analytics is growing in business transactions due to
exposure of various kind of risk involved in it. Risk mitigation, exposure management and
the uses of hedging strategies are all now considered essential. Treasury managers must
be able to use and apply financial products in order to maximize profit along with
minimizing risk. With the ever-increasing range and complexity of available financial
instruments and derivatives, treasury analytics professionals must constantly update their
skills in order to effectively undertake their crucial duties. This course prepare students in
enhancing their skills to deal with key functions in foreign exchange management, risk
management, asset liability management and financing activities. This course includes the
discussion of various risks involves in treasury function and their management with the
help of case studies, practical data etc.
Learning Objectives
This course aims at providing the detailed application of various tools in finance to manage
the different types of risk associated with financial assets and a comprehensive
understanding of how to manage treasury affairs with a detailed look at the various
financial markets and instruments that can be traded.
After this course the participants will be able to:
1.
2.
3.
4.
Understand the overall risk measurement framework

Recognize the types of risk associated with the financial assets.
Quantify the risk
Identify and execute the best method to hedge the risk associated with the financial
assets.
5. Design the OTC derivative instrument with its valuations
Teaching Pedagogy
The pedagogy will be a mix of lectures, critique of readings/articles, case discussion,
assignments and data analysis using software. The course uses data and cases as the
means to drive the contextual suitability of treasury analytics. Besides the readings in the
course pack, additional reading material will be distributed in the class from time to time.
The 16 sessions of 1 hr 15 minutes each would be conducted.
Course Requirement
xii.
Prerequisite to this course is the learning derived from Derivatives and Security
Analysis and Portfolio Management courses.
xiii.
Since much of the course material requires class discussion, it is important that you
are prepared for the class and present and defend your ideas. Preparation for
class includes having read the assigned material.
xiv.
The class will be divided into a number of groups and each group will have 4-5
students. For all projects and assignments, each group will submit analysis report
and power point presentation one day before scheduled class.
xv.
Evaluation for this assignment will be done based on individual as well as

group performance.
xvi.
Class participation will be based on the value you add to the class through your
creating learning environment in class by raising intelligent questions, relevant
statements on questions raised by others, and maintaining class decorum.
Assessment method in alignment with learning outcomes

Students will be evaluated on the basis of case analysis, project, assignments, class
participation, mid-term and end-term exam. The weightages given to each of these units is
listed below:
Course Evaluation
Quiz (2)
Assignments (3)
Project report (3)
Mid Term Exam
End Term Exam
10%
10%
20%
10%
50%
Project Evaluation
Group
presentation
Group
Assessment
Methods
Group
Project
Proposal
Presentation
Group
Project
Presentation
Group
Project
Report
Submission
Group
Case
analysis
proposal

30%
40%
Group Project Report submission
Specific
Assessment
Method
Project
30%
Weightage Intended subject learning outcome to be

assessed
1.1
1.2
1.3
30%
30%
40%
15%
submission
Group
Assignments
Individual
Assessment
Methods
Mid Term Exam
End-term Exam
15%
30%
40%

The group project will be one of the most important learning tools of the course. Each
group will comprise of 5 students.
The project work should preferably be a practical issue, which requires a high degree of
analysis and tangible recommendations. Your group is required to identify a company as
well as project. Some projects are identified at the end of this note. The deliverables of
the project include:
9. Project proposal
10. Data Collection
11. Final Report along with data used (if applicable)
12. Presentation

Session 1: Introduction of Financial risk, types of financial risks, Explanation of the
Treasury Function in an Organisation: Corporate and Bank/FI, What is Treasury
Management? Structure of Treasury Management, Functions of Treasurer and Controller,
Participants in the Clearing/Non Clearing areas in the Derivative Market, Central
Counterparty, Clearing House/Clearing Member/Clearing Broker, Swap Dealer

15 minutes
20 minutes
Types of financial
risks, Market risk,
Introduction
to
treasury Credit risk, liquidity
risk, financial risk.
Analytics
Functions
of
Treasurer
and
Controller.
20 minutes
Quantification
of
different type of risk,
Participants
in
Treasury Function
20 minutes
Application of
analytics
in
risk
management,
Problem
solving
Session 2 and 3: Market Risk Value At Risk: Methods of calculating VaR Historical,
Parametric VAR, Simulation, Monte Carlo Simulation, Bootstrap VAR, Liquidity VAR, Credit
VAR

30 minutes
40 minutes
40 minutes
Estimation of Value at Parametric VaR,
Concept
of risk- Historical method and
Montecarlo
value at risk
VaR
and
its
importance
40 minutes
Liquidity VaR,
Credit
VaR,
Portfolio VaR,
RAROC
Session 4 and 5: Valuations of Equity and Equity Index Options using Black Scholes
Model, Binomial Tree Method and Taylors Series Method. KMV Model, Merton Model,
Real options.

30 minutes
Black
Scholes
Model
40 minutes
40 minutes
40 minutes
Model
Estimating Probability KMV
of default using Black Merton Model
Scholes model
and Business
Valuations using
Black Scholes
Model
Session 6 and 7: Option Greeks, Developing immunized portfolio using option Greeks
30 minutes
40 minutes
Introduction
to
option Features
Greeks
Greeks
of
40 minutes
Portfolio
immunization
Option option Greeks
40 minutes
Exercise
using
Session 8 and 9: : Introduction to the Credit Derivatives Market: . CLO, CBO, CDO etc,
SPVs, CDS, Players in the CDS market, Interpretation of CDS Spreads/Index, Valuations
of CDS, Total Return Swap
30 minutes
40 minutes
Credit
derivative CDS valuation
market, CDS
40 minutes
Total Return Swap
40 minutes
Copula
Functions
Session 10 & 11: Multi Period options, caps, floors, captions, swaptions
30 minutes
Introduction to
multi
period
options
40 minutes
Caps and Floors
40 minutes
Captions
40 minutes
Swaptions
Session 12 and 13: Evolution of risk measures- Standard Deviation, Semi deviation, VaR,
CVaR, etc, Risk modeling using performance analytics package in R.
30 minutes
Introduction to R
software
40 minutes
40 minutes
Risk Modelling in R
Performance
package
analytics
40 minutes
Altman z score,
Practice
Session 14 & 15: Simulating Financial Asset Price, Arithmetic and Geometric Brownian
motion, Introduction to Martingales.
30 minutes
40 minutes
Simulations
Asset Prices
40 minutes
40 minutes
Arithmetic and Geometric

Brownian motions
Martingales
Session 15 and 16: Project Presentations

Project Presentations: Your proposal should include following:

Scope of the study
Expected outcome
The presentation should cover both the analysis of primary and secondary data, as
applicable.
Each presentation will be of 10 minutes with 8 minutes given to the group to
highlight the key findings and 2 minutes for open discussion in the class.
Post-Graduate Diploma in Management
Financial Econometrics
Background and Objective

The course is a gateway to econometric modelling and applications in finance. Financial
econometric is a tool to help in understanding and analysing the finance better. The
subject eases the processing the financial information for various decision making
purposes. Of late, modern tools and techniques have become necessary to know the
complex financial products and their behaviour in the markets.
The course is intended to deliver the following objectives to;
Understand econometric concepts for modelling
Critically analyse the situation for forward thinking with innovation (Programme obj-3.1)
Perform various diagnostic checks to establish the model
Report the results/outcomes and their managerial implication
Demonstrate techno-savvy analytical capabilities (Programme obj-3.2)
Teaching Pedagogy
The pedagogy will be a blend of lectures, critical articles, case discussion and
assignments. A well formed course pack will be given. The course employs chapters of
the course pack as the means to link the theory with practices. Every theoretical session
will be followed by hands-on session to appreciate the concepts by applying them. Data
sets for the hands-on exercises are to be downloaded from the folder FE folder within the
Hands-Out available in the common server.
Basic Text Book
Basic Econometrics by Damodar N. Gujrati & Sangeetha
Recommended Books
Introduction to Econometrics by G S Maddala
Introductory Econometrics for Finance by C. Brooks

Applied Econometric Time Series by W. Enders
Financial Econometrics by C. Gourieroux & Joann Jasiak
Practical Financial Econometrics by C. Alexander
Web Links
www.sebi . gov.in
www.mcxindia.com
www.ncdex.com
www.nseindia.com
www.bseindia.com
Software/Tools
Eviews-6, & R
Assessment method in alignment with learning outcomes

Students will be evaluated on the basis of quizzes, end term, final project presentation and
submission, and class participation. The weightage given to each of these units is listed below:
Evaluation Criteria
Quiz
End Term
Final project Presentation
Class participation
20%
50%
20%
10%
Assignment Evaluation
Final assignment is to be done and presented in a group of 4-5 members. The group should
be formed after the second session. Each group has to select a
commodity/index/stock/currency etc. which may be given by the instructor. Each group is
expected to present all the concepts and analysis discussed in the class. Assignment
presentation would be evaluated based on the concepts and coverage, depth of analysis,
presentation skill and question & answer.
Class Participation
As this course is centred around both theory and hands-on, so active classroom
participation is expected from every student. Those who will present would definitely be
categorised as active class participation.
Evaluation Type
Weightage
Group Project
Group project
End term
20%
50%
Intended programme objective (students

learning outcome)
Programme
Objective-3.1
Programme
Objective-3.2
Guidelines for Assignment Presentation

i.
The presentation should be based a proper flow.
ii.
The
rationale
for
choosing
commodity/stock/currency/index etc. and the country should be justified.
iii.
the
The data collected should be properly analysed and

presented.
iv.
Each presentation has to finish off by 25 minutes. First

10 minutes for the background information, portfolio activity etc. 10 minutes for analyses,
final 2 minutes for conclusion and 3 minutes for question & answer.
Session Plan
Session 1 & 2: Overview of Classical Linear Regression Model (CLRM) and Hands-on
exercise on data sets
Session 1 & 2 (150 minutes)
30 minutes
30 minutes
15 minutes
75 minutes
How
CLRM
is Hands on experience
What
is Different
characteristics performed?
with Eviews & R
classical
of CLRM
Linear
Regression
Model?
Session 3 & 4: Further Developments and Diagnostic Tests of CLRM (Programme obj3.1) and Hands-on exercise on the data sets
30 minutes
15 minutes
30 minutes
75 minutes
What
are Importance of Various
necessary Hands on experience
further
diagnostic
diagnostic checks after with Eviews & R
developments checks
performing CLRM
of CLRM?
Session 5 & 6: Problem of Heteroscedasticity (when the error variance is non-constant) &
Autocorrelation (when the error terms are correlated) (Programme obj-3.1) and Hands-on
exercise on the data set (Programme obj-3.1)
30 minutes
What
is
heteroscedasticity?
Why it has to be
taken care of?

30 minutes
15 minutes
75 minutes
What
is What are different Hands on experience
autocorrelation? methods to detect with Eviews & R
Why it has to be heteroscedasticity
and autocorrelation?
taken care of?
Session 7 & 8: Concepts of Time Series Tests of stationarity, unit root, Univariate Time
series modelling (Programme obj-3.1) and Hands-on exercise on the data sets
(Programme obj-3.2)
30 minutes
What is time
series?
What
are
different

30 minutes
15 minutes
75 minutes
What is non- Discussion
on Hands on experience
stationarity?
Univariate time series with Eviews & R
What is unit moddeline-ARIMA
root problem?
components
of a time
series?
Session 9 & 10: Modelling Volatility (Programme obj-3.1) and Hands-on exercise on the
data sets (Programme obj-3.2)
30 minutes
30 minutes
15 minutes
75 minutes
Hands on experience
What
is Discussion on Diagnostic checks
with Eviews & R
various
volatility?
What
is volatility
modelling
conditional
volatility?
Session 11 & 12: Multivariate Time Series Modelling- Vector Auto Regression (VAR), and
Hands-on exercise on the data sets (Programme obj-3.2)
30 minutes
30 minutes
15 minutes
75 minutes
Test
of Diagnostic checks
Hands on experience
Discussion
with Eviews & R
on multivatite causality
time
series
modelling
(VAR)
Lag
length
selection
Session 13 & 14: Co-integration, Error Correction Modelling (ECM). (Programme obj-3.1)
and Hands-on exercise on the data sets (Programme obj-3.2)
30 minutes
30 minutes
15 minutes
75 minutes
Error correction Diagnostic checking on Hands on experience
Discussion
models formulated
with Eviews & R
on long term modelling
relationship
(cointegration)
Error
correction
modelling
Session 15 & 16: Course recap, final and project presentation, and feed back
Post-Graduate Diploma in Management-Full Time

(PGDM-FT)
Area: Operations
Course Title Operations Analytics
Course Description:
This course is aimed at improving the students skills in solving Operations and supply chain
problems through development of modeling and analytical skills
The primary goal of this course is to introduce the concepts, modeling, and dynamics of Supply
Chains and their design considerations. The specific objectives are as follows:
1. To introduce the concepts of Supply Chain Dynamics and its impact on Design of SCs
2. To introduce techniques to model the supply chain mathematically
3. To introduce the appropriate mathematical techniques to analyze it
4. To introduce the principles on which to design suitable system controls appropriate for the
situation at hand
5. To provide a deeper understanding of the underlying dynamic factors affecting SC operation.
The above modeling and analytical skills will prove useful and effective in the design of supply
chain systems, as well as their operation
Learning Outcomes:
At the end of the course, the students would be able to:
1. Conceptualize a dynamic supply chain and identify factors in a dynamic environment that
affect it.
2. Model the supply chain mathematically in a dynamic environment.
3. Apply appropriate mathematical techniques to analyze it
4. Design suitable system controls appropriate to the objectives of the chain.
5. Obtain a deeper understanding of the dynamics and factors affecting the supply chain.
Pedagogy:
Pedagogy:TheMathematicaltechniquesusedformodeling,analysisanddesignofSupplyChains
inadynamicenvironmentwillbethefocusofthiscourse.TheoryandClassroomlectureswillbe
themainstayforthecourse.Therewillbeseveralgroupassignments,whichwillservetoelucidate
thetheoreticaldiscussions.Atermpaperisalsoenvisaged,ifpossible,whichwouldhelpthe
studenttoprobedeeperintothetopic.
Note: There is no text-book available for the latter Applications part of this course, and hence
students are advised to take down notes in class. Course notes will not be supplied, rather
students are required to take down their own notes in class to supplement their
understanding.
The course will be mathematical and a number of mathematical techniques will be developed
sequentially. Hence students are requested not to miss any class whatsoever to maintain their
learning continuity
Evaluation
Evaluation Scheme:
Sr. No.
1
2
Components
Weightages (in %)
Related Learning Outcomes
20%
Learning outcomes 1,2,3,4

Learning outcomes 1, 2, 3, 4,
and 5
Mid-term Exam
Assignments
20%
3
Term paper/Class test
20%
EndTerm
Examination
40 %
Learning outcomes 1,2,3,4

and 5
Learning outcomes 1-4
Group Project/Alternatively, Class Test

Group Project/ Term-paper: will involve a deeper analysis of supply chains and their dynamics
based on the current research literature available
Alternatively, a class test would be conducted on the syllabus as prescribed for it by the instructor
Assignments
A number of group assignments are envisaged to elucidate the mathematical concepts
covered in class
Recommended Text Book

Basic Text Book:
Difference Equations, 2/e, Kelley G Walter and Peterson C Allan, Academic Press, (2001), Elsevier
ISBN-0-12-403330-X
Reference Books:
Reference articles from research journals, if required
Note: There is no text-book available for the latter Applications part of this course, and hence
students are advised to take down notes in class.
E-Resources/Databases:- (ONLY IF REQUIRED)
ON 10.40.0.25 IMTS LIBRARY PORTAL: JSTORE; EBSCO; HBR; DELNET; etc.
Course Outline: Session No/Topic/Reading Material

Session Plan:
Session
No
1
Topic
Motivation,DynamicSupplyChain
examples,andControlPrinciples:
Reference material
Classnotes
4,5
6,7,8
913/14
AnaircraftMaintenancehangarexample,
increasinginventoryfluctuationsalongthe
chain,andincreasingdisturbance
propagationbackwardsinthechain.Likely
Bullwhipeffect,Control/mitigationofthe
bullwhipeffect,controlobjectives:basedon
ResponsivenessandEfficiency
SupplyChainStrategiesandtheir
PerformanceMetrics:Twobasicstrategies:
ResponsivenessversusEfficiency,flexibility,
theirperformancemetrics,measurement,
implications,andoperationalsignificance
VarioustypesofControlsforSCs:Inventory
triggeredanddemandtriggeredcontrols,
proportional,proportionalintegral,and
proportionalintegralderivativetypeof
schemes,movingaveragetypeofschemes,
andtheirbasiccharacteristics
IntrotoLinearDifferenceEquations;
historicaldevelopmentandoccurrenceof
differenceequations,examplesfromclassical
mathematics,examplesformdiversefields:
physics,engineering,biology,etc.,examples
inmanagementdisciplines,relationshipwith
andoccurrenceinotherareasof
mathematicsandmathematicalmodeling,
combinatorialproblems,recurrencerelations
andinduction,closerelationshipwith
differentialequations
DifferenceCalculusanditsdevelopment:
Thedeltaoperator,theshiftoperatorE,
operatormechanics,differentiationcalculus,
deltacalculusofsimpleandcommon
functions,thefallingfactorialnotationandits
centralroleindifferencecalculus,product
rule,quotientrule,parallelwithdifferential
calculus,thesummationoperator,asthe
inverseofthedeltaoperator,summation
rules,summationbyparts,theconstantof
summation(akintotheconstantof
integrationincontinuousvariablecalculus),
indefiniteanddefinitesummation
SolutionMethodsforLDEs:
LinearDifferenceEquationsandcanonical
forms,firstorderequations,homogeneous
andnonhomogeneousequations,second
andhigherorderequations,InitialConditions
anduniquenessofsolution,shigherorder
LDEswithconstantcoefficients,
homogeneoussolutionandparticular
do
do
Ch1
Ch2
Ch3
14/1518
19
20
integral,theannihilatormethod,factoring
theLHSOperator,formofthesolution,
linearlyindependentsolutions,the
Casoratianmatrix,repeatedroots,complex
roots,specialmethodsforLDEs,series
expansionmethods,thegeneratingfunction
ApplicationsandWarehousesystem
Models:
Designparametersanddisturbancetypes,
TheP(I),P(D)andP(ID)schemesandtheir
characteristics,controlofoffsetand
permanentdepletionofinventory,thePI(I)
scheme,thePID(I)scheme,theirdesign
parametersandfluctuationlevels,methods
forcontroloffluctuationsandrapid
restorationtonormalcy,theMA(ID)scheme,
comparativeperformanceanddesign
parametersettings
TermpaperPresentations
Review,Wrapup,andscopeforfurther
reading
ClassNotes
*Chapters indicated are with reference to the Basic Text Book

Note: The split of sessions between topics and number of sessions for each topic are of an
indicative nature, and could be varied based on the learning progress of the students
Any other Remarks:

Learning outcomes 1, 2, and 5 will measure modeling skills, and 3 and 4, analytical skills
Mid-term Exam: will be held in the 16th or 17th session
The schedule of the class test will be announced later.
Industry Application:
Most supply chain and warehouse operators, especially the TPL (Third Party Logistics) providers,
are switching to automated control systems for their warehouses and supply chains, given their
scale of operations and the dynamic nature of their operations. Hence the systems/software
providers are now in the process of developing warehouse management software packages capable
of handling such dynamic systems, and are hence required to model and analyze such systems. The
techniques covered in this course would provide the necessary background and tools and techniques
for these requirements. And consequently, these systems providers are also in need of competent
personnel who can model and analyze such systems. It is only a question of time before they start
actively looking for such people, and you could be the ones to fit their requirements precisely.
Post-Graduate Diploma in Business Management

Subject Title: HR Analytics
(Term VI)
Course Description
This course exposes the student to the concepts and business applications of HR Data,
metrics, systems, analyses, and reporting. It provides an overview of how to track and
analyse HR data to support decision making in realm of human capital management.
Different tools and techniques used to analyse quantitative data to draw insights for
effective decision making will be covered.
Learning Outcomes
1) Research and analyse appropriate internal and external human resource metrics,
benchmarks, and indicators.
2) Apply quantitative and qualitative analysis to understand trends and indicators in
human resource data; understand and apply various statistical analysis methods.
3) Help participants appreciate and use analytics to improve HR processes like
attraction, retention, performance and engagement of talent.
Teaching Pedagogy
A mix of pedagogical methods will be used. Case studies, class discussions, project
based, problem solving with hard data, etc will be the prominent methods.
Session Plan
Sessions: 1 & 2
Topic
Readings/Cases
Introduction to HR Metrics & 1)Competing on Talent Analytics
Analytics
2) Learning from Practice: How HR Analytics Avoids
being a Management Fad
Sessions 3 & 4
Topic
How and Why HR Analytics is
Strategic.
Linking
HR
Analytics
to
Business
Performance
Sessions 5 & 6
Topic
Foundations of Measurement
Readings/Cases
3) Making HR Measurement Strategic
4) Toward Analytics and Prediction
Readings/Cases
5) Analytics Foundations of HR Measurement
6) Big Data and Talent Management: Using Hard
Data to make the Soft Stuff easy
Sessions 7 & 8
Topic
HR Metrics for Effectiveness
Evaluation
Readings/Cases
7) Predictive Analytics in Action
8) The Analytics Era
9) Prioritize Critical Business Questions
Sessions 9 & 10
Topic
Tools and Techniques for
Analytics
Sessions 11 & 12
Topic
Metrics to Optimize HR Cost
Reduction
Readings/Cases
10) Apply Business Judgement to Data Science
11) Drive End-to-User Ownership of Talent
Analytics
Readings/Cases
12) Using HR Metrics to identify opportunities for
Cost Reduction
13) Business Driven HR Analytics Case of Novo
Nordisk
Sessions 13 & 14
Topic
Evidence Based
Support System
Decision
Readings/Cases
14) Implication Based Decision Support Case of
Seagate
15) Analytics Prioritization Principles Case of
Gap Inc.
Sessions 15 & 16
Students Presentations
Course Pack
A Compilation of selection readings, cases, etc will be given to the course participants.
Evaluation Scheme
Class Participation
Group Assignment
Individual Assignment
Case Discussion
End Term
:10%
:20%
:10%
:10%
: 40%
References Books:
Jac Fitz-Enz- The New HR Analytics- Predicting the Economic Value of Your Companys
Human Capital Investment-, American Management Association.
Becker, B., Huselid, M, and Ulrich, D. The HR Scorecard: Linking People, Strategy, and
Performance. HBS Press, 2001.
Cascio, W & John Boudreau- Investing in People: Financial Impact of Human Resource.
Robert S. Kaplan and David P. Norton, The Balanced Scorecard: Translating Strategy into
Action (Boston, MA: Harvard Business School Press, 1996).

(PGDM)
Area- Analytics
Course Title:
Quantitative Models in Marketing (QMM)
Course Description
1. Introduction
Quantitative models in marketing plays a crucial role in providing decision makers with timely and objective
information to help them make informed decision in many areas. QMM links the consumer, customer and the
public to the marketer through information. The information is used to identify marketing opportunities and
problems (market demand determination, market segments identification, product/ service use studies,
competitive analysis), in generating, refining and evaluating potential marketing actions (proposed
marketing-mix evaluation testing, concept tests of proposed new products or services, new-product
prototype testing, pricing tests, advertising pretesting, in-store promotion effectiveness studies, distribution
effectiveness studies), in monitoring marketing performance (image analysis, customer-satisfaction and
distributor-satisfaction studies, web site evaluations) and improving marketing as a process (consumer
behaviour differences in e-business transactions, Predictors of new product success, The impact of longterm advertising on consumer choice). Thus, QMM is highly indispensable in generating the information
necessary for assisting in the strategic decision making.
The course of QMM is designed with a special emphasis on multivariate data analysis which is the lifeblood
of marketing research. Students taking the course will gain an expertise in different multivariate data analysis
tools like discriminant analysis for classification and prediction, cluster analysis for market segmentation,
conjoint analysis for product design and multidimensional scaling for brand positioning etc. They will also
gain hands-on experience in different statistical software like SPSS and AMOS.
Pre-requisites to take this course include successful completion of Business Research Methods with an
expertise in the statistical tools and techniques. The students should also have clarity of marketing
management and should possess sound analytical skills.
Course outcomes: After successful completion of the course, the students should be able to:
Understand the role of quantitative models in marketing research in taking better decisions.
Apply the research skills in a team in solving marketing problems.
Decide on the appropriate statistical tool to be used.
Analyse the collected data with the statistical tool.
Interpret the output of the analysis generated by the software.
Learning Objectives: The course is designed to help students to:
Appreciate the application of marketing research in solving marketing problems.

Determine which multivariate technique is appropriate for a specific marketing research problem.
Apply multivariate data analysis skills using SPSS & AMOS software.
Teaching Pedagogy
The pedagogy will be a mix of lectures, critique of readings/articles, case discussion, assignments and data
analysis using SAS software. The course uses data and cases as the means to drive the contextual
suitability of predictive modeling. Besides the readings in the course pack, additional reading material will be
distributed in the class from time to time.
Course Requirements
xvii.
Prerequisite to this course is the learning derived from Business Statistics and Business
Research Methods courses.
xviii.
Since much of the course material requires class discussion, it is important that you are prepared
for the class and present and defend your ideas. Preparation for class includes having read the
assigned material.
xix.
The class will be divided into a number of groups and each group will have 4-5 students. For all
projects and assignments, each group will submit analysis report and power point presentation one
day before scheduled class.
xx.
Evaluation for this assignment will be done based on individual as well as group
performance.
xxi.
Class participation will be based on the value you add to the class through your creating learning
environment in class by raising intelligent questions, relevant statements on questions raised by
others, and maintaining class decorum.
Evaluation
Students will be evaluated on the basis of case analysis, project, assignments, class participation, mid-term
and end-term exam. The weightages given to each of these units is listed below:
Course Evaluation
Class Participation
Assignments (4)
Project report (1)
Quiz (best 1 out of 2)
End Term Exam
10
10
30
10
40
Project Evaluation
Group Project Report submission
Specific
Method
Assessment
Group Assessment
Methods
Group
Project
Proposal Presentation
Group
Project
Presentation
Group Project Report
Submission
Group Case analysis
submission
Group Assignments
Individual
Assessment
Methods
Mid Term Exam
End-term Exam
Weightage
20
10
Intended subject learning outcome to be assessed
30%
30%
40%
15%
15%
30%
40%

The group project will be one of the most important learning tools of the course. Each group will comprise of
5 students.
The project work should preferably be a practical issue, which requires a high degree of analysis and
tangible recommendations. Your group is required to identify a company as well as project. Some projects
are identified at the end of this note. The deliverables of the project include:
13.
14.
15.
16.
Project proposal
Data Collection
Final Report along with data used (if applicable)
Presentation


Scope of the study
Expected outcome
The presentation should cover both the analysis of primary and secondary data, as applicable.
Each presentation will be of 10 minutes with 8 minutes given to the group to highlight the key
findings and 2 minutes for open discussion in the class.

Session 1 & 2: Understanding Market response models.

15 minutes
20 minutes
20 minutes
20 minutes
Market
response Estimation of different Practice
response
exponential market
Introduction to models,
models, semi log and models
quantitative
models
in double log models, Log
marketing area models
Session 3 & 4: Forecasting of a new product using Bass diffusion models.

15 minutes
20 minutes
20 minutes
20 minutes
Bass diffusion model, Estimation of Bass Practice

Understanding estimation of market Diffusion model with
diffusion model response, coefficient of the help of case studies
in new product innovation and imitation
Session 5 & 6: Brand Analysis, Perceptual models, preferential mapping and image mapping of
different brands.
15 minutes

20 minutes
20 minutes
Perceptual mapping
Preferential mapping
20 minutes
Image mapping
Introduction to
brand analysis
Session 7, 8, 9 and 10: Structural equation Modelling, construct analysis, path analysis

45 minutes
45 minutes
30 minutes
Testing goodness of fit, Case study
Path
analysis,
Constructs and
Mediating
and
variables.
Developing
structural
Types
of models, Estimation of moderating effects
constructs,
SEM, Assumption of
Reflexive and SEM
formative
constructs
30 minutes
Session 11 & 12: Product Analytics

20 minutes
20 minutes
20 minutes
Designing conjoint
method
of
Types of attributes layout, Estimation of Matrix
and utilities
utilities and relative solving system of Practice
importance
of equations, Case study session
attributes
15 minutes
Session 13 & 14: Survival analysis

15 minutes
Survival function,
Lifetime distribution
function and event
density

20 minutes
20 minutes
20 minutes
Hazard function and
Fitting
cumulative
hazard Censoring,
function, Quantities parameters to data, Case study
derived from the Non-parametric
estimation,
survival distribution
Distributions used in
survival analysis
Session 15 and 16: Project presentations

Analytics

Uploaded by

Copyright:

Available Formats

Analytics

Uploaded by

Document Information

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

Analytics

Uploaded by

Copyright:

Available Formats

Post-Graduate Diploma in Management-Full Time

Course Prerequisites and Requirements:

To be monitored for all

Submission Requirements and Guidelines:

Recommended Text Book

Course Outline: Session/Module/Reading Material

Crosstabs, Chi-square Test, Association, Risk & Factor Analysis.

Session 2 (January 15): Data Mining & Dimension Analytics

Crosstabs, Chi-square Test, Association, Risk & Factor Analysis.

Session 3 (January 19): Predictive Analytics

Linear and Polynomial Regression, Interaction Effects, Multi-group Regression

Session 4 (January 22): Predictive Analytics

Linear and Polynomial Regression, Interaction Effects, Multi-group Regression

Session 5 (January 29): Mid Term Exam

Session 6 (February 2): Interactive Analytics

Big data, Web-site and Web-advertising Analytics, Attribution Modeling.

Session 7 (February 5): Interactive Analytics

Big data, Web-site and Web-advertising Analytics, Attribution Modeling.

Session 8 (February 9): Conjoint Analytics

Part-worth Utilities, Multi-attribute Modeling

Session 9 (February 12): Conjoint Analytics

Part-worth Utilities, Multi-attribute Modeling

Session 10 (February 16): Positioning Analytics

Session 11 (February 19): Positioning Analytics

Sessions 11 (150 minutes)

Session 12 (February 23): Mixture Analytics: Cluster Analytics

Hierarchical Cluster Analysis, K-Means Cluster Analysis, Discriminant

Session 13 (February 26): Mixture Analytics: Cluster Analytics

Hierarchical Cluster Analysis, K-Means Cluster Analysis, Discriminant

Assignment #2: Predictive Analytics

Assignment #4: Positioning Analytics

(Chocolates are numbered from left to right as chocolate_1 to chocolate_16)

Assignment #5: Mixture Analytics

Post Graduate Diploma in Management

Business Analytics & Predictive Modelling

Institute of Management Technology, Ghaziabad

Group Project presentation

Intended subject learning outcome to be assessed

Guidelines for Group Project

Project Proposal Format

Introduction/Background of the project

Guidelines for Presentation

Course Outline: Session/Module/Reading Material

Sessions 1 and 2 (150 minutes)

Introduction to R software Econometrics vs data Practice

Sessions 3 and 4 (150 minutes)

Basic regression analysis, Assumptions

OLS Case study

Sessions 5 and 6 (150 minutes)

Sessions 7 and 8 (150 minutes)

KMO and Bartlett test,

Sessions 11 and 12 (150 minutes)

Session 15 and 16: Project presentations

Post-Graduate Diploma in Management

Area: IT and Analytics

CRISP-DM Methodology: Cross-Industry Standard Process (CRISP) for Data Mining:

Reference Journals (you will have to read compulsorily)

Course Outline: Session/Module/Reading Material

Sessions 11 & 12 (150 minutes), Session 15 & 16 , Session 3,4,7-9

Topic / Session/ Lecture Name