FORE School of Management, New Delhi
Course Outline
Programme: PGDM(FMG-29/IMG-14/FM-03/BDA-01)
Name of the Course: Machine Learning with Python Credit: 3.0
Term: III Academic Year: 2020-2021
Faculty: Prof. Lalit K Jiwani Office Contact No.: 41242410
Email: lalit.jiwani@fsm.ac.in
Introduction: (Max 150 words)
The Artificial Intelligence (AI) is bringing a paradigm shift in the business and the way we live. It is
impacting and transforming every aspect of business and industry. The business world is increasingly
deploying and using data driven AI models in all industrial sectors. – in telecom, retail, finance,
manufacturing etc. Machine learning and deep learning - two broader areas of AI are driving this
revolution and these are thriving on the big data. This course introduces the new class of managers to
the foundation of Machine Learning (ML) in a very systematic manner using world’s favorite
computing language Python. Some of the models used will be K-Means clustering, Decision Tree and
Random Forrest based classification and regression, Neural Network based prediction and forecasting.
The course is completely practical in nature and each concept will be illustrated by solving business
problems in retail, bank, operation customer engagement etc. These will help student develop and deploy
agile data-driven processes and innovation.
Objective: (Max 50 words; bulleted preferred)
The goal of this course is learning to use and understand various machine learning models in a systematic
manner using Python to solve variety of business problems. Specifically, the objectives are:
- To introduce the fundamental concepts of machine learning and their applications.
- Choose a Right ML Model and parameters for a given business problem and processes
- Type of data it requires. Whether we can get or generate the data or not.
- Streamlining the Business Process, automation and What value it offers.
- Teach the student the skills needed to execute a smallish commercial project.
Prerequisite: This course assumes some prior basic working knowledge of two python libraries—
pandas and numpy. Students are encourage to discuss with the course faculty about this.
Text Book: (Please write complete citation)
Hands on Machine Learning with SciKit-Learn & Tensorflow by Aurelien Geron, O’Reilly Publications
Reference Book: (if any. Please write complete citation)
Required material will be provided during the course.
Pedagogy:
The course uses extensive hands-on using the programming language Python to explore data and
will be delivered through lecture, projects & presentation, and assignments. It will introduce
participants to use open-source machine learning libraries Scikit-learn, TensorFlow and Keras to
work with variety of dataset. The editing tools used will be ipython and Jupyter (a GUI for python).
Evaluation Component and weightage: (an indicative evaluation component guideline is
attached)
Team Project 10%
Assignment 15%
CP 5%
Quiz 10%
Mid Term 20%
End Term 40%
Total 100%
Session Plan:
Session(s) Topic/Session Theme Additional Reading/Cases/ Question to
Project(s) explore/Learning
(*see note on data sources below) outcome*
1-2 Introduction to Machine Understanding Machine
Learning, Data Exploration using Learning in the business
Python Provided during the course scenario
3 Classification and Regression and Supervised Learning
K-Nearest Neighborhood Problems -
Generalization,
Overfitting and Under
Provided during the course
fitting and an example
using using Supervised
Learning (Non
Parametric)
4 Linear Models and Prediction using
Regularization Techniques Supervised Learning
Provided during the course
5-6 Classification Analysis: Neural Developing Neural network Classification using
Network using Keras and Tensorflow basic Neural Network
7-8 Classification and Regression Predict Customer will return a Supervised Learning
Analysis: Decision Trees and loan or not. German Credit Problem
Random Forrest Dataset
Sales Dataset of Men's Understanding various
Measure of Proximity Fashion Stores metrics
9 - 10 Intellectual Property Rights By guest faculty Prof. S
(IPR) K Jain, IIT Delhi
11-12 Principal Component Analysis Provided during the course Unsupervised Learning
(PCA) and Feature Extraction Problem and Data
Reduction
13-14 Cluster Analysis: K-means and Clustering of credit card Unsupervised Learning
Agglomeration clustering holder Problem
15 minutes online quiz
15-16 Classification using XGBoost
Predict which calls will be Advanced tool for
cold: Car Insurance Cold Calls classification and
predictive analytics
17-18 Classification using CatBoost BNP Paribas Cardif Claims Advanced tool for
Management—Predict which classification of
claims can be processed faster categorical data
19-20 Students Project work Using ML and Big Data
presentation in class framework and methods
to solve a problem
Note on the Data Sources: Data for the projects will be taken from ‘Kaggle: The Home of Data Science’.
The data may be changed or updated during the class.
Note: Mid-Term and End-Term examination must be marked on a 100 max. marks basis
and the Component weight can be applied later.
For official use: -
As Benchmarked with course content in previous year, the contents of this course: (Please mark
the right option below)
(a) Is totally new
(b) Has not changed at all
(c) Has undergone less than/equal to 20% change
(d) Has undergone more than 20% change
Course Faculty Area Chair
Manager (Academics) Manager (Academics)
Dean (Academics)
