S. P.

MANDALI’s
PRIN L. N. WELINGKAR INSTITUTE OF MANAGEMENT DEVELOPMENT & RESEARCH,
Bengaluru

ACADEMIC DELIVERABLES CELL (ADC)

TEACHING AND LEARNING PLAN (TLP)

Title of the Course Machine Learning- I

Course Code
No. of Credits 3
No. of Hours 30
No. of Sessions 15
Marks 100
Pre-requisite Course(s), if any
Name of the Program PGDM Research and Business Analytics (PGDM RBA)
Specialization, if any
Course Revision No.
Academic Year 2023-24
Batch Year 2023-2025
Trimester/Semester Trimester III
Syllabus Revision No.
Name of the Faculty Dr. Tripti Mahara
Faculty Email Address [email protected]
Faculty Contact No. 9761714567

Description of the Course:

Machine learning is the science of getting computers to act without being explicitly programmed.
Applications of machine learning in various domain include self-driving cars, speech recognition,
effective web search, and a vastly improved understanding of the human genome. It is so pervasive
today that you probably use it dozens of times a day without knowing it. Looking at the potential of
machine learning, this course provides core knowledge and skills required in the area of Machine
Learning Algorithms so that it can be used for effective business decision making.

1
Course Learning Objectives:
1 To introduce fundamentals of Machin Learning
2 To apply data preprocessing techniques for data preparation
3 To solve business problems using Supervised Machine Learning Algorithms
4 To examine application of Neural Networks in business
5 To discover Unsupervised Machine Learning Algorithms for business decision making

Course Outcomes (CO):

Course Course Outcome Blooms Blooms Level
Outcom Level (in word)
e (in
Number Roman
Numerals
)
CO1 Illustrate types of Machine Learning Algorithms II Understandin
with examples g
CO2 Make use of relevant data preprocessing techniques III Applying
to prepare data for model building.
CO3 Experiment with different supervised machine III Applying
learning algorithms to address a business problem
CO4 Examine application of Neural Networks in IV Analyze
business.
CO5 Assess Unsupervised Machine Learning V Evaluate
Algorithms to get insights from data and help in
business decision making

Role of Self in 'Data

PO Critical &
Communica- Global Per- the Organiza- Driven De-
/ Leadership Innovation Analytical
tion Skills spective tion & in Soci- cision
CO Thinking
ety Making'
CO1 3
CO2 2 3 3 2 3
CO3 2 3 3 3 2 3
CO4 2 3 3 3 2 3
CO5 2 3 3 3 2 3

Detailed Session Plan:

Session Topic and Subtopics to be CO(s) Pedagogy
2
No. Covered Mapped to
the Topic
1 Introduction to Machine CO1 Lecture
Learning: Overview of Artificial
Intelligence, Machine Learning and
Deep Learning, Need for Machine
Intelligence, Overview of types of
ML Algorithm: Supervised,
Unsupervised & Reinforcement
Learning, Introduction to CRISP-
DM framework.
2, 3 ML Modeling Process: CO2 Lecture, Hands on Session
End-to-End Machine Learning
Project: Working with Real Data,
Understand & Frame the Business
Problem, Data Preparation, Data
Cleaning, Feature Engineering,
Overview of Training and Test Data.

4, 5 Supervised Learning: Regression CO3 Lecture, Demonstration and

Technique Hands on Session
Understanding Regression
technique, Model Estimation &
Prediction, Model Selection and
Validation, Execution &
Interpretation.

6,7 Supervised Learning: CO3 Lecture, Demonstration and

Classification Technique Hands on Session
Introduction to classification
problem, The Logistic Regression
Model, Interpreting the output of
Logistic Regression, Goodness of
Fit, Model Interpretation, Model
Performance.

8,9, 10 Introduction to Neural Networks: CO4 Lecture, Demonstration and

Structure of Neuron, Network Hands on Session
Architecture, Perceptron and its
types, Linear and Non-Linear
Problems,
Activations Functions, Feed forward
Neural Networks, Back Propagation
Algorithm.
11, 12, Unsupervised Learning: CO5 Lecture, Demonstration and
13 Clustering Hands on Session
Understanding the business scenario,
k- Means Clustering, Hierarchical
Clustering, Measuring Cluster

3
 Goodness, Cluster Identification.

14,15 Unsupervised Learning: CO5 Lecture, Demonstration and

Association Mining Hands on Session
Affinity Analysis, Market Basket
Analysis, A Prior Algorithm for
Association Mining.

Reference Texts/Books/Websites/etc:

Textbooks:
Sr No Name of the Book Author, Edition
1 Machine Learning using Python. Manoranjan Pradhan and U Dinesh
Kumar (2019), Wiley Publications
2 Machine Learning for Decision Sciences with Case Sumathi S., Rajappa, S., Ashok
Studies in Python. Kumar, Paneerselvam S (2022),
Taylor and Francis

Recommended Readings:
Sr No Title of the article Author
1 Business Analytics: The Science of Data-Driven U Dinesh Kumar. Wiley
Decision Making. Publications

2 Data Mining and Predictive Analytics. Daniel Larose, Chantal Larose,

Wiley

Evaluation Schedule
Evaluation Methodology % of marks The Course
assigned Outcome that it
will measure*
1. Quiz 10% CO1-CO5

2. Mid Term Evaluation: Assignment 30% CO2-CO3

3. End Term Evaluation: Project 60% CO4-CO5

End Term Evaluation

Project/Assignment Details, if any:
CO(s) Mapped to CO4-CO5
Project/Assignment
Objective/s of the To apply neural network and Unsupervised machine learning algo-
Project/Assignment rithms to gain business insights.
Assignment/Project Methodology Each Student has to select a data set and has to use Neural
Network and Unsupervised Machine Learning Algorithm to gain
business insights.
Outcome of the Presentation for Business Insights
Project/Assignment

4
Rubrics for Mid Term Assignment (30 marks)

1) There will be a practice assignment given to students at the end of selected sessions to practice
the skills learned during that session.
2) The students must complete the assignment and submit it before the next session.
3) Each assignment will carry 10 marks and the evaluation will be as below. The final marks will be
an average of the total marks scored in each of the assignments.

Evaluation Rubrics: Mid Term Evaluation- 30 Marks

Criteria Max Unsatisfactory Satisfactory Excellent
Marks
Choose the 10 No preprocessing Limited All the required
relevant data pre done. (1) preprocessing task preprocessing tasks done
processing done with valid appropriately with valid
techniques justifications (4) justification (5)

Inspect 8 Limited rationale to Reasonable Detailed rationale to

Supervised select algorithm rationale to select select algorithm/s.
Machine and no description algorithm/s. (3) Detailed description of
Learning of the working of the working of the
Algorithms the algorithm. algorithm (5)

Utilize the 7 Incomplete The complete The complete solution

selected solution and does solution executes executes without errors.
algorithm for not execute. but does not meet It meets all the
results and all the specifications. (5)
discussions specifications (2)
Presentation 5 Unable to Able to Able to communicate the
communicate in communicate the report in a proper
right manner (0) results in a proper manner; and also put
manner; however, forward the
fails to put forward recommendations to
the facilitate decision
recommendations making (3)
(2)

TLP submitted by Approved by

Teaching Faculty Program Head Head – Specialization
Name Dr. Tripti Mahara Dr. Madhumita Majumder Dr. Madhumita Majumder
Signature
Date 10/2/2024