Scribd
Upload
32 views5 pages

DMPA

Data Mining and Predictive Analytics IIM Ranchi

Uploaded by

Sagar Ansary
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
32 views5 pages

DMPA

Data Mining and Predictive Analytics IIM Ranchi

Uploaded by

Sagar Ansary
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

Indian Institute of Management

Ranchi

Course Name:
Data Mining & Predictive Analytics
Term IV, 2017-2019

Course Outline

INSTRUCTOR AND CONTACT INFORMATION


Name: Pradip Kumar Bala
E-mail: [email protected]
Office Tel: 140

COURSE DESCRIPTION

Data Mining & Predictive Analytics deals with data mining techniques used in analytics with
a thrust on predictive analytics. Predictive analytics is used to make predictions about unknown
future events. Predictive analytics uses data mining and other techniques based on statistics,
modeling, machine learning, and artificial intelligence to analyze current and past data to make
predictions about future. However, the focus of this course is on data mining techniques and
their applications in predictive analytics.
Participants will also have hands-on-experience on data mining software, R and also in SPSS
Modeller and they need to use software (preferably R) for their group project work.

COURSE OBJECTIVE

Objective is to impart knowledge on the emerging trends in data mining and predictive analytics,
enabling students to understand and appreciate the importance of making meaningful use of large
volume of data in decision-making processes in various functional area of management.

LEARNING OUTCOMES

Students will learn how to make meaningful use of large volume of data for business insight in
managerial decision making.
2

ALIGNMENTS OF INTENDED PROGRAM & COURSE LEARNING OUTCOMES

Program Learning Outcomes Course Learning outcomes

 Develop competence in participants to learn and adapt to the dynamic


national and international environments and strive for excellence. Students will learn how to
make meaningful use of large
 Orient the participants to apply knowledge and understanding of theories and
volume of data for business
concepts from basic disciplines and functional areas for creation, growth, and
insight in managerial decision
management of organizations. making.
 Develop acumen to implement suitable strategies by critically analyzing both
internal and external organizational environment.

 Understand various approaches and techniques relevant to the organizational


processes, models and practices.

 Develop cultural sensitivity to appreciate diverse points of view in a global


environment.

 Exhibit high degree of integrity and ethics in behavior.

REQUIRED COURSE MATERIALS AND READINGS

TEXTBOOK

Linoff and Berry – Data Mining Techniques (Wiley)

Additional References:

(i) J. Hahn and Micheline Kamber - Data Mining: Concepts and Techniques (Morgan Kaufmann)
(ii) A.K.Pujari -Data mining (University Press)
(iii) John W. Foreman – Data Smart (Wiley)
3

EVALUATION

GRADING SCHEME

Component Mode Duration Weightage


Mid Term Exam Written examination 1.5 Hrs. 25%
(Compulsory) (Open-Book)
Written examination 2 Hrs. 35%
End Term Exam (Open-Book)
(Compulsory)
Quizzes/ Assignments
Project Report (10%) and
Group Project Project Presentation (10%) 20%

Participation In-class Contribution 20%


(Individual)
Total 100%

ACADEMIC DISHONESTY
i. It may be noted that any kind of copying/plagiarism by any student and/or malpractice in
examinations will be subject to strict disciplinary action under IIM Ranchi rules. If a student is
found guilty in any such case(s), it will be recorded in his/her personal file.

ii. The reports submitted by the students like Summer Project Reports/Term Papers/ Case Study
Report/ Project Report/CIS dissertation paper or any other report will go through the anti-
plagiarism software.

iii. In all cases where the software has reported more than 30% of plagiarism by a student or
group of students, there will be automatic conversion of the grade given in that component
into “F”.

iv. The faculty may even choose to report the matter to the PGP Committee which will temporarily
convert the course grade into “F” or an “I”, issue a show cause to the student (s) and based
upon the response of the student(s) assign any punishment or its combination from the options
below.
4

a. Expulsion from the Institute


b.Suspension for a specified period
c. “F” grade in the course concerned
d.Scaling down grades obtained in the specific subject
e. Repeating the course
f. Withdrawal of placement services
g.Suspension, withdrawal or made ineligible for scholarships

For details, kindly refer to PGP Manual.


Course Schedule

Session Topics to be Readings Assessment


covered in the course and Book Criteria
Chapter
1 ‘Data Mining’ as a subject for the management students,
Motivation behind data mining, Predictive analytics vs
Descriptive Analytics
2 What is data mining?, KDD vs Data Mining (DM), DM Tasks,
DM Application Areas
3 Association Rule (AR): Market Basket Analysis, Representation
of an AR, Strength of AR
4 Support, Confidence, and Lift, Generalized Association Rule
(numeric, categorical, temporal, spatial etc.)
5 Association rules in Market Basket Analysis and Inventory
Management
6 Difference between clustering & classification, Modeling a
business problem into clustering or classification problem
7 Application of clustering in customer segmentation, drug
clustering, product grouping
Association rule as input to clustering
8 Classification using Decision Tree, Decision tree for customer
segmentation
9 Decision tree for prediction of demand, Identification of
classes guided by business
10 KNN, Random Forest for ensemble classification
11 Classification using Artificial Neural Network (ANN),
Association rule as input to classification, Hybrid data mining
models in DSS
12 Feature Selection, Identification of important attributes for
predictive modeling
13 Sequence Mining, Sequence rules from online purchases,
Sequence rule as an input in inventory management and CRM
14 Text Mining and Web Mining

15 Performance Measures of Classifier, Cumulative Gain Chart


5
16 Lift Chart, Decile Chart and ROC Curve (to be contd. in the
next session)
17 Lift Chart, Decile Chart and ROC Curve (contd. From the
previous session)
18 Issues in Model fitting: Overfitting, unbalanced data,
oversampling, undersampling
19 Sampling Techniques for cross-validation of models, Group
Presentation on Project Work
20 k-fold, Monte-Carlo, Bootstrapping, Group Presentation on
Project Work

Details of Group Project (optional)

You might also like