SCHOOL OF ADVANCED SCIENCES

M.Sc Data Science

(M.Sc MDT)

Curriculum
(2019-2020 onwards)
VISION STATEMENT OF VELLORE INSTITUTE OF TECHNOLOGY

Transforming life through excellence in education and research.

MISSION STATEMENT OF VELLORE INSTITUTE OF

TECHNOLOGY

World-class Education: Excellence in education, grounded in ethics and

critical thinking, for improvement of life.
Cutting edge Research: An innovation ecosystem to extend knowledge and
solve critical problems.
Impactful People: Happy, accountable, caring and effective workforce and
students.
Rewarding Co-creations: Active collaboration with national & international
industries & universities for productivity and economic development.
Service to Society: Service to the region and world through knowledge and
compassion.

VISION STATEMENT OF THE SCHOOL OF ADVANCED SCIENCES

To be an internationally renowned department in teaching, innovative research

and high impact publications toward addressing the current societal problems.

MISSION STATEMENT OF THE SCHOOL OF ADVANCED

SCIENCES

Our mission is to educate students from all over India, including those from the
local and rural areas, and from other countries, so they become enlightened
individuals, improving the living standards of their families, industry and
society. We will provide individual attention, world-class quality education and
take care of character building.

M.Sc. Data Science Page 2

 M.Sc Data Science
PROGRAMME EDUCATIONAL OBJECTIVES (PEOs)

1. Graduates will demonstrate proficiency with

statistical analysis of Data.

2. Graduates will execute statistical analyses with professional

statistical software.

3. Graduates will demonstrate skill in Data management.

4. Graduates will develop the ability to build and assess Data-

based models.

5. Graduates will apply data science concepts and methods

to solve problems in real-world contexts and
will communicate these solutions effectively

M.Sc. Data Science Page 3

 M.Sc Data Science

PROGRAMME OUTCOMES (POs)

PO_02: Having a clear understanding of the subject related concepts and

contemporary issues.

PO_06: Having problem-solving ability- to assess social issues (societal, health,

safety, legal and cultural) and engineering problems.
PO_08: Having a clear understanding of professional and ethical responsibility.
PO_09: Having cross-cultural competency exhibited by working as a member or
in teams.

PO_10: Having a good working knowledge of communicating in English –

communication with the engineering community and society.

M.Sc. Data Science Page 4

 M.Sc Data Science

ADDITIONAL PROGRAMME OUTCOMES (APOs)

APO_01: Having an ability to be socially intelligent with good SIQ (Social

Intelligence Quotient) and EQ (Emotional Quotient)

APO_04: Having computational thinking (Ability to translate vast data into

abstract concepts and to understand database reasoning

APO_05: Having Virtual Collaborating ability

APO_07: Having critical thinking and innovative skills

APO_08: Having a good digital footprint

M.Sc. Data Science Page 5

 M.Sc Data Science

PROGRAMME SPECIFIC OUTCOMES (PSOs)

On completion of M.Sc. Data Science programme, graduates will be

able to

 PSO1: To become a skilled Data Scientist in industry, academia, or

government.

 PSO2: To use specialist software tools for data storage, analysis

and visualization.

 PSO3: Able to independently carry out research/investigation to

solve practical problems

M.Sc. Data Science Page 6

 M.Sc Data Science

CREDIT STRUCTURE

Category-wise Credit distribution

Category Credits
University core (UC) 29
Programme core (PC) 23
Programme elective (PE) 22
University elective (UE) 06
Total credits 80

M.Sc. Data Science Page 7

 M.Sc. Data Science
DETAILED CURRICULUM
University Core

Course
S. No. Course Title L T P J C
Code

1 MAT5010 Foundations of Data Science 3 0 0 0 3

2 RES5001 Research Methodology 2 0 0 0 2
3 SET5001 Science, Engineering and Technology Project – I 0 0 0 0 2
4 SET5002 Science, Engineering and Technology Project – II 0 0 0 0 2
5 SET5003 Science, Engineering and Technology Project – III 0 0 0 0 2
6 MAT6099 Master's Thesis 0 0 0 0 14

ENG5003/ English for Science and Technology/ 0 0 4 0 2

7 FRE5001/ French/ 2 0 0 0 2
GER5001 German 2 0 0 0 2

8 STS4001 Essentials of Business Etiquettes-Soft Skills 3 0 0 0 1

9 STS4002 Preparing for Industry 3 0 0 0 1

M.Sc. Data Science Page 8

 M.Sc Data Science
Programme Core

S. No. Course Code Course Title L T P J C

1 MAT5011 Matrix Theory and Linear Algebra 3 0 0 0 3

2 MAT5012 Probability Theory and Distributions 3 0 2 0 4
3 MAT5013 Statistical Inference 3 0 2 0 4

Regression Analysis and Predictive

4 MAT6002 3 0 2 0 4
Models

5 MAT5016 Time series analysis and Forecasting 3 0 2 0 4

6 MAT5017 Multivariate Data Analysis 3 0 2 0 4

M.Sc. Data Science Page 9

 M.Sc Data Science
Programme Elective

Course
S. No. Course Title L T P J C
Code

1 MAT6003 Programming for Data Science 0 0 4 0 2

2 MAT6004 Computational Statistics for Data Science 0 0 4 0 2

3 MAT6005 Machine learning for Data Science 3 0 2 0 4

4 MAT6007 Deep learning 2 0 2 0 3

5 MAT6008 Artificial intelligence for Data Science 2 0 2 0 3

6 MAT6009 Design and Analysis of Experiments 3 0 2 0 4

7 MAT6010 Optimization Techniques 3 2 0 0 4

8 MAT6011 Statistical Quality Control 3 0 2 0 4

9 MAT6012 Programming for Data Analysis 2 0 4 0 4

10 MATXXXX Bio-Statistics 2 0 2 0 3

11 MATXXXX Reliability and Survival Analysis 2 0 2 0 3

12 MATXXXX Queuing Theory and Network Analysis 3 0 0 0 3

13 MATXXXX Stochastic Process and Applications 3 0 0 0 3

14 MATXXXX Statistical Computing for Data Analysis 0 0 4 0 2

15 MATXXXX Statistics for Managers 3 0 0 0 3

16 MATXXXX Data Mining and Information Security 2 0 0 4 3

17 MATXXXX Exploratory Data Analysis and Visualization 3 0 2 0 4
18 MATXXXX Actuarial statistics 2 2 0 0 3

M.Sc. Data Science Page 10

University Elective Baskets

S.No Code Title L T P J C

1 CSE5007 Exploratory Data Analysis 2 0 0 4 3

2 ECE6045 Neural Networks and Fuzzy systems 2 0 0 4 3

3 CSE6060 Statistical NLP 3 0 0 0 3

4 ITA5007 Data Mining and Business Intelligence 3 0 0 4 4

M.Sc. Data Science Page 11

 Course code Course Title L T P J C
MAT5010 Foundations of Data science 3 0 0 0 3
Pre-requisite Syllabus version
1.1
Course Objectives (CoB):
The course is aimed at

 Building the fundamentals of data science.

 Imparting design thinking capability to build big-data
 Developing design skills of models for big data problems
 Gaining practical experience in programming tools for data sciences
 Empowering students with tools and techniques used in data science

Expected Course Outcome (CO):

At the end of the course the student should be able to:

 Apply data visualisation in big-data analytics

 Utilise EDA, inference and regression techniques
 Utilize Matrix decomposition techniques to perform data analysis
 Apply data pre-processing techniques
 Apply Basic Machine Learning Algorithms

Student Learning Outcomes (SLO): 1,7,9,17,18

[1] Having an ability to apply mathematics and science in AI and machine learning
applications
[7] Having computational thinking (Ability to translate vast data into abstract
concepts and to understand database reasoning)
[9] Having problem-solving ability- solving social issues and engineering problems
[17] Having an ability to use techniques, skills and modern engineering
tools necessary for engineering practice
[18] Having critical thinking and innovative skills
Module:1 Introduction 4 hours
Big Data and Data Science - Big Data Analytics, Business intelligence vs Big data, big
data frameworks, Current landscape of analytics, data visualisation techniques,
visualisation software

Module:2 EDA 6 hours

Exploratory Data Analysis (EDA), statistical measures, Basic tools (plots, graphs and
summary statistics) of EDA, Data Analytics Lifecycle, Discovery

Module:3 Basic Statistical 6 hours

M.Sc. Data Science Page 12

 Inference
Developing Initial Hypotheses, Identifying Potential Data Sources, EDA case study,
testing hypotheses on means, proportions and variances

Module:4 Regression models 6 hours

Regression models: Simple linear regression, least-squares principle, MLR, logistic
regression, Multiple correlation, Partial correlation

Module:5 Linear Algebra Basics 6 hours

Matrices to represent relations between data, Linear algebraic operations on matrices –
Matrix decomposition: Singular Value Decomposition (SVD) and Principal Component
Analysis (PCA).

Module:6 Data Pre-processing 7 hours

and Feature Selection
Data cleaning - Data integration - Data Reduction - Data Transformation and Data
Discretization, Feature Generation and Feature Selection, Feature Selection
algorithms: Filters- Wrappers - Decision Trees - Random Forests

Module:7 Basic Machine 8 hours

Learning Algorithms
Classifiers - Decision tree - Naive Bayes - k-Nearest Neighbors (k-NN), k-means – SVM
Association Rule mining – Ensemble methods

Module:8 Expert Lecture 2 hours

Skillsets required for a Data Scientist

Total Lecture hours: 45 hours

Text Book(s)
 1Mining of Massive Datasets. v2.1, Jure Leskovek, Anand Rajaraman and Jefrey
.Ullman., Cambridge University Press. (2019). (free online)
 2Big Data Analytics, paperback 2 ed., Seema Acharya, Subhasini Chellappan,
nd

.Wiley (2019).
Reference Books
 Doing
1 Data Science, Straight Talk From The Frontline, Cathy O'Neil and Rachel
.
Schutt, O'Reilly (2014).
 Data
2 Mining: Concepts and Techniques”, Third Edition, Jiawei Han, Micheline
Kamber and Jian Pei, ISBN 0123814790,(2011).
 Big
3 Data and Business Analytics, Jay Liebowitz, CRC press (2013)
 Data
4 mining methods,2nd edition, C. Rajan, Narosa (2016)
Mode of Evaluation: CAT / Assignment / Quiz / FAT / Project / Seminar
Recommended by Board of 24-06-2020
Studies
Approved by Academic Council No. 59 Date 24-09-2020

M.Sc. Data Science Page 13

Course code Course Title L T P J C
ENG5003 English for Science and Technology 0 0 4 0 2
(for MCA & M.Sc., programmes)
Pre-requisite Cleared EPT Syllabus version
v. 1.1
Course Objectives:
 To enable students to communicate effectively in social, academic and professional contexts
thereby enhancing their interpersonal, managerial, problem-solving, and presentation skills.
 To facilitate students to develop their listening competency and critically evaluate and review
documentaries, talks and speeches.
 To Assist students to read and comprehend News Articles and Scientific Texts; effectively interpret
tables and graphs; write and proof-read official correspondences.

Expected Course Outcome:

 Make effective presentations and display their interpersonal skills in academic and professional
contexts.
 Emerge as good listeners and critically evaluate oral communication.
 Excel in reading, comprehending and interpreting technical reports, texts and data.
 Able to write effectively in English and also display their proof-reading abilities.
 Face real interviews and handle personal and professional conflicts effectively.

Student Learning Outcomes (SLO): 16, 18,20

16. Good working knowledge of communicating in English.
18. Critical thinking and innovative skills.
20. Having a good digital footprint.
Module:1 Career Goals 4hours
Short term and long term career goals
Activity: SWOT Analysis/ Comprehending speeches

Module:2 Interpersonal Skills 4 hours

Interpersonal Communication in/with Groups (Corporate Etiquette: Journey from Campus to corporate)
Activity: Role Plays/Mime/Skit

Module:3 Listening Skills 4 hours

Listening to Documentary
Activity: Critically evaluate/Review a documentary/TED Talk

Module:4 Reading Skills 4hours

Skimming, Scanning, Intensive & Extensive reading
Activity: Reading News Papers/Magazines/Scientific Texts

Module:5 Report Writing 4hours

Language and mechanics of writing report
Activity: Writing a Report/Mini Project

M.Sc. Data Science Page 14

Module:6 Study Skills 4hours
Summarizing the report
Activity: Abstract, Executive Summary, Digital Synopsis

Module:7 Interpreting skills 4hours

Interpret data in tables and graphs Activity: Transcoding

Module:8 Editing Skills 4hours

Proof Reading
Sequencing
Activity: Editing any given text

Module:9 Presentation Skills 4 hours

Oral Presentation using digital tools
Activity: Oral presentation on the given topic using appropriate non-verbal cues

Module:10 Group Discussion 4 hours

Intragroup interaction (avoid, accommodate, compete, compromise, collaborate)
Activity: Group discussion on a given topic

Module:11 Professional Skills 4 hours

Résumé Writing
Activity: Prepare an Electronic Résumé

Module:12 Skill-Gap Analysis 4 hours

Tailor your skills to suit the Job needs
Activity: Write a SoP for higher Studies/Purpose Statement for job

Module:13 Interview Skills 4 hours

Placement/Job Interview
Activity: Mock Interview

Module:14 Managerial Skills 4 hours

Official Meeting to organize events
Activity: Writing Agenda, Minutes of Meeting (video conferencing) and Organizing an event

Module:15 Problem Solving Skills 4 hours

Conflict Management & Decision Making
Activity: Case analysis of a challenging Scenario

Total Lecture hours: 60 hours

Text Book(s)
 Kuhnke, E. Communication Essentials For Dummies. (2015). First Edition. John Wiley &
Sons.
 Hewings, M. Advanced Grammar in Use Book with Answers and CD-ROM: A Self-Study
Reference and Practice Book for Advanced Learners of English. (2013). Third Edition.
Cambridge University Press. UK.
Reference Books

M.Sc. Data Science Page 15

  Churches, R. Effective Classroom Communication Pocketbook. Management Pocketbooks.
(2015). First Edition. USA.
 Wallwork, A. English for Writing Research Papers. (2016). Second Edition. Springer.
 Wood, J. T. Communication in Our Lives. (2016). Cengage Learning. Boston. USA.
 Anderson, C. TED Talks: The Official TED Guide to Public Speaking. (2016). First Edition.Boston.
Houghton Mifflin. New. York.
 Zinsser, William. On writing well. HarperCollins Publishers. 2016. Thirtieth Edition. New York.
Tebeaux, Elizabeth, and Sam Dragga. The essentials of Technical Communication. 2015. First
 Edition Oxford University Press. USA.
Mode of Evaluation: Mini Project, Flipped Class Room, Lecture, PPT’s, Role play, Assignments Class/Virtual
Presentations, Report and beyond the classroom activities

List of Challenging Experiments (Indicative)

1. Setting short term and long term goals 2 hours
2. Mime/Skit/ Activities through VIT Community Radio 6 hours
3. Critically evaluate / review a documentary/ Activities through VIT 4 hours
Community Radio
4. Mini Project 10 hours
5. Digital Synopsis 4 hours
6. Case analysis of a challenging Scenario 4 hours
7. Intensive & Extensive reading of Scientific Texts 4 hours
8. Editing any given text 8 hours
9. Group discussion on a given topic / Activities through VIT Community 8 hours
Radio
10. Prepare a video résumé along with your video introduction and then 10 hours
create a website (in Google Sites/Webly/Wix) showcasing skills and
achievements.
Total Laboratory Hours 60 hours
Mode of evaluation: Mini Project, Flipped Class Room, Lecture, PPT’s, Role play, Assignments Class/Virtual
Presentations, Report and beyond the classroom activities
Recommended by Board of Studies 22-07-2017
Approved by Academic Council No. 47 Date 24.08.2017

M.Sc. Data Science Page 16

Course code Course title L T P J C
FRE5001 Francais Fonctionnel 2 0 0 0 2
Pre-requisite Syllabus version
Nil v.1
Course Objectives:
The course gives students the necessary background to:
 demonstrate competence in reading, writing, and speaking basic French, including knowledge of
vocabulary (related to profession, emotions, food, workplace, sports/hobbies, classroom and
family).
 achieve proficiency in French culture-oriented viewpoint.

Expected Course Outcome: Students will be able to

 Remember the daily life communicative situations via personal pronouns, emphatic pronouns,
salutations, negations, interrogations etc.
 Create communicative skill effectively in the French language via regular/irregular verbs.
 Demonstrate comprehension of the spoken/written language in translating simple sentences.
 Understand and demonstrate the comprehension of some particular new range of unseen written
materials.
 Demonstrate a clear understanding of the French culture through the language studied.

Student Learning Outcomes (SLO): 9, 10

9 Having problem-solving ability- solving social issues and engineering problems
10 Having a clear understanding of professional and ethical responsibility
Module:1 Saluer, Se présenter, Etablir des contacts 3 hours
Les Salutations, Les nombres (1-100), Les jours de la semaine, Les mois de l’année, Les Pronoms Sujets,
Les Pronoms Toniques, La conjugaison des verbes réguliers, La conjugaison des verbes irréguliers- avoir /
être / aller / venir / faire etc.

Module:2 Présenter quelqu’un, Chercher un(e) 3 hours

correspondant(e), Demander des nouvelles d’une
personne.

La conjugaison des verbes Pronominaux, La Négation,

L’interrogation avec ‘Est-ce que ou sans Est-ce que’.

Module:3 Situer un objet ou un lieu, Poser des questions 4 hours

L’article (défini/ indéfini), Les prépositions (à/en/au/aux/sur/dans/avec etc.), L’article contracté, Les
heures en français, La Nationalité du Pays, L’adjectif (La Couleur, l’adjectif possessif, l’adjectif
démonstratif/ l’adjectif interrogatif (quel/quelles/quelle/quelles), L’accord des adjectifs avec le nom,
L’interrogation avec Comment/ Combien / Où etc.,

Module:4 Faire des achats, Comprendre un texte court, 6 hours

Demander et indiquer le chemin.
La traduction simple :(français-anglais / anglais –français)

Module:5 Trouver les questions, Répondre aux questions 5 hours

M.Sc. Data Science Page 17

 générales en français.
L’article Partitif, Mettez les phrases aux pluriels, Faites une phrase avec les mots donnés, Exprimez les
phrases données au Masculin ou Féminin, Associez les phrases.

Module:6 Comment ecrire un passage 3 hours

Décrivez :
La Famille /La Maison, /L’université /Les Loisirs/ La Vie quotidienne etc.

Module:7 Comment ecrire un dialogue 4 hours

Dialogue:
a) Réserver un billet de train
b) Entre deux amis qui se rencontrent au café
c) Parmi les membres de la famille
d) Entre le client et le médecin

Module:8 Invited Talk: Native speakers 2 hours

Total Lecture hours: 30 hours

Text Book(s)
 Echo-1,
1 Méthode de français, J. Girardet, J. Pécheur, Publisher CLE International, Paris 2010.
.
 2 Echo-1, Cahier d’exercices, J. Girardet, J. Pécheur, Publisher CLE International, Paris 2010.
Reference Books
 CONNEXIONS
1 1, Méthode de français, Régine Mérieux, Yves Loiseau,Les Éditions Didier, 2004.
.
 CONNEXIONS
2 1, Le cahier d’exercices, Régine Mérieux, Yves Loiseau, Les Éditions Didier, 2004.

 ALTER
3 EGO 1, Méthode de français, Annie Berthet, Catherine Hugo, Véronique M. Kizirian, Béatrix
Sampsonis, Monique Waendendries , Hachette livre 2006.

Mode of Evaluation: CAT / Assignment / Quiz / FAT

Recommended by Board of Studies 26-2-2016
Approved by Academic Council No 41 Date 17-6-2016

M.Sc. Data Science Page 18

Course code Course title L T P J C
GER5001 Deutsch für Anfänger 2 0 0 0 2
Pre-requisite NIL Syllabus version
v.1
Course Objectives:
The course gives students the necessary background to:
 enable students to read and communicate in German in their day to day life
 become industry-ready
 make them understand the usage of grammar in the German Language.

Expected Course Outcome: Students will be able to

 Create the basics of the German language in their day to day life.
 Understand the conjugation of different forms of regular/irregular verbs.
 Understand the rule to identify the gender of the Nouns and apply articles appropriately.
 Apply the German language skill in writing corresponding letters, E-Mails etc.
 Create the talent of translating passages from English-German and vice versa and to frame simple
dialogues based on given situations.

Student Learning Outcomes (SLO): 9, 10

9. Having problem-solving ability- solving social issues and engineering problems
10. Having a clear understanding of professional and ethical responsibility
Module:1 3 hours
Einleitung, Begrüssungsformen, Landeskunde, Alphabet, Personalpronomen, Verb Konjugation, Zahlen (1-
100), W-fragen, Aussagesätze, Nomen – Singular und Plural
Lernziel:
Elementares Verständnis von Deutsch, Genus- Artikelwörter

Module:2 3 hours
Konjugation der Verben (regelmässig /unregelmässig) die Monate, die Wochentage, Hobbys, Berufe,
Jahreszeiten, Artikel, Zahlen (Hundert bis eine Million), Ja-/Nein- Frage, Imperativ mit Sie
Lernziel :
Sätze schreiben, über Hobbys erzählen, über Berufe sprechen usw.

Module:3 4 hours
Possessivpronomen, Negation, Kasus- AkkusatitvundDativ (bestimmter, unbestimmterArtikel), trennnbare
verben, Modalverben, Adjektive, Uhrzeit, Präpositionen, Mahlzeiten, Lebensmittel, Getränke
Lernziel :
Sätze mit Modalverben, Verwendung von Artikel, über Länder und Sprachen sprechen, über eine
Wohnung beschreiben.

Module:4 6 hours
Übersetzungen : (Deutsch – Englisch / Englisch – Deutsch)
Lernziel :
Grammatik – Wortschatz – Übung

M.Sc. Data Science Page 19

Module:5 5 hours
Leseverständnis,Mindmap machen,Korrespondenz- Briefe, Postkarten, E-Mail
Lernziel :
Wortschatzbildung und aktiver Sprach gebrauch

Module:6 . 3 hours
Aufsätze :
Meine Universität, Das Essen, mein Freund oder meine Freundin, meine Familie, ein Fest in Deutschland
usw

Module:7 4 hours
Dialoge:
e) Gespräche mit Familienmitgliedern, Am Bahnhof,
f) Gespräche beim Einkaufen ; in einem Supermarkt ; in einer Buchhandlung ;
g) in einem Hotel - an der Rezeption ;ein Termin beim Arzt.
Treffen im Cafe

Module:8 2 hours
Guest Lectures/Native Speakers / Feinheiten der deutschen Sprache, Basisinformation über die
deutschsprachigen Länder
Total Lecture hours: 30 hours

Text Book(s)
 Studio
1 d A1 Deutsch als Fremdsprache, Hermann Funk, Christina Kuhn, Silke Demme : 2012
.
Reference Books
 Netzwerk
1 Deutsch als Fremdsprache A1, Stefanie Dengler, Paul Rusch, Helen Schmtiz, Tanja Sieber,
2013
 Lagune
2 ,Hartmut Aufderstrasse, Jutta Müller, Thomas Storz, 2012.
 Deutsche
3 SprachlehrefürAUsländer, Heinz Griesbach, Dora Schulz, 2011
 ThemenAktuell
4 1, HartmurtAufderstrasse, Heiko Bock, MechthildGerdes, Jutta Müller und Helmut
Müller, 2010
www.goethe.de
wirtschaftsdeutsch.de
hueber.de, klett-sprachen.de
www.deutschtraning.org
Mode of Evaluation: CAT / Assignment / Quiz / FAT
Recommended by Board of Studies 04-03-2016
Approved by Academic Council No. 41 Date 17-06-2016

M.Sc. Data Science Page 20

 Course code Course title L T P J C
STS4001 Essentials of Business Etiquettes 3 0 0 0 1
Pre-requisite Syllabus version
v2
Course Objectives:
 To develop the students’ logical thinking skills
 To learn the strategies of solving quantitative ability problems
 To enrich the verbal ability of the students
 To enhance critical thinking and innovative skills

Expected Course Outcome:

 Enabling students to use relevant aptitude and appropriate language to express themselves
 To communicate the message to the target audience clearly

Student Learning Outcomes (SLO): 7, 9

7. Having Computational thinking (Ability to translate vast data into abstract concepts and to understand
database reasoning)

9. Having problem-solving ability- solving social issues and engineering problems

Module:1 Business Etiquette: Social and Cultural Etiquette 9 hours

and Writing Company Blogs and Internal
Communications and Planning and Writing press
release and meeting notes

Value, Manners, Customs, Language, Tradition, Building a blog, Developing brand message, FAQs', Assessing
Competition, Open and objective Communication, Two-way dialogue, Understanding the audience,
Identifying, Gathering Information, Analysis, Determining, Selecting plan, Progress check, Types of planning,
Write a short, catchy headline, Get to the Point –summarize your subject in the first paragraph., Body –
Make it relevant to your audience,

Module:2 Study skills – Time management skills 3 hours

Prioritization, Procrastination, Scheduling, Multitasking, Monitoring, Working under pressure and adhering to
deadlines

Module:3 Presentation skills – Preparing presentation and 7 hours

Organizing materials and Maintaining and
preparing visual aids and Dealing with questions
10 Tips to prepare PowerPoint presentation, Outlining the content, Passing the Elevator Test, Blue sky
thinking, Introduction, body and conclusion, Use of Font, Use of Color, Strategic presentation, Importance
and types of visual aids, Animation to captivate your audience, Design of posters, Setting out the ground
rules, Dealing with interruptions, Staying in control of the questions, Handling difficult questions

Module:4 Quantitative Ability -L1 – Number properties and 11 hours

Averages and Progressions and Percentages and

M.Sc. Data Science Page 21

 Ratios

Number of factors, Factorials, Remainder Theorem, Unit digit position, Tens digit position, Averages,
Weighted Average, Arithmetic Progression, Geometric Progression, Harmonic Progression, Increase &
Decrease or successive increase, Types of ratios and proportions

Module:5 Reasoning Ability-L1 – Analytical Reasoning 8 hours

Data Arrangement(Linear and circular & Cross Variable Relationship), Blood Relations,
Ordering/ranking/grouping, Puzzle test, Selection Decision table

Module:6 Verbal Ability-L1 – Vocabulary Building 7 hours

Synonyms & Antonyms, One-word substitutes, Word Pairs, Spellings, Idioms, Sentence completion,
Analogies

Total Lecture hours: 45 hours

Reference Books
1. Kerry Patterson, Joseph Grenny, Ron McMillan, Al Switzler(2001) Crucial Conversations: Tools for
Talking When Stakes are High. Bangalore. McGraw‐Hill Contemporary
2. Dale Carnegie,(1936) How to Win Friends and Influence People. New York. Gallery Books
3. Scott Peck. M(1978) Road Less Travelled. New York City. M. Scott Peck.
4. FACE(2016) Aptipedia Aptitude Encyclopedia. Delhi. Wiley publications
5. ETHNUS(2013) Aptimithra. Bangalore. McGraw-Hill Education Pvt. Ltd.
Websites:
1. www.chalkstreet.com
2. www.skillsyouneed.com
3. www.mindtools.com
4. www.thebalance.com
5. www.eguru.ooo
Mode of Evaluation: FAT, Assignments, Projects, Case studies, Roleplays,
3 Assessments with Term End FAT (Computer Based Test)

Recommended by Board of Studies 09/06/2017

Approved by Academic Council No. 45th AC Date 15/06/2017

M.Sc. Data Science Page 22

Course code Course title L T P J C

STS4002 Preparing for Industry 3 0 0 0 1

Pre-requisite Syllabus version

v2
Course Objectives:
 To develop the students’ logical thinking skills
 To learn the strategies of solving quantitative ability problems
 To enrich the verbal ability of the students
 To enhance critical thinking and innovative skills

Expected Course Outcome:

 Enabling students to simplify, evaluate, analyze and use functions and expressions to simulate
real situations to be industry-ready.

Student Learning Outcomes (SLO): 9, 10

9. Having problem-solving ability- solving social issues and engineering problems
10. Having a clear understanding of professional and ethical responsibility
Module:1 Interview skills – Types of interview and 3 hours
Techniques to face remote interviews and Mock
Interview

Structured and unstructured interview orientation, Closed questions and hypothetical questions,
Interviewers’ perspective, Questions to ask/not ask during an interview, Video interview¸ Recorded
feedback, Phone interview preparation, Tips to customize preparation for personal interview, Practice
rounds

Module:2 Resume skills – Resume Template and Use of 2 hours

power verbs and Types of resume and Customizing
resume

Structure of a standard resume, Content, color, font, Introduction to Power verbs and Write up, Quiz on
types of resume, Frequent mistakes in customizing resume, Layout - Understanding different company's
requirement, Digitizing career portfolio

Module:3 Emotional Intelligence - L1 – Transactional Analysis 12 hours

and Brain storming and Psychometric Analysis and
Rebus Puzzles/Problem Solving
Introduction, Contracting, ego states, Life positions, Individual Brainstorming, Group Brainstorming,
Stepladder Technique, Brain writing, Crawford's Slip writing approach, Reverse brainstorming, Star
bursting, Charlette procedure, Round robin brainstorming, Skill Test, Personality Test, More than one
answer, Unique ways

Module:4 Quantitative Ability-L3 – Permutation- 14 hours

Combinations and Probability and Geometry and
mensuration and Trigonometry and Logarithms and
Functions and Quadratic Equations and Set Theory

M.Sc. Data Science Page 23

Counting, Grouping, Linear Arrangement, Circular Arrangements, Conditional Probability, Independent
and Dependent Events, Properties of Polygon, 2D & 3D Figures, Area & Volumes, Heights and distances,
Simple trigonometric functions, Introduction to logarithms, Basic rules of logarithms, Introduction to
functions, Basic rules of functions, Understanding Quadratic Equations, Rules & probabilities of Quadratic
Equations, Basic concepts of Venn Diagram

Module:5 Reasoning ability-L3 – Logical reasoning and Data 7 hours

Analysis and Interpretation

Syllogisms, Binary logic, Sequential output tracing, Crypto arithmetic, Data Sufficiency, Data
interpretation-Advanced, Interpretation tables, pie charts & bar chats

Module:6 Verbal Ability-L3 – Comprehension and Logic 7 hours

Reading comprehension, Para Jumbles, Critical Reasoning (a) Premise and Conclusion, (b) Assumption &
Inference, (c) Strengthening & Weakening an Argument
Total Lecture hours: 45 hours

Reference Books
 1Michael Farra and JIST Editors(2011) Quick Resume & Cover Letter Book: Write and Use an
. Effective Resume in Just One Day. Saint Paul, Minnesota. Jist Works
 2Daniel Flage Ph.D(2003) The Art of Questioning: An Introduction to Critical Thinking. London.
. Pearson
 3David Allen( 2002) Getting Things done : The Art of Stress -Free productivity. New York City.
. Penguin Books.
 4FACE(2016) Aptipedia Aptitude Encyclopedia.Delhi. Wiley publications
.
 5ETHNUS(2013) Aptimithra. Bangalore. McGraw-Hill Education Pvt. Ltd.
.

Websites:
1. www.chalkstreet.com
2. www.skillsyouneed.com
3. www.mindtools.com
4. www.thebalance.com
5. www.eguru.ooo
Mode of Evaluation: FAT, Assignments, Projects, Case studies, Role plays,
3 Assessments with Term End FAT (Computer Based Test)

Recommended by Board of Studies 09/06/2017

Approved by Academic Council No. 45th AC Date 15/06/2017

M.Sc. Data Science Page 24

Course code Course title L T P J C

SET 5001 Science, Engineering and Technology Project– I 0 0 0 0 2

Pre-requisite Syllabus Version
Anti-requisite v1.10
Course Objectives:
 To provide opportunity to involve in research related to science / engineering
 To inculcate research culture
 To enhance the rational and innovative thinking capabilities

Expected Course Outcome: Student will be able to

 Identify a research problem and carry out literature survey
 Analyse the research gap and formulate the problem
 Interpret the data and synthesize research findings
 Report research findings in written and verbal forms
Student Learning Outcomes : 5, 6, 9 & 20

Modalities / Requirements
1. Individual or group projects can be taken up
2. Involve in literature survey in the chosen field
3. Use Science/Engineering principles to solve identified issues
4. Adopt relevant and well-defined / innovative methodologies to fulfill the specified objective
5. Submission of scientific report in a specified format (after plagiarism check)

Student Assessment : Periodical reviews, oral/poster presentation

Recommended by Board of Studies 17-08-2017
Approved by Academic Council No. 47 Date 05-10-2017

M.Sc. Data Science Page 25

Course Code Course title L T P J C

SET 5002 Science, Engineering and Technology Project– II 0 0 0 0 2

Pre-requisite Syllabus Version
Anti-requisite v1.10
Course Objectives:
 To provide an opportunity to involve in research related to science/engineering
 To inculcate research culture
 To enhance the rational and innovative thinking capabilities

Expected Course Outcome: Student will be able to

 Identify a research problem and carry out a literature survey
 Analyse the research gap and formulate the problem
 Interpret the data and synthesize research findings
 Report research findings in written and verbal forms
Student Learning Outcomes : 5, 6, 9 & 20

Modalities / Requirements
6. Individual or group projects can be taken up
7. Involve in literature survey in the chosen field
8. Use Science/Engineering principles to solve identified issues
9. Adopt relevant and well-defined / innovative methodologies to fulfill the specified objective
10. Submission of scientific report in a specified format (after plagiarism check)

Student Assessment : Periodical reviews, oral/poster presentation

Recommended by Board of Studies 17-08-2017
Approved by Academic Council No. 47 Date 05-10-2017

M.Sc. Data Science Page 26

Course Code Course title L T P J C

SET 5003 Science, Engineering and Technology Project– III 0 0 0 0 2

Pre-requisite Syllabus Version
Anti-requisite v1.10
Course Objectives:
 To provide an opportunity to involve in research related to science/engineering
 To inculcate research culture
 To enhance the rational and innovative thinking capabilities

Expected Course Outcome: Student will be able to

 Identify a research problem and carry out a literature survey
 Analyse the research gap and formulate the problem
 Interpret the data and synthesize research findings
 Report research findings in written and verbal forms
Student Learning Outcomes : 5, 6, 9 & 20

Modalities / Requirements
11. Individual or group projects can be taken up
12. Involve in the literature survey in the chosen field
13. Use Science/Engineering principles to solve identified issues
14. Adopt relevant and well-defined/innovative methodologies to fulfil the specified objective
15. Submission of a scientific report in a specified format (after plagiarism check)

Student Assessment: Periodical reviews, oral/poster presentation

Recommended by Board of Studies 17-08-2017
Approved by Academic Council No. 47 Date 05-10-2017

M.Sc. Data Science Page 27

Course Code Course title L T P J C
RES5001 Research Methodology 2 0 0 0 2
Pre-requisite Nil Syllabus version
v. 1.0
Course Objectives:
 Impart skills to develop a research topic and design
 Define a purpose statement, a research question or hypothesis, and a research objective
 Analyze the data and arrive at a valid conclusion
 4. Compile and present research findings

Expected Course Outcome: student will be able to

 Explain the basic aspects of research and its ethics
 Outline research problems, their types and objectives
 Formulate good research designs and carry out statistically relevant sampling
 Collect, collate, analyze and interpret data systematically
 Experiment with animals ethically
 Make use of literature and other search engines judiciously for research purposes

Student Learning Outcomes (SLO): 2,8

2. Having a clear understanding of the subject related concepts and of contemporary issues
8. Having Virtual Collaborating ability
Module:1 Introduction and Foundation of Research 2 hours
Meaning, Objectives, Motivation, Utility for research. Concept of theory, empiricism, deductive
and inductive theory. Characteristics of scientific method –Understanding the language of research.

Module:2 Problem identification and formulation 4 hours

Scientific Research: Problem, Definition, Objectives, Types, Purposes and components of
Research problem

Module:3 Research Design 4 hours

Concept and Importance in Research : Features of a good research design, Exploratory
Research Design and Descriptive Research Designs

Module:4 Sampling 6 hours

Sampling methods, Merits and Demerits. Observation methods, Sampling Errors (Type I and Type II).
Determining size of the sample. Experimental Design: Concept of Independent &
Dependent variables.

Module:5 Data analysis and Reporting 6 hours

Fundamentals of Statistical Analysis and Inference, Multivariate methods, Concepts of
Correlation and Regression; Research Reports: Structure, Components, Types and Layout of
Research report and articles, Writing and interpreting research results, Figures and Graphs

Module:6 Animal handling 2 hours

Guidelines-animal ethical committee, animal models, various routes of drug administrations,
LD50, ED50

M.Sc. Data Science Page 28

Module:7 Use of encyclopedias and tools in research 4 hours
Research Guides, Handbook, Academic Databases for Biological Science Discipline. Methods to search
required information effectively.

Module:8 Contemporary issues: 2 hours

Total Lecture hours: 30 hours

Text Book(s)
 Catherine
1 Dawson, Introduction to research methods : a practical guide for anyone undertaking
a. research project, Oxford : How To Books, Reprint 2010
 Julius
2 S. Bendat, Allan G. Piersol, Random Data: Analysis and Measurement Procedures,
4.thEdition, ISBN: 978-1-118-21082-6, 640 pages, September 2011

 Research
3 in Medical and Biological Sciences, 1st Edition, From Planning and Preparation to
Grant
. Application and Publication, Editos: Petter Laake Haakon Benestad Bjorn Olsen,
ISBN: 9780128001547, Academic Press, March 2015
Reference Books
 John
1 Creswell, Research Design: Qualitative, Quantitative, and Mixed Methods
Approaches,
. Fourth Edition (March 14, 2013)
Mode of Evaluation: CAT / Assignment / Quiz / FAT / Project / Seminar

Recommended by Board of Studies 03-08-2017

Approved by Academic Council No. 46 Date 24-08-2017

M.Sc. Data Science Page 29

Course Code Course title L T P J C
MAT6099 Master’s Thesis 0 0 0 0 14
Pre-requisite As per the academic regulations Syllabus version
v 1.0
Course Objectives:
To provide sufficient hands-on learning experience related to the area of specialization with a focus
on research orientation

Expected Course Outcome: Students will be able to

 Formulate specific problem statements for ill-defined real-life problems with reasonable
assumptions and constraints.
 Perform a literature search and/or patent search in the area of interest.
 Develop a suitable solution methodology for the problem
 Conduct experiments / Design & Analysis / solution iterations and document the results
 Perform error analysis / benchmarking/costing
 Synthesise the results and arrive at scientific conclusions/products/solution
 Document the results in the form of technical report/presentation
Student Learning Outcomes (SLO): 5, 6 & 20

1. Can be a theoretical analysis, modelling & simulation, experimentation & analysis, prototype
design, correlation and analysis of data, software development, applied research and any
other related activities.
2. The project can be for one or two semesters based on the completion of the required
number of credits as per the academic regulations.
3. Should be individual work.
4. Carried out inside or outside the university, in any relevant industry or research institution.
5. Publications in the peer-reviewed journals / International Conferences will be an added
advantage

Mode of Evaluation: Periodic reviews, Presentation, Final oral viva, Poster submission

Recommended by Board of Studies 04.03.2016

Approved by Academic Council 40thAC Date 18.03.2016

M.Sc. Data Science Page 30

 Programme Core
Course code Course title L T P J C
MAT 5011 Matrix theory and Linear Algebra 3 0 0 0 3
Pre-requisite Syllabus version
1.1
Course Objectives:
 Understand the basic concepts of matrix algebra and its applications.
 Solving computational problems of linear algebra.

Expected Course Outcomes:

At the end of the course students will be able to:
 Understand basic matrix properties like rank, determinant, inverse and a special type of
matrices
 Introduce Gaussian / Gauss-Jordan elimination methods, LU factorisation technique
 Use computational techniques for singular value decomposition (Computational and
Algebraic Skills).
 Understand the concepts of vector space and subspaces.
 Find the matrix representation of a linear transformation given bases of the relevant
vector spaces.
 Compute inner products on a real vector space and compute angle and orthogonality in
inner product spaces.
 Understand the use of linear algebra and matrices in several important, modern
applications of research and industrial problems involving statistics.
Student Learning Outcomes (SLO): 2, 7, 9
2. Having a clear understanding of the subject related concepts and contemporary issues.
7. Having computational thinking (Ability to translate vast data into abstract concepts and to
understand database reasoning).
9. Having problem-solving ability- solving social issues and engineering problems.
Module: 1 Matrix theory 6 hours
Algebra of Matrices, Trace and Rank of a Matrix and their properties, Determinants, Inverse,
Eigen values and Eigen vectors, symmetric, orthogonal and idempotent matrices and their
properties
Module:2 Matrix Factorization 6 hours
Gauss elimination, row canonical form, diagonal form, triangular form, Gauss-Jordan-LU
decomposition, solving systems of linear equations.
Module:3 Decomposition of Matrices 6 hours
Spectral decomposition, singular value decomposition, Quadratic forms, definiteness and related
results with proofs.
Module:4 Vector Spaces 6 hours
Vector Spaces, Subspaces, Basis and dimension of a vector space, linear dependence and linear
independence, spanning set.
Module:5 Linear transformation 6 hours
Linear transformation, kernel, range, Matrix Representation of a linear transformation, rank-
nullity theorem, change of basis and similar matrices.

M.Sc. Data Science Page 31

Module:6 Inner product spaces 6 hours
Inner-product spaces, orthogonal sets and bases, Orthogonal Projection, Gram-Schmidt
orthogonalization process.
Module:7 Applications in Statistics 7 hours
Generalized inverses (g-inverses), Methods of constructing g-inverses, general solution to a
system of linear equations. Sparse matrices, Linear Discriminant Analysis and Canonical
Correlation Analysis.
Module:8 Contemporary issues: ( Industry Expert 2 hours
Lecture)
Applications into linear models, Regression analysis and Multivariate analysis using computer
software packages.
Total Lecture hours: 30 hours

Tutorial  A minimum of 5 problems to be 15 hours

worked out by student in every
tutorial class.
 Another 5 problems per tutorial class
to be given as home work.
Text Book(s)
 Gilbert Strang, Introduction to linear algebra, 5/e., Wellesley-Cambridge, 2016.
 David C. Lay, Linear Algebra and Its Applications, Pearson, 5/e 2019.
Reference Book(s)
 G. Allaire and S. M. Kaber. Numerical Linear Algebra, Texts in Applied Mathematics,
Springer, 2008.
 L. Hogben, Handbook of Linear Algebra, CRC Press/Taylor & Francis Group, 2014.
 Friedberg, S., Insel, A., and Spence, L., Linear Algebra, 5/e, Pearson, 2019.
 Nick Fieller, "Basics of Matrix Algebra for Statistics with R", published in 2015, CRC
Press
Mode of Evaluation: CAT, Quiz, Assignment and FAT.

Recommended by Board of Studies 24-06-2020

Approved by Academic Council No. 59 Date 24-09-2020

M.Sc. Data Science Page 32

Course code Course title L T P J C
MAT5012 Probability Theory and Distributions 3 0 2 0 4
Pre-requisite Basic knowledge of sets, sample space, probability space, Syllabus version
measure space, probability measure and calculus.
1.1
Course Objectives:
 To incorporate the concepts of probability theory and its applications as the core material in
building theoretical ideas along with the practical notion.
 To integrate the intrinsic ideas of preliminary and advanced distributions to correlate with the real-
world scenarios.
Expected Course Outcome:
At the end of the course student will be able to:
 Develop problem-solving techniques needed to calculate probability and conditional probability.
 Formulate fundamental probability distribution and density functions, as well as functions of
random variables, derive the probability density function of transformations.
 Derive the expectation and conditional expectation, and describe their properties.
 Understand various types of generating functions used in statistics.
 Describe commonly used univariate discrete and continuous probability distributions.
 Apply sampling distributions to testing of hypotheses.
 Translate and correlate the statistical problems into Statistical analysis
Student Learning Outcomes (SLO): 2, 7, 9, 18
[2] Having a clear understanding of the subject related concepts and contemporary issues
[7] Having computational thinking (Ability to translate vast data into abstract concepts and to
understand database reasoning)
[9] Having problem-solving ability- solving social issues and engineering problems
[18] Having critical thinking and innovative skills
Module:1 Probability and Random variables 8 hours
Introduction – Random Experiments, Empirical basis of probability, Algebra of events, laws of
probability; Conditional Probability, Independence, Bayes’ law; Application of probability to business
and economics. One-dimensional Random variable- Discrete and Continuous; Distribution functions and its
properties; Bivariate Random Variables- Joint Probability functions, marginal distributions, conditional
distribution functions; Notion of Independence of Random variables
Module:2 Functions of Random Variables 6 hours
Functions of random variables: introduction, distribution function technique, transformation
technique: one variable, transformation technique: several variables, theory and applications.
Module:3 Mathematical Expectation 6 hours
Expectation, Variance, and Co-variance of random variables; Conditional expectation and
conditional variance; Markov, Holder, Jensen and Chebyshev’s Inequality; Weak Law of Large
numbers, Strong law of large numbers and Kolmogorov theorem; Central Limit Theorem.
Module:4 Generating Functions 5 hours
Probability generating function (p.g.f.), moment generating function (m.g.f.), characteristic function
(c.f.) ; Properties and Applications. Probability distributions of functions of random variables: one and
two dimensions.

M.Sc. Data Science Page 33

Module:5 Discrete Distributions 7 hours
Bernoulli, Binomial, Poisson, Geometric, Hypergeometric, Negative Binomial, Multinomial,
distributions and Discrete Uniform distribution - definition, properties and applications with numerical
problems.
Module:6 Continuous Distributions 7 hours
Uniform, Normal distribution function, Exponential, Gamma, Beta distributions (First and Second
kind), Weibull, Cauchy and Laplace distributions, lognormal, logistic, Pareto and Rayleigh
distribution functions - definition, properties and applications; concept of truncated distributions.
Module:7 Sampling Distributions 4 hours
Introduction, The sampling distribution of the Mean: Finite Populations, Sampling distribution of the
proportion: Finite Populations, distribution of sample variance, the chi-square distribution, the t
distribution, the F distribution, order statistics: properties, and applications, procedure of hypothesis
testing.
Module:8 Contemporary issues (Industry Expert Lecture) 2 hours
Research and Analytical problems on various applications of the distribution functions with computer
software packages.
Total Lecture hours: 45 hours

Text Book(s)
 1Sheldon Ross; A First Course in Probability, Pearson, 2014.
.Parimal Mukhopadhyay; An Introduction to the Theory of Probability, World scientific, 2012.
 Irwin Miller, Marylees Miller, John E. Freund’s; Mathematical Statistics, Pearson, 2017
3
.
Reference Book(s)
 1FetsjeBijma, Marianne Jonker and Aad van der Vaart; Introduction to Mathematical Statistics,
. Amsterdam University Press, 2018.
 Krishnamoorthy, K., Handbook of Statistical Distributions with Applications, Chapman &
2Hall/CRC, 2006. nd
. Rohatgi, V.K. and Ebsanes Saleh, A.K. Md., An introduction to Probability and Statistics, 2 Ed.,
 John Wiley & Sons, 2002.
Shanmugam, R., Chattamvelli, R. Statistics for scientists and engineers, John Wiley, 2015.
4
.

Mode of Evaluation: CAT, Quiz, Assignment and FAT.

List of Challenging Experiments (Indicative): Using Computational software’s like MS-Excel/MS-
Solver/R/Python/Minitab etc.
Introduction to computational procedure, import and export of data, data
1. processing, tabulation and visualization of data and charts, Diagrammatical 4 hours
Presentation of data.
2. Various plots and graphical Presentation of Statistical Data 4 hours
3. Computation of descriptive Statistics and summarizing the data 4 hours
Computational methods of discrete distributions and generating random 2 hours
4.
numbers using standard distributions.

M.Sc. Data Science Page 34

 Normal distribution : calculation of probabilities, fitting of normal data and 4 hours
5.
related applications
Binomial distribution: Calculation of probabilities, fitting of binomial data and 4 hours
6.
related applications on real time data.
Poisson distribution: Calculation of probabilities, fitting of Poisson data and 2 hours
7.
related applications on real time data.
Exponential distribution: Calculation of probabilities, fitting of exponential 2 hours
8.
data and related applications on real time data.
Gamma distribution: Calculation of probabilities, fitting of Gamma data and 2 hours
9.
related applications on real time data.
10. Beta distribution: Calculation of probabilities, fitting of Beta data and related 2 hours
applications on real time data.
Total Laboratory hours 30 hours
Mode of evaluation: Continuous assessment and FAT.
Recommended by Board of Studies 24-06-2020
Approved by Academic Council No. 59 Date 24-09-2020

M.Sc. Data Science Page 35

 Course code Course title L T P J C
MAT5013 Statistical Inference 3 0 2 0 4
Pre-requisite Nil Syllabus version
1.1
Course Objectives:
 Understand the types of questions that the statistical method addresses for decision making.
 Apply statistical methods to hypotheses testing and inference problems.
 Interpret the results in a way that addresses the question of interest.
 Use data to make evidence-based decisions that are technically sound.
 Communicate the purposes of the analyses, the findings from the analysis, and the implications of
those findings.
Expected Course Outcomes:
At the end of the course students will be able to:
1. Understand the notion of a parametric model and point estimation of the parameters of those
models and properties of a good estimator.
2. Learn the approaches to point estimation of parameters.
3. Understand the concept of interval estimation and confidence intervals.
4. Basic concepts in tests of hypotheses.
5. Understand and apply large-sample tests.
6. Use small-sample tests of hypotheses.
7. Discuss nonparametric tests of hypotheses.
8. Translate and correlate the statistical analysis into Statistical inference
Student Learning Outcomes (SLO): 2, 7, 9, 18
[2] Having a clear understanding of the subject related concepts and contemporary issues

[7] Having computational thinking (Ability to translate vast data into abstract concepts and to

understand database reasoning)

[9] Having problem-solving ability- solving social issues and engineering problems

[18] Having critical thinking and innovative skills

Module:1 Introduction 9 hours
Population, sample, parameter and statistic; characteristics of a good estimator; Consistency –
Invariance property of Consistent estimator, Sufficient condition for consistency; Unbiasedness;
Sufficiency – Factorization Theorem – Minimal sufficiency; Efficiency – Most efficient estimator,
likelihood equivalence, Uniformly minimum variance unbiased estimator,applications of
Lehmann-Scheffe’s Theorem, Rao - Blackwell Theorem and applications.
Module:2 Point Estimation 6 hours
Point Estimation- Estimator, Estimate, Methods of point estimation – Maximum likelihood method
(the asymptotic properties of ML estimators are not included), Large sample properties of ML
estimator(without proof)- applications , Method of moments, method of least squares, method of
minimum chi-square and modified minimum chi-square-Asymptotic Maximum Likelihood
Estimation and applications
Module:3 Interval Estimation 4 hours

M.Sc. Data Science Page 36

Confidence limits and confidence coefficient; Duality between acceptance region of a test and a
confidence interval; Construction of confidence intervals for population proportion (small and large
samples) and between two population proportions(large samples); Confidence intervals for mean
and variance of a normal population; Difference between the mean and ratio of two normal
populations.
Module:4 Testing of hypotheses 6 hours
Types of errors, power of a test, most powerful tests; Neyman-Pearson Fundamental Lemma and its
applications; Notion of Uniformly most powerful tests; Likelihood Ratio tests: Description and
property of LR tests - Application to standard distributions.
Module:5 Large sample tests 4 hours
Large sample properties; Tests of significance (under normality assumption)- Test for a population
mean, proportion; Test for equality of two means, proportions; Test for variance,Test for
correlation, Test for Regression.
Module:6 Small sample tests 6 hours
Student’s t-test, test for a population mean, equality of two population means, paired t-test, F-test
for equality of two population variances,CRD,RBD,LSD; Chi-square test for goodness of fit and
test for independence of attributes, χ2 test for testing variance of a normal distribution
Module:7 Non-parametric tests 8 hours
Sign test, Signed rank test, Median test, Mann-Whitney test, Run test and One sample Kolmogorov
–Smirnov test ,Kruskal – Wallis H test(Description, properties and applications only).
Module:8 Contemporary issues: (Industry Expert Lecture) 2 hours
Research and Development problems related to various fields of inferential statistics with practical
knowledge of computer softwares.
Total Lecture hours: 45 hours

Text Book(s)
 Manoj
1 Kumar Srivastava and Namita Srivastava, Statistical Inference – Testing of
Hypotheses,
. Prentice Hall of India, 2014.

Robert V Hogg, Elliot A Tannis and Dale L.Zimmerman, Probability and Statistical
 Inference,9th
. edition,Pearson publishers,2013
Reference Book(s)
 Marc S. Paolella, Fundamental statistical inference: A computational approach, Wiley, 2018.
 B. K. Kale and K. Muralidharan, Parametric Inference, Narosa Publishing House, 2016.
 Miller, I and Miller, M, John E. Freund's Mathematical statistics with Applications, Pearson
Education, 2002.
 Rao, C.R., Linear Statistical Inference and its applications, 2nd Edition, Wiley Eastern, 1973.
 Gibbons, J.D., Non-Parametric Statistical Inference, 2/e,Marckel Decker, 1985.
 Bansilal, Sanjay Arora and Sudha Arora, Introducing Probability and Statistics, 2/e, Satya
Prakash Publications, 2006.
 George Casella and Roger L.Berger: , Statistical Inference, 2nd edition,Casebound Engelska,
2002

M.Sc. Data Science Page 37

Mode of Evaluation: CAT, Quiz, Assignment and FAT.
List of Experiments
1 Calculating Confidence intervals, p-value 2 hours
2 Large Sample Tests- Test for Population mean & Population proportions 4 hours
3 Small Sample Tests – t – test for population mean, Paired t test 4 hours
4 F- test for population variances 2 hours
5 Chi-square test for goodness of fit and Independence of Attributes 4 hours
6 Computation of - consistent estimator, unbiased estimators and their
2 hours
variances.
7 Computation of ML estimator by Iterative method/Method of scoring,
2 hours
computation of estimators for grouped data applying the ML.
8 Minimum χ2 and modified minimum χ2 2 hours
9 Computation of least squares estimator - calculation of standard errors of
2 hours
estimators
10 Test for correlation coefficient & Non-parametric Tests 6 hours
Total Laboratory hours 30 hours
Mode of evaluation: Continuous assessment and FAT.
Recommended by Board of Studies 24-06-2020
Approved by Academic Council No. 59 Date 24-09-2020

M.Sc. Data Science Page 38

 Course code Course title L T P J C
MAT5016 Time series analysis and Forecasting 3 0 2 0 4
Pre-requisite NIL Syllabus version
1.0
Course Objectives:
 To equip various forecasting techniques and familiarize on modern statistical methods for
analyzing time-series data.
 To amalgamate the intellectual facts of the time series data to implement in the field projects
scientifically.
 To link time-dependent analytical tools and building the models by extracting real-time data.
Expected Course Outcomes:
 On completion of the course, students will be able to
 understand the fundamental advantages and apply essential of forecasting techniques
 apply an appropriate forecasting method in any given situation.
 apply non-stationary methods in real-time problems.
 forecast with better statistical models based on statistical data analysis
 learn and apply variance transformation techniques
 understand the application of frequency-domain time series analysis.
Student Learning Outcomes (SLO): 2, 7, 9, 18
[2] Having a clear understanding of the subject interrelated concepts and of up-to-date issues
[7] Having computational thinking (Ability to translate vast data into abstract concepts and to
Understand database reasoning).
[9] Having problem-solving ability- solving social issues and engineering problems
[18] Having critical thinking and innovative skills
Module:1 Exploratory analysis of Time Series 4 hours
Graphical display, classical decomposition model, Components and various decompositions of Time
Series Models-Numerical description of Time Series: Stationarity, Autocovariance and
Autocorrelation functions - Data transformations - Methods of estimation –Trend, Seasonal and
exponential.
Module:2 Smoothing Techniques 6 hours
Moving Averages: Simple, centered, double and weighted moving averages; single and double
exponential smoothing – Holt’s and winter’s methods - Exponential smoothing techniques for series
with trend and seasonality-Basic evaluation of exponential smoothing.
Module:3 Stationary models 6 hours
Time series data, Trend, seasonality, cycles and residuals, Stationary, White noise processes,
Autoregressive (AR), Moving Average (MA), Autoregressive and Moving Average (ARMA) and
Autoregressive Integrated Moving Average (ARIMA) processes, Choice of AR and MA periods.
Module:4 Non-stationary time series models 9 hours
Tests for Nonstationarity: Random walk –random walk with drift –Trend stationary –General Unit
Root Tests: Dickey Fuller Test, Augmented Dickey Fuller Test.
ARIMA Models: Basic formulation of the ARIMA Model and their statistical properties -
Autocorrelation function (ACF), Partial autocorrelation function (PACF) and their standard errors.
Module:5 Forecasting 6 hours
Nature of Forecasting – Forecasting methods- qualitative and quantitative methods – Steps involved
in stochastic model building – Forecasting model evaluation.
Model selection techniques: AIC, BIC and AICC – Forecasting model monitoring.
Module:6 Transfer function and Intervention analysis 6 hours

M.Sc. Data Science Page 39

Transfer function models- Transfer function – noise models; Cross correlation function; Model
specification; Forecasting with Transfer function – noise models; Intervention analysis.
Module:7 Spectral analysis 6 hours
Spectral density function (s. d. f.) and its properties, s. d. f. of AR, MA and ARMA processes, Fourier
transformation and periodogram.
Module:8 Contemporary issues 2 hours
Research and Analytical problems on various applications of the sampling Techniques.
Total Lecture hours: 45 hours

Text Book(s)
 1Douglas C. Montgomery, Cheryl L. Jennings, Murat Kulahci, Introduction to Time Series
.Analysis and Forecasting, Second Ed., Wiley, 2016.

 2George E. P. Box, Gwilym M. Jenkins, Gregory C. Reinsel, Greta M. Ljung, Time Series
.Analysis: Forecasting and Control, Fifth Ed., Wiley, 2016.
Reference Books
 1Brockwell, P. J., & Davis, R. A., Introduction to time series and forecasting, Third Ed.,
.Springer, 2016.

 2Terence C. Mills, Applied Time Series Analysis: A Practical Guide to Modeling and
.Forecasting, Academic Press, 2019.

Mode of Evaluation: CAT, Quiz, Digital Assignment and FAT.

List of Challenging Experiments (Indicative)
1 Visualization of Stationary and Non-stationary time series 4 hours
2 Moving Average Time Series Model and Differencing 4 hours
3 Exponential smoothing technique (Single, double and triple) 4 hours
4 Auto-Regressive Model for Stationary Time Series 4 hours
5 Autoregressive Integrated Moving Average for Non- Stationary Time Series 4 hours
6 Forecasting With Univariate Models 4 hours
7 Transfer Functions and Autoregressive Distributed Lag Modeling 4 hours
8 Spectral density function 2 hours
Total Laboratory hours 30 hours
Mode of Evaluation: Continuous assessment and FAT.
Recommended by Board of Studies 10.09.2019
Approved by Academic Council No. 56 Date 24-09-2019

M.Sc. Data Science Page 40

 Regression Analysis and Predictive
Course code L T P J C
Modelling
MAT6002 3 0 2 0 4
Pre-requisite MAT5012 - Probability Theory and Syllabus version
Distributions
1.0
Course Objectives:
 Develop an understanding of regression analysis and model building.
 Provide the ability to develop relationship between variables
 Investigate possible diagnostics in regression techniques
 Formulate feasible solution using regression model for real-life problems.
Expected Course Outcome:
At the end of the course students will be able to:
 develop in-depth understanding of the linear and nonlinear regression model.
 demonstrate the knowledge of regression modeling and model selection techniques.
 examine the relationships between dependent and independent variables.
 estimate the parameters and fit a model.
 investigate possible diagnostics in regression modeling and analysis.
 validate the model using hypothesis testing and confidence interval approach.
 understand the generalizations of the linear model to binary and count data.
Student Learning Outcomes (SLO): 2, 7, 9, 18
[2] Having a clear understanding of the subject related concepts and contemporary issues
[7] Having computational thinking (Ability to translate vast data into abstract concepts and
to understand database reasoning)
[9] Having problem-solving ability- solving social issues and engineering problems.
[18]Having critical thinking and innovative skills
Module:1 Simple Regression Analysis 6 hours
Introduction to a linear and nonlinear model. Ordinary Least Square methods. Simple linear
regression model, using simple regression to describe a linear relationship. Fitting a linear trend
to time series data, Validating simple regression model using t, F and p test. Developing
confidence interval. Precautions in interpreting regression results.
Module:2 Multiple Regression Analysis 6 hours
Concept of Multiple regression model to describe a linear relationship, Assessing the fit of the
regression line, inferences from multiple regression analysis, problem of overfitting of a model,
comparing two regression model, prediction with multiple regression equation.
Module:3 Fitting Curves and Model Adequacy Checking 6 hours
Introduction, fitting curvilinear relationship, residual analysis, PRESS statistics, detection and
treatment of outliers, lack of fit of the regression model, test of lack of fit, Problem of
autocorrelation and heteroscedasticity. Estimation of pure errors from near neighbors.
Module:4 Transformation techniques 5 hours
Introduction, variance stabilizing transformations, transformations to linearize the model, Box-
Cox methods, transformations on the repressors variables, Generalized and weighted least
squares, Some practical applications.
Module:5 Multicollinearity 7 hours
Introduction, sources of multicollinearity, effects of multicollinearity. Multicollinearity
diagnostics: examination of correlation matrix, variance Inflation factors (VIF), Eigen system
analysis of X1X. Methods of dealing with Multicollinearity: collecting additional data, model

M.Sc. Data Science Page 41

re-specification, and ridge regression.
Module:6 Generalized Linear Models 7 hours
Generalized linear model: link functions and linear predictors, parameter estimation and
inference in the GLM, prediction and estimation with the GLM, Residual Analysis, and
concept of over dispersion.
Module:7 Model building and Nonlinear Regression 6 hours
Variable selection, model building, model misspecification. Model validation techniques:
Analysis of model coefficients, and predicted values, data splitting method. Nonlinear
regression model, nonlinear least squares, transformation to linear model, parameter estimation
in nonlinear system, statistical inference in nonlinear regression.
Module:8 Contemporary issues: 2 hours
Research and Analytical problems on various applications of the regression analysis and predictive
modeling.
Total Lecture hours: 45 hours

Text Book(s)
 Douglas C. Montgomery, Elizabeth A. Peck, G. Geoffrey Vining, Introduction to
Linear Regression Analysis, Third Ed., Wiley India Pvt. Ltd., 2016.
 Norman R. Draper, Harry Smith; Applied Regression Analysis, WILEY India Pvt.
Ltd. New Delhi; Third Edition, 2015.
Reference Books
 . Johnson, R A., Wichern, D. W., Applied Multivariate Statistical Analysis, Sixth Ed., PHI
learning Pvt., Ltd., 2013.

 . Iain Pardoe, Applied Regression Modeling, John Wiley and Sons, Inc, 2012.
Mode of Evaluation: CAT / Digital Assignment / Quiz / FAT
List of Challenging Experiments
1. Correlation Analysis using- scatter diagram, Karl Pearson’s correlation 2 hours
coefficient and drawing inferences.
2. Simple linear regression: model fitting, estimation of parameters, 4 hours
computing R2 and adjusted R2 and model interpretation.
3. Residual analysis and forecast accuracy for a given data set. 2 hours
4. Validating Simple linear regression using t, F and p- test. 4 hours
5. Developing confidence interval and testing the model simple and multiple 4 hours
regression.
6. Multiple regression: estimation of parameters, fitting of the model, error 4 hours
analysis, model validation, variable selection and testing.
7. Problem of multicollinearity and, determination of VIF. 2 hours
8. Diagnostic measures and outliers detection, Durbin Watson test, variable 4 hours
selection and model building
9. Autocorrelation, auto regressive model. 2 hours
10 Fitting of nonlinear regression model. 2 hours
Total Laboratory Hours: 30 hours
Mode of assessment: Continuous Assessment and FAT
Recommended by Board of Studies 10-09-2019
Approved by Academic Council No. 56 Date 24-09-2019

M.Sc. Data Science Page 42

Course code Course Title L T P J C
MAT5017 Multivariate Data Analysis 3 0 2 0 4
Pre-requisite Knowledge of Fundamental of Statistics, Matrices and Syllabus version
Linear Algebra
1.0
Course Objectives:
The objective of the course is to make the student:
 Understand the fundamental concepts of Multivariate Data Analysis / Multivariate Statistical
Analysis.
 Conversant with various methods and techniques used in summarization and analysis of
multivariate data.
 Prepare for investigation of multivariate data and examine the possible diagnostics in
multivariate methods.
 Formulate real time problem in a form of multivariate model.
 Develop feasible solution of real-life problems, using multivariate methods and techniques.
 Conduct research using multivariate data analysis techniques.

Expected Course Outcome:

 At the end of the course students will be able to:
 Learn to develop an in-depth understanding of the Multivariate models, methods and
techniques.
 Demonstrate the knowledge and skill of multivariate normal distributions, related probability
distributions and their applications.
 Examine the relationships between dependent and independent variables of multivariate
models, estimate the parameters and fit a model.
 Perform, handle and manipulate the analysis of discriminant function and logistic regression.
 Apply the method and analysis of principal components, factor analysis and dimension
reduction of sample data.
 Investigate the events of clustering and multidimensional scaling presence in sample data.
 Conduct the application of Structural Equation Modeling (SEM) to real-time observations.
 8. Research on real-time problems from various disciplines using multivariate data analysis.

Student Learning Outcomes (SLO): 2, 7, 9, 18
[2] Having a clear understanding of the subject related concepts and contemporary issues
[7] Having computational thinking (Ability to translate vast data into abstract concepts and
to understand database reasoning)
[9] Having problem-solving ability- solving social issues and engineering problems.
[18] Having critical thinking and innovative skills.
Module:1 Introduction to Multivariate Data Analysis 5 hours
Multivariate data and their diagrammatic representation. Exploratory multivariate data analysis,
sample mean vector, sample dispersion matrix, sample correlation matrix, graphical representation,
means, variances, co-variances, correlations of linear transforms, six step approach to multivariate
model building. Introduction to multivariate linear regression, logistic regression, principal
component analysis, factor analysis, cluster analysis, canonical analysis and canonical variables,
structured equation modeling (SEM).

Module:2 Multivariate Normal Distribution(MND) 8 hours

M.Sc. Data Science Page 43

Introduction to multivariate normal distribution, probability density function and moment generating
function of multivariate normal distribution, singular and nonsingular normal distributions,
distribution of linear and quadratic form of normal variables, marginal and conditional distributions.
Random sampling from multivariate normal distributions. Goodness of fit of multivariate normal
distribution. Wishart matrix-its distribution and properties.

Module:3 Multivariate Linear Model and Analysis of 8 hours

Variance and Covariance
Maximum likelihood estimation of parameters, tests of linear hypothesis, distribution of partial and
multiple correlation coefficients and regression coefficients. Multivariate linear regression,
multivariate analysis of variance of one and two way classification data (only LR test). Multivariate
analysis of covariance. Hoteling 𝑇 2 and Mahalanobis 𝐷2 applications in testing and confidence set
construction.

Module:4 Multiple Discriminant Analysis and 7 hours

Logistic Regression
Discriminant model and analysis: a two group discriminant analysis, a three group discriminant
analysis, the decision process of discriminant analysis( objective, research design, assumptions,
estimation of the model, assessing overall fit of a model, interpretation of the results, validation of
the results). Logistic Regression model and analysis: regression with a binary dependent variable,
representation of the binary dependent variable, estimating the logistic regression model, assessing
the goodness of fit of the estimation model, testing for significance of the coefficients, interpreting
the coefficients.

Module:5 Principal Components and common 5 hours

Factor Analysis
Population and sample principal components, their uses and applications, large sample inferences,
graphical representation of principal components, Biplots, the orthogonal factor model, dimension
reduction, estimation of factor loading and factor scores, interpretation of factor analysis.

Module:6 Cluster Analysis and Multidimensional 5 hours

Scaling
Concepts of cluster analysis and multidimensional scaling, similarity measures, hierarchical
clustering methods, Ward’s hierarchical clustering method’s, nonhierarchical clustering methods,
K-means methods. Clustering based on statistical models, multidimensional scaling and
correspondence analysis, perceptual mapping.

Module:7 Structural Equation Modelling (SEM) 5 hours

Concept of structural equation modeling, Confirmatory factor analysis, canonical correlation
analysis, conjoint analysis.

Module:8 Contemporary issues: 2 hours

Research and Analytical problems of multivariate data / statistical analysis from science, engineering,
industry, economics, environment, commerce, medicine & health, general and administrative
management etc.

Total Lecture hours: 45 hours

M.Sc. Data Science Page 44

Text Book(s)
 Hardly W.K. and Simor L., Applied Multivariate Statistical Analysis, 4th Edition,
Springer- Verlag, 2015.

 Richard A. Johnson and Dean W. Wichern, Applied Multivariate Statistical Analysis,

Prentice hall India, 7th Edition, 2019.

Reference Books
 Joseph F. Hair, Jr., William C. Black, Barry J. Babin, Rolph E. Anderson and Ronald L.
Tatham, Multivariate Data Analysis, 7th Edition, Pearson Education India, 2014.
 Rao, C. R. and Rao, M. M., Multivariate Statistics and Probability, Elsevier & Academic
Press, 2014.
 Kshirsagar, A. M., Multivariate Analysis, Marcel Dekkar, 2006.
 Anderson T.W., An Introduction to Multivariate Statistical Analysis, John Wiley & sons,
3rd Edition, 2009.
Bhuyan, K. C., Multivariate Analysis and its Applications, New Central book Agency Pvt.

Ltd., 2005.
Weisberg S., Applied Linear Regression, 4th Edition, Wiley, 2013.

Kollo T., and Rosen D. Von, Advanced Multivariate Statistical Analysis with Matrices,
Springer, New York, 2005.

Authors, book title, year of publication, edition number, press, place

Mode of Evaluation: CAT / Assignment / Quiz / FAT / Project / Seminar.
List of Challenging Experiments (Indicative) using
packages, software’s and other scientific devices
1. MLE of mean vector and variance-covariance matrix from the normal 4 hours
population. Generating random numbers from a multivariate normal
distribution.
2. Hoteling 𝑇 2 and Mahalanobis 𝐷2 4 hours
3. Computation of principal components and conducting factor analysis 4 hours
4. Fitting a multivariate linear regression model and its interpretation. 4 hours
5. Error analysis, outliers detection and related tests 2 hours
6. Estimation, fitting and validating a logistic regression model. 4 hours
7. Classification between two normal populations using discriminant analysis. 2 hours
8. Cluster analysis 2 hours
9. Computation of canonical variables and correlation 2 hours
10 Structural Equation Modeling and related computations 2 hours
Total Laboratory Hours 30 hours
Mode of assessment: Continuous Assessment and FAT.
Recommended by Board of Studies 24-06-2020
Approved by Academic Council No. 59 Date 24-09-2020

M.Sc. Data Science Page 45

 Programme Elective
Course code Course title L T P J C
MAT6003 Programming for Data Science 0 0 4 0 2
Pre-requisite MAT5012- Probability Theory and Distributions Syllabus version
1.0
Course Objectives:
 Formulate simple problems, and code a high-level appropriate programme for data science.
 Acquire knowledge of standard data visualization and formal inference procedures to
interpret the results.
 To develop complex statistical models to assess data and apply to real-world contexts.
Expected Course Outcome:
At the end of the course students will be able to:
 develop relevant programming techniques of moderate complexity and execute in data
science.
 demonstrate the proficiency in statistical data analysis of inferential methods and interpret
the results contextually.
 apply data science concepts and methods to solve problems in real-world contexts
 integrate data from disparate sources and transform in relational databases.
Student Learning Outcomes (SLO): 2, 7
[2] Having a clear understanding of the subject related concepts and contemporary issues
[7] Having computational thinking (Ability to translate vast data into abstract concepts and to
understand database reasoning)
List of Challenging Experiments (Indicative)
1 Introduction to Python – Keywords, identifiers, I/O statements. 4 hours
2 Sequence and File operations. 4 hours
3 Functions, loops, Modules, errors and exceptions. 4 hours
Data Manipulation- Basic Functionalities, Merging, Concatenation of data
4 6 hours
objects, Exploring a Dataset and Analysing a dataset.
5 Data visualization – Graphical and diagrammatical presentation 4 hours
6 Descriptive statistical analysis – evaluation, plotting and interpretation. 4 hours
7 Evaluation of probability using various distribution functions 4 hours
Correlation – Simple, Partial and Multiple Correlations for linear and non-linear
8 6 hours
data.
9 Regression – Simple, Multiple Regression and linear models. 6 hours
Test for normality and homogeneity of variance-Inferential Statistics for Single
10 6 hours
through multiple samples.
Experimental Design: One way ANOVA-two way ANOVA- Multiple
11 6 hours
comparison tests
Time series analysis – White noise, AR, MA, ARMA, ARIMA, ACF and
12 6 hours
PACF.
Total Laboratory hours 60 hours
Text Book(s)
 Jake
1 VanderPlas, Python Data Science Handbook - Essential Tools for Working with Data,
O’Reily
. Media, 2017.
Zhang.Y, An Introduction to Python and Computer Programming, Springer Publications,
 2016.
2

M.Sc. Data Science Page 46

 .
Reference Book(s)
 Nelli, F., Python Data Analytics: With Pandas, NumPy, and Matplotlib, Second Ed., Apress,
2018.
Samir Madhavan, Mastering Python for Data Science, Packt Publishing Ltd., 2015.
Mode of Evaluation: Continuous assessment and FAT
Recommended by Board of Studies 10.09.2019
Approved by Academic Council No. 56 Date 24-09-2019

M.Sc. Data Science Page 47

 Course code Course title L T P J C
MAT6012 Programming for Data Analysis 2 0 4 0 4
Pre-requisite NIL Syllabus version
1.0
Course Objectives:
 To introduce core programming basics required for data science using Python language
 To read and write simple Python programs
 To develop Python programs with conditionals and loops
 To use Python data structures – lists, tuples, dictionaries
 To introduce the important data science modules NumPy, SciPy and Matplotlib
 To introduce the input/output with files in Python and statistical processing of a data using
Pandas
Expected Course Outcome:
At the end of the course students will be able to:
 Read, write, execute simple Python programs
 Decompose a Python program into functions
 Manipulate with 1-d,2-d and multidimensional data using Python
 Read and write data from/to files in Python programs
 Develop algorithmic solutions to data science related problems
Module:1 Algorithmic Problem Solving 3 hours
Algorithms, building blocks of algorithms (statements, state, control flow, functions); algorithmic
problem solving; iteration, recursion. Illustrative problems: finding minimum in a list, guess an integer
number in a range, factorial of a number
Module:2 Data, Expressions, Statements in Python 4 hours
Python Strengths and Weakness; Installing Python; IDLE - Spyder – Jupyter; Mutable and Immutable
Data Types, Naming Conventions; String Values; String Operations; String Slices; String Operators;
String functions – split, join, chr, ord; Numeric Data Types; Arithmetic Operators and Expressions;
Comments in the Program; Understanding Error Messages
Module:3 Data Collection and Language Component of Python 4 hours
List; Tuples; Sets; Dictionaries; Sorting Dictionaries; Control Flow and Syntax; Indenting; The if
statement; Relational Operators; Logical Operators; Bit-wise Operators; The while Loop – break and
continue statements; The for Loop; List Comprehension
Module:4 Functions and Modules in Python 4 hours
Functions - Introduction; Defining your own functions; parameters; local and global scope; passing
collections to a function; variable number of arguments; passing functions to a function; Lambda
function; map; filter; Modules: Introduction; Standard Modules – sys, math, time
Module:5 Python Modules for Data Science – I 5 hours
NumPy arrays – 1-d, multidimensional arrays and matrices; Mathematical operations with arrays;
Slicing and addressing arrays; Boolean masks; Difference between lists and arrays
SciPy – Scientific Computing library of Python – Introduction, Basic functions, Special functions,
scipy.integrate, scipy.optimize, scipy.interpolate
Module:6 Python Modules for Data Science – II 5 hours
Python Plotting: PyPlot – Basic Plotting; Logarithmic Plots; Plots with multiple axes; Matplotlib –
interactive functions 3d plotting; Pandas – Introduction, DataFrame, Reading and writing CSV, XLS
files, Working with missing data, categorical data, data visualization with pandas
Module:7 Error Handling in Python 3 hours

M.Sc. Data Science Page 48

 Handling IO Exceptions, Metadata, Errors, Runtime Errors, Exception Model

Module:8 Contemporary issues: (Industry Expert Lecture) 2 hours

Research and Development problems related to Data Science
Total Lecture Hours 30 hours

Mode of Evaluation: CAT, Quiz, Digital Assignment and FAT.

List of Challenging Experiments (Indicative)

1. Python Program Environment, IDLE, Jupyter, Spyder environments 4 hours
First Basic Experiment(s): (i) “Hello World!” Program in IDLE, Jupyter, Spyder
Environments.
(ii) Program(s) to demonstrate the Python data types
2. Python Operators, Expressions and Flow Controls 4 hours
Simple Experiment(s): (i) Program to demonstrate the Python operators and their
order of preference.
(ii) Program to add/multiply/divide two numbers
(iii) Program to verify whether a given number is even or odd
Perfection: Program to verify whether a given number is Armstrong number or
not. A number is said to Armstrong number if sum of the cubes of individual
digits of that number is equal to the number itself. Viz., 153 = 1^3 + 5^3 + 3^3
3. Python Lists, Tuples, Dictionaries & Sets 6 hours
Simple Experiment: Write a Python program which demonstrate the use of Lists,
Tuples Dictionaries and Sets. This program should accepts the elements into
various types and perform the other operations such as append, copy, extend,
pop, remove operations.
4. Python Functions, Modules and Packages 4 hours
Simple Experiment(s): Write a function file which accepts a set of numbers and
displays the largest among them
Perfection: Write a function which accepts a number ‘n’ and list the first ‘n’
Fibonacci numbers
Challenging: Create a own module in Python which includes functions such as
greeting() which greets a welcome message to user. This module should also
contain some variables and functions which finds the maximum among the two
given numbers.
5. Array and Matrix Manipulation in Python 4 hours
Simple Experiment: Write a Python program demonstrating the NumPy matrix
operations such as accepting two matrices finding the dimension, adding the two
matrices
Perfection: Write a Python program which accepts a matrix A of order m x p
another matrix B of order p x n and checks whether the matrix multiplication is
possible or not. If possible then finds matrix multiplication and displays it to
user.
6. Data Manipulation – SciPy Module 6 hours
Simple Experiment: Write a Python program to find the det, inv, eigenvalues and
eigenvectors of a matrix using corresponding SciPy module functions
Challenging: Create a data set consisting of time series observations of an
experiment. Using the interpolation techniques of SciPy module form an
interpolating polynomial and use it to estimate the experimental values for

M.Sc. Data Science Page 49

 intermediate values.
7. Data Visualization in Python – PyPlot Module 6 hours
Compare: Given the examination scores of students of three different classes for
the same subject taught by different professors, display them visually to aid
comparison of pass percentage, A grades etc.
8. Data Manipulation using Pandas – Exploring a Dataset and Analysing a Dataset 6 hours
Simple Experiments: Create a data frame consists of five countries, their capitals,
area of the country, population. The program should also print the description of
the data frame and finally save this data frame to a csv file.
Challenging: Write a Python program demonstrating the Pandas indexing
capabilities, identifying the null values in the dataset and filling them with or
dropping them from the dataset. Also demonstrate the merging, joining and
concatenating data frames using Pandas.
9. Descriptive Statistical Analysis – Evaluation, Plotting and Interpretation 6 hours
Linear Regression: Read a data frame in csv/xls format containing the weather
data such as pressure, min temp, max temp, humidity, rainfall. Using the
Pandas, MatPlotlib and SciPy plot the scatter plots and develop a linear
interpolation between rainfall with all other parameters and evaluate the
statistical significance of the model.
10. Evaluation of Probability using various Distributions Functions 6 hours
Simple Experiments: Write Python programs to generate a normal distribution,
binomial distribution and Poisson distribution using Python and visualize them.
Challenging: Write Python program to check the normality of a dataset, which a
foremost important test, required to determine whether to apply parametric tests
or nonparametric tests on the given test. These tests include Histogram,
Quantile-quantile plot, Shapiro-Wilk test, D’Agotino’s K-squared test,
Anderson-Darling test
11. Linear and Nonlinear Regression in Python 4 hours
Simple Linear Regression: Write a Python program to implement the Simple
Linear Regression model to predict the wine quality using the physicochemical
and sensory variables by using Scikit-Learn module and estimate the statistical
significance of the model.
Nonlinear Linear Regression: Write a Python program to predict the price of oil
(OIL) from indicators such as the West Texas Intermediate (WTI) price, Henry
Hub gas price (HH), and the Mont Belvieu (MB) propane spot price. Data is
available for OIL, WTI, HH, and MB from the years 2000 to 2016 at the link
https://apmonitor.com/me575/uploads/Main/oil_data.txt. The OIL is related with
WTI, HH and MB nonlinearly as follows:
OIL = A (WTIB) (HHC) (MBD)
12. Decision Trees and Time Series Analysis in Python 4 hours
Programs to illustrate the use of decision trees in machine learning to develop
the decisions and their possible consequences. In this experiment we will use the
dataset related breast cancer to predict the breast cancer spread using decision
trees.
Total Laboratory Hours 60 hours

Mode of Evaluation: CAT and FAT

Text Book(s)

M.Sc. Data Science Page 50

  David
1 J. Pine, Introduction to Python for Science and Engineering, CRC Press, 2019.
. vander Plas, Python Data Science Handbook – Essential Tools for Working with Data,
Jake
 O’Really
2 Media, 2017
.

Reference Book(s)
 Robert Johansson, Numerical Python – Scientific Computing and Data Science Applications with
NumPy, SciPy and Matplotlib, Apress, 2019
 Robert Sedgewick, Kevin Wayne, Robert Dondero, Introduction to Programming in Python: An
Inter-disciplinary Approach, Pearson India Education Services Pvt. Ltd., 2016
 Nelli, F., Python Data Analytics: with Pandas, NumPy and Matplotlib, Apress, 2018.

Mode of Evaluation: CAT, Quiz, Digital Assignment and FAT.

Recommended by Board of Studies 24-06-2020
Approved by Academic Council No. 59 Date 24-09-2020

M.Sc. Data Science Page 51

Course code Course title L T P J C
MAT 6004 Computational statistics for Data science 0 0 4 0 2
Pre-requisite MAT5013 - Statistical Inference Syllabus version
1.0
Course Objectives:
 Use of software packages for statistical theory towards computing environment.
 To enhance the theoretical concepts and its application in the real-time domain.
Expected Course Outcomes:
Students will be able to
 use software tools for projects in data management.
 apply technical skills in the statistical data analysis to transform a simple to multiple
variables.
 understand the statistical decision-making theory and interpretation.
 analyze and solve real-time problems
Student Learning Outcomes (SLO): 2, 7
[2] Having a clear understanding of the subject related concepts and contemporary issues
[7] Having computational thinking (Ability to translate vast data into abstract concepts and to
understand database reasoning)
List of Challenging Experiments (Indicative)
1 Data Management – Handling Big data sets and variable selection 6 hours
2 Descriptive statistics and their interpretation 8 hours
3 Tabulation of Data and Cross Tabulation 6 hours
4 Correlation analysis 8 hours
5 Regression analysis 8 hours
6 Testing of the hypothesis ( 𝑍, 𝑡, 𝐹 and 𝜒 2 - tests) 8 hours
7 Non-parametric tests 8 hours
8 Design and analysis of experiments 8 hours
Total Laboratory hours: 60 hours
Text Book(s)
 McCormick,
1 Keith; Salcedo, Jesus, SPSS statistics for data analysis and visualization, Wiley,
2017.
.

 K.2 V. S. Sarma, Statistics Made Simple Do It Yourself, 2nd Ed, Prentice-Hall, 2010.
.
Reference Book(s)
 Murtaza
1 Haider, Getting Started with Data Science: Making Sense of Data with Analytics,
.
IBM Press, 2015.

 J.P.
2 Verma, Data Analysis in Management with SPSS Software, Springer, 2013.
.
Mode of Evaluation: Continuous Assessment and FAT.
Recommended by Board of Studies 10.09.2019
Approved by Academic Council No. 56 Date 24-09-2019

M.Sc. Data Science Page 52

Course code Course title L T P J C
MAT6005 Machine Learning for Data Science 3 0 2 0 4
Pre-requisite MAT 5010- Foundations of Data Science Syllabus version
1.0
Course Objectives:
 Lay the foundation of machine learning and its practical applications and prepare students for
real-time problem-solving in data science.
 Develop self-learning algorithms using training data to classify or predict the outcome of
future datasets.
 Distinguish overtraining and techniques to avoid it such as cross-validation.
Expected Course Outcome:
At the end of the course students will be able to:
 understand the most popular machine learning algorithms
 analyze and perform an evaluation of learning algorithms and model selection.
 compare the strengths and weaknesses of many popular machine learning approaches
 appreciate the underlying mathematical relationships within and across machine learning
algorithms and the paradigms of supervised and unsupervised learning.
 design and implement various machine learning algorithms in a range of real-world
applications.
Student Learning Outcomes (SLO): 2, 7, 9, 18
[2] Having a clear understanding of the subject related concepts and contemporary issues
[7] Having computational thinking (Ability to translate vast data into abstract concepts and to
understand database reasoning)
[9] Having problem-solving ability- solving social issues and engineering problems
[18] Having critical thinking and innovative skills
Module:1 Introduction to Machine Learning 2 hours
The origins of machine learning-How machines learn - Machine learning in practice- Exploring and
understanding state-of-the-art methods.
Module:2 Classification 6 hours
Learning Associations-Classification-Regression- Decision Trees - Reinforcement Learning-
Probably Approximately Correct Learning (PAC)- Noise-Learning -Multiple classes-Model Selection
and Generalization- Support Vector Machines.
Module:3 Parametric Methods 5 hours
Introduction to Parametric methods-Maximum Likelihood Estimation: Bernoulli, binomial, Poisson
distributions - Gaussian Density. Evaluating an Estimator: Bias and Variance-The Bayes Estimator-
Parametric Classification.
Module:4 Nonparametric Methods 8 hours
Introduction-Nonparametric Density Estimation: Histogram Estimator-Kernel Estimator-K-Nearest
Neighbour Estimator-Generalization to Multivariate Data-Nonparametric classification-Distance
Based Classification-Outlier Detection.
Module:5 Multivariate Methods 8 hours
Multivariate Data-Parameter Estimation-Estimation of Missing Values- Expectation-Maximization
algorithm -Multivariate Normal Distribution- Multivariate Classification-Tuning Complexity-
Discrete Features.
Module:6 Dimensionality Reduction 8 hours

M.Sc. Data Science Page 53

Introduction- Subset Selection-Principal Component Analysis, Feature Embedding-Factor Analysis-
Singular Value Decomposition-Multidimensional Scaling- Canonical Correlation Analysis.
Module:7 Supervised Learning and Unsupervised 6 hours
Learning
Linear Discrimination: Introduction- Generalizing the Linear Model-Geometry of the Linear
Discriminant- Linear Discriminant Analysis- Pairwise Separation-Gradient Descent-Logistic
Discrimination. Clustering: Introduction, K-Means Clustering- Mixtures of Latent Variable Models-
Spectral Clustering-Hierarchical Clustering-Clustering, Choosing the number of Clusters.
Module:8 Contemporary issues 2 hours
Practical knowledge on machine learning techinuques in data science.
Total Lecture hours: 45 hours

Text Book(s)
 1E. Alpaydin, Introduction to Machine Learning, 3rd Edition, MIT Press, 2015.
.Pratap Dangeti, Statistics for Machine Learning, Packt Publishing, 2017.
 2
.
Reference Book(s)
 1C.M. Bishop, Pattern Recognition and Machine Learning, Springer, 2016
.K. P. Murphy, Machine Learning: A Probabilistic Perspective, MIT Press, 2012
 2
.
Mode of Evaluation: CAT, Quiz, Digital Assignment and FAT
List of Challenging Experiments (Indicative)
1 Exploring and Understanding data and formats 2 hours
2 Classification techniques using Decision Trees 4 hours
3 Support Vector Machines 4 hours
4 Clustering Algorithms 4 hours
5 Computation of missing values and multivariate classification 4 hours
6 Dimensionality reduction: A factor analysis. 4 hours
7 Discriminant analysis 4 hours
8 Canonical Correlation analysis 4 hours
Total Laboratory hours: 30 hours
Mode of evaluation: Continuous Assessment and FAT.
Recommended by Board of Studies 10.09.2019
Approved by Academic Council No. 56 Date 24-09-2019

M.Sc. Data Science Page 54

Course code Course Title L T P J C
MAT6010 Optmization Techniques 3 2 0 0 4
Pre-requisite NIL Syllabus version
v. xx.xx
Course Objectives:
 To familiarize the students with some basic concepts of optimization techniques and
approaches.
 To formulate a real-world problem as a mathematical programming model.
 To develop the model formulation and applications are used in solving decision problems.
 To solve specialized linear programming problems like the transportation and assignment
 Problems.
Expected Course Outcome:
Student will be able to
 apply operations research techniques like linear programming problem in industrial
optimization problems.
 solve allocation problems using various OR methods.
 understand the characteristics of different types of decisionmaking environment and the
appropriate decision making approaches and tools to be used in each type.
 recognize competitive forces in the marketplace and develop appropriate reactions based
on existing constraints and resources.
Student Learning Outcomes (SLO): 2, 7, 9, 18
[2] Having a clear understanding of the subject related concepts and contemporary issues
[7] Having computational thinking (Ability to translate vast data into abstract concepts and to
understand database reasoning)
[9] Having problem-solving ability- solving social issues and engineering problems
[18] Having critical thinking and innovative skills
Module:1 Introduction to Operations Research 6 hours
Introduction-Mathematical models of Operation Research-Scope and applications of Operation
Research-Phases of Operation Research study-Characteristics of Operation Research-Limitations
of Operation Research.
Module:2 Linear Programming 6 hours
Introduction –Properties of Linear Programming-Basic assumptions-Mathematical formulation of
Linear Programming-Limitations or constraints-Methods for the solution of LP Problem-Graphical
analysis of LP-Graphical LP Maximization problem-Graphical LP Minimization problem.
Module:3 Linear Programming Models 7 hours
Simplex Method-Basics of Simplex Method-Formulating the Simplex Method-Simplex Method
with two variables-Simplex Method with more than two variables-Big M Method.
Module:4 Dual Linear Programming 6 hours
Introduction- Primal and Dual problem -Dual problem properties-Solution techniques of Dual
problem-Dual Simplex method-Relations between direct and dual problem-Economic
interpretation
of Duality.
Module:5 Transportation and Assignment Models 6 hours
Introduction: Transportation problem-Balanced-Unbalanced-Methods of basic feasible solution-
Optimal solution-MODI method. Assignment problem-Hungarian Method.
Module:6 Network Analysis 6 hours

M.Sc. Data Science Page 55

Basic concepts-Construction of Network-Rules and precautions-CPM and PERT Networks-
Obtaining of critical path. Probability and cost consideration. Advantages of Network.
Module:7 Theory of Games 6 hours
Introduction-Terminology-Two Person Zero-Sum game-Solution of games with saddle points and
without saddle points-2X2 games-dominance principle – mX2 and 2Xn games-Graphical method.
Module:8 Contemporary issues (Industry Expert Lecture) 2 hours
Research and Analytical problems on various applications of the industrial issues.
Total Lecture hours: 45 hours
 A minimum of 5 problems to be worked out by students in every
Tutorial tutorial class 15 hours
 Another 5 problems per tutorial class to be given as a home work
Text Book(s)
 1Hamdy Taha, Operations Research, 10th edition, Prentice Hall India, 2019.
 2P. K. Gupta and D. S. Hira, Operations Research, S. Chand & co., 2007.
Reference Books
 1S.D. Sharma (2000), Operations Research, Nath & Co., Meerut.
Maurice Solient, Arthur Yaspen, Lawrence Fridman, (2003), OR methods and Problems,
 2New Age International Edition.
 3J K Sharma (2007), Operations Research Theory & Applications, 3e, Macmillan India Ltd.
P. Sankara Iyer, (2008), Operations Research, Tata McGraw-Hill.
 4A Ravindran,
nd
Don T Philips and James J Solberg, Operations Research: Principles and
Practice, 2 edition, John Wiley and sons, 2007
Mode of Evaluation: CAT / Digital Assignment / Quiz / FAT
Recommended by Board of Studies 24.06.2020
Approved by Academic Council No. 59 Date 24-09-2020

M.Sc. Data Science Page 56

Course code Course title L T P J C
MAT6007 Deep Learning 2 0 2 0 3
Pre-requisite NIL Syllabus version
v. 1.0
Course Objectives:
 To introduce the fundamentals of neural networks as well as some advanced topics such as
recurrent neural networks, long/short term memory cells and convolutional neural
networks.
 To introduce complex learning models and deep learning models
 To explore various learning models using different software packages
Expected Course Outcome:
On completion of the course, students will be able to
 understand the fundamentals of deep learning and build deep learning models
 Apply the most appropriate deep learning method in any given situation.
 Develop neural network models in data-intensive real-time problems.
 Develop efficient generative models
 Learn and apply convolutional and recurrent neural network techniques.
Student Learning Outcomes (SLO): 2, 7, 18
[2] Having a clear understanding of the subject related concepts and of contemporary issues
[7] Having computational thinking (Ability to code deep learning algorithms)
[17] Having an ability to use techniques, skills and modern engineering tools necessary for deep
learning practice
Module:1 Introduction 4 hours
What is neural network, Biological Neuron, Idea of computational units, McCulloch–Pitts unit and
Thresholding logic, Linear Perceptron, Perceptron Learning Algorithm, Convergence theorem for
Perceptron Learning Algorithm, Linear separability, feed-forward networks, input, hidden and
output layers, organization and architecture of neural networks, linear and nonlinear networks
Module:2 Training algorithms for Feedforward networks 5 hours
Learning the weights, Cost functions, Back-propagation algorithms, gradient descent algorithm,
unit saturation, heuristics to avoid local optima, accelerated algorithms, Multilayer Perceptron,
Empirical Risk Minimization, regularization, autoencoders
Module:3 Deep Neural Networks 4 hours
Architectures, Properties of CNN representations: invertibility, stability, invariance, convolution,
pooling of layers, CNN and Tensorflow, Difficulty of training deep neural networks, Greedy layer-
wise training.
Module:4 Better Training of Neural Networks 4 hours
Newer optimization methods for neural networks (Adagrad, adadelta, rmsprop, adam, NAG),
second order methods for training, Saddle point problem in neural networks, Regularization
methods (dropout, drop connect, batch normalization).
Module:5 Recurrent neural networks 4 hours
LSTM, GRU, Encoder-decoder architectures, Auto-encoders (standard, de-noising, contractive,
etc), Variational Autoencoders, kohonen SOM, : Back propagation through time, Long Short Term
Memory, Gated Recurrent Units, Bidirectional LSTMs, Bidirectional RNNs.
Module:6 Deep Generative learning 4 hours
Dynamic memory models. Reinforcement learning, Restrictive Boltzmann Machines (RBMs),
Introduction to MCMC and Gibbs Sampling, gradient computations in RBMs, Deep Boltzmann
Machine., deep belief networks, convolutional networks, LeNet, AlexNet
Module:7 Recent trends 3 hours

M.Sc. Data Science Page 57

Variational Auto-encoders, Generative Adversarial Networks, Multi-task Deep Learning, Multi-
view Deep Learning
Module:8 Contemporary issues (Industry Expert Lecture) 2 hours
Research and Analytical problems related to data science.
Total Lecture hours: 30 hours
Text Book(s)
 Bengio,
1 Yoshua, Ian Goodfellow, Aaron Courville, Deep learning, MIT press, 2016.
.
Reference Book(s)
 Raúl
1 Rojas, Neural Networks: A Systematic Introduction, 1996, 2nd edition
Bishop
. C., neural networks for pattern recognition, 2015, Oxford university press
 2
Mode of Evaluation: CAT / Digital Assignment / Quiz / FAT
List of Challenging Experiments (Indicative)
1. Setting up a neural network in memory 6 hours
2. Backpropagation training experiment 6 hours
3. Recurrent NN 6 hours
4. Experiment: Object recognition 6 hours
5. Experiment: Highway sign recognition 6 hours
Total Laboratory Hours 30 hours
Mode of assessment: Continuous assessment and FAT
Recommended by Board of Studies 24.06.2020
Approved by Academic Council No. 59 Date 24-09-2020

M.Sc. Data Science Page 58

 Course code Course title L T P J C
MAT6008 Artificial intelligence for Data Science 2 0 2 0 3
Pre-requisite NIL Syllabus version
1.0
Course Objectives:
 The main purpose of this course is to provide the most fundamental knowledge to the
students so that they can understand AI.
 To provide the foundations for AI problem-solving techniques and knowledge
representation formalisms.
Expected Course Outcome:
On completion of the course, students will be able to
 Ability to identify and formulate appropriate AI methods for solving a problem
 Ability to implement AI algorithms
 Ability to Identify the type of AI problem (search, inference, decision making under
uncertainty, game theory, etc).
 Ability to compare the difficulty of different versions of AI problems, in terms of
computational complexity and the efficiency of existing algorithms.
Student Learning Outcomes (SLO): 2, 7, 9, 18
[2] Having a clear understanding of the subject interrelated concepts and of up-to-date issues
[7] Having computational thinking (Ability to translate vast data into abstract concepts and to
Understand database reasoning).
[9] Having problem-solving ability- solving social issues and engineering problems
[18] Having critical thinking and innovative skills
Module:1 Introduction 3 hours
The AI problems, AI technique, philosophy and development of Artificial intelligence.
Module:2 Problem Spaces and Search 4 hours
State-space search, Uninformed and informed search techniques: BFS, A*, variations of A*. Local
search and optimization: hill-climbing, simulated annealing.
Module:3 Adversarial Search and Game Playing 4 hours
Minimax algorithm, alpha-beta pruning, stochastic games, Constraint- satisfaction problems.
Module:4 Knowledge and Reasoning 5 hours
Logical agents, Propositional logic, First-order logic, Inference in FoL: forward chaining, backward
chaining, resolution, Knowledge representation: Frames, Ontologies, Semantic web and RDF.
Module:5 Introduction to PROLOG 4 hours
Facts and predicates, data types, goal finding, backtracking, simple object, compound objects, use
of cut and fail predicates, recursion, lists, simple input/output, dynamic database.
Module:6 Uncertain knowledge and reasoning 4 hours
Probabilistic reasoning, Bayesian networks, Fuzzy logic
Module:7 Natural Language Processing 4 hours
An Introduction to Natural language Understanding, Perception, Learning.
Module:8 Contemporary issues (Industry Expert Lecture) 2 hours
Research and Analytical problems related to data science.
Total Lecture hours: 30 hours
Text Book(s)
 Elaine
1 Rich, Kevin Knight, Artificial Intelligence, 3/Ed., Tata McGraw Hill, 2017.

M.Sc. Data Science Page 59

 Dan
. W. Patterson, Introduction to AI and ES, Pearson Education, 2015.
 2
.
Reference Books
 Deepak
1 Khemani, Artificial Intelligence, Tata Mc Graw Hill Education, 2017.
Stuart
. Russel, Peter Norvig, Artificial Intelligence, 3/Ed, Perason, 2015.
 N.P.
2 padhy: Artificial Intelligence and Intelligent Systems, Oxford Higher Education,
OxfordUniversity
. Press, 2005.
 3Ivan Bratko, PROLOG Programming, 4/Ed. Pearson Education, 2020.
.

4
.
Mode of Evaluation: CAT, Quiz, Digital Assignment and FAT.
List of Challenging Experiments (Indicative)
1 Study of facts, objects, predicates and variables in PROLOG 2 hours
2 Study of Rules and Unification in PROLOG 2 hours
3 Study of “cut” and “fail” predicate in PROLOG 2 hours
4 Study of arithmetic operators, simple input/output and compound goals in 4 hours
PROLOG
5 Study of recursion in PROLOG 4 hours
6 Study of Lists in PROLOG 2 hours
7 Study of dynamic database in PROLOG 2 hours
8 Study of string operations in PROLOG (Implement string operations like 4 hours
substring, string position, palindrome etc.)
9 Write a prolog program to maintain family tree 4 hours
10 Write a prolog program to implement all set operations (Union, intersection, 4 hours
complement etc.)
Total Laboratory hours 30 hours
Mode of Evaluation: Continuous assessment and FAT.
Recommended by Board of Studies 24.06.2020
Approved by Academic Council No. 59 Date 24-09-2020

M.Sc. Data Science Page 60

 Course code Course title L T P J C
MAT6011 Statistical Quality Control 3 0 2 0 4
Pre-requisite NIL Syllabus version
1.0
Course Objectives:
 To understand different control charts for analyzing industrial quality experiments.
 To amalgamate the intellectual facts of the quality characteristics to implement in the Industrial
experiments scientifically.
 To link and analyse the various sampling schemes to find the plan for quality inspection.
Expected Course Outcome:
On completion of the course, students will be able to
 understand the fundamental advantages and apply essential of Control charts
 apply appropriate Charts for the industrial experiments.
 apply some standard distributions for construction of sampling plans.
 able to construct the AOQL plans for normal inspection scheme.
 learn and apply variance transformation techniques.
 understand the difference between sampling plans for attributes and variables.
Student Learning Outcomes (SLO): 2, 7, 9, 18
[2] Having a clear understanding of the subject interrelated concepts and of up-to-date issues
[7] Having computational thinking (Ability to translate vast data into abstract concepts and to
Understand database reasoning).
[9] Having problem-solving ability-solving engineering problems.
[18] Having critical thinking and innovative skills
Module:1 Control Charts 4 hours
Introduction to Quality control; control charts for mean – CUSUM chart – technique of V-mask –
Weighted Moving average charts – multivariate control charts – Hotelling’s T2-control charts and
Economic design of X-bar chart.
Module:2 Process Capability analysis 8 hours
Process Capability analysis: Meaning, Estimation technique for capability of a process –Capability
Indices: Process capability ratios Cp; Cpk, Cpm, Cmk, Cpc – Process capability analysis using a
control chart – Process capability analysis using design of experiments.
Module:3 Acceptance Sampling 6 hours
Acceptance sampling – Terminologies – Attribute sampling plan by attributes – Single sampling plan
and Double sampling plan – OC, ASN, AOQ, AOQL and ATI curves –MILSTD -105E Tables.
Module:4 Acceptance sampling variables 6 hours
Acceptance sampling variables for process parameter – Sequential plans for process parameter (σ
known and unknown) – Sampling variables for proportion non-conforming – 𝑋 method, K method.
Module:5 Double Sampling methods 6 hours
Double specification limits – M-method, Double sampling by variables - MILSTD -414 Tables –
Continuous Sampling plan – CSP-1, CSP-2, CSP-3, Wald and Wolfowitz SP-A.
Module:6 Attribute Sampling plans 6 hours
Producers risk, Consumers Risk, designing single sampling plan for stipulated Producers and
consumers risk,OC curves under Normal,Tightened and reduces inspection,Single, Double and
Multiple sampling plans in AQL systems.
Module:7 Six-Sigma 7 hours
Concept of six sigma, methods of six sigma, DMAIC methodology, DFSS methodology, six-sigma
control chart, case studies.

M.Sc. Data Science Page 61

Module:8 Contemporary issues 2 hours
Research and Analytical problems on various applications of the industrial issues.
Total Lecture hours 45 hours

Text Book(s)
 1Eugene L.Grant Richard S. Leavenworth, Statistical Quality Control,7 edition,McGraw Hill
Education,India, 2017.
 2Douglas C. Montgomery, Introduction to Statistical Quality Control, Seventh Edition, John
Wiley and Sons, New York. 2013.
Reference Books
 1Edward G. Schilling, Dean V. Neubauer, Acceptance Sampling in Quality Control, Second
Edition, Taylor & Francis, 2009.
 2Poornima M.Charantimath,Total quality Management, 3/e, Pearson India Limited, 2017.
Mode of Evaluation: Continuous assessment, Quiz, Digital Assignment and FAT.
List of Challenging Experiments (Indicative)
1 Mean and Range charts: Experimental control charts for process control. 4 hours
2 Control chart for nonconformities. 4 hours
3 A control chart for nonconformities per unit with variable subgroup size. 4 hours
4 C chart used to control errors on forms. 2 hours
5 Acceptance decisions based on plotted frequency distributions. 4 hours
6 AOQL inspection to produce quality improvement. 4 hours
7 Construction of rectifying inspection using AOQL normal inspection plans 4 hours
8 Acceptance sampling under standard sampling plans. 4 hours
Total Laboratory hours 30 hours
Mode of Evaluation: Continuous assessment and FAT
Recommended by Board of Studies 24.06.2020
Approved by Academic Council No. 59 Date 24-09-2020

M.Sc. Data Science Page 62

 Course code Course title L T P J C
MAT6009 Design and Analysis of Experiments 3 0 2 0 4
Pre-requisite MAT5013-Statistical Inference Syllabus version
1.0
Course Objectives
 Describe how to design experiments, carry them out, and analyze the data they yield.
 Construct appropriate experimental designs for given problems: sample size
determination, choice of levels of variables, designs with restrictions on randomization,
utility functions for measuring design objectives, use of simulation to characterize
properties of designs.
Expected Course Outcome
 Describe the purpose of robust construction and how it is applied in experimental design
 To formulate and validate the experimental designs in agricultural, medical, biomedical
projects
 Avails them to fetch the background concepts of Model formulation and validation
 To accomplish research-oriented concepts given for statistical techniques required for
experimental designs
Student Learning Outcomes (SLO) 2, 7, 9, 18
[2] Having a clear understanding of the subject interrelated concepts and of up-to-date issues
[7] Having computational thinking (Ability to translate vast data into abstract concepts and to
Understand database reasoning)
[9] Having the problem-solving ability for social issues and engineering problems
[18] Having critical thinking and innovative skills
Module:1 Basic Principles of Experimental design 2 hours
Strategy of Experimentation - Applications of Experimental Design – Basic Principles –
Guidelines for designing experiments.
Module:2 Simple Comparative Experiments 8 hours
Principles of scientific experimentation – Basic Designs: Completely Randomized Design (CRD),
Randomized Block Design (RBD) and Latin Square Design (LSD) – Analysis of RBD (with one
observation per cell, more than one but equal number of observations per cell).
Module:3 Analysis of Co-variance 6 hours
Multiple Comparisons – Multiple Range Tests - Analysis of Covariance – Construction of
Orthogonal Latin Square – Analysis of Graeco Latin Squares.
Module:4 Factorial experiments 8 hours
Factorial experiments - 22, 23 and 32, 33 experiments and their analysis - Fractional replication in
Factorial Experiments.
Module:5 Confounding 6 hours
Necessity of confounding, Types of confounding, complete and partial confounding in 2 , 32n

and 33- factorial designs, Analysis of confounded factorial designs; Fractional Replication.
Module:6 Balanced Incomplete Block design 6 hours
Balanced Incomplete Block Design (BIBD)– Types of BIBD – Simple construction methods –
Concept of connectedness and balancing – Intra Block analysis of BIBD.
Module:7 Partially Balanced Incomplete Block design 6 hours
Partially Balanced Incomplete Block Design with two associate classes – intra block analysis -

M.Sc. Data Science Page 63

Split plot and strip plot design and their analysis.
Module:8 Contemporary issues (Industry Expert Lecture) 2 hours
Research and Analytical problems related to
Total Lecture hours 45 hours
Text Book(s)
 1Douglas C. Montgomery, Design and Analysis of Experiments, 9h Edition, John Whiley
 2and Sons, 2017.
Angela Dean and Daniel Voss Danel Draguljić, Design and Analysis of Experiments, 2nd
Edition, Springer International Publishing AG, 2017.
Reference Books
 1Das M.N. and Giri N.C., Design and Analysis of Experiments, 3rd Edition, New Age
International (P) Ltd 2017
 2John Lawson, Design and Analysis of Experiments with R, 1st Edition, CRC Press, 2015.
Mode of Evaluation: CAT, Quiz, Digital Assignment and FAT
List of Challenging Experiments (Indicative)
1 One-way analysis of variance - CRD 2 hours
2 RBD & LSD analysis of one and two observations 4 hours
3 Analysis of Co-variance CRD & RBD 4 hours
4 Analysis of Graeco Latin Squares 4 hours
5 Factorial experiments 4 hours
6 Confounding 4 hours
7 BIBD and PBIBD 4 hours
8 Split plot design 4 hours
Total Laboratory hours 30 hours
Mode of Evaluation: Continuous assessment and FAT
Recommended by Board of Studies 24.06.2020
Approved by Academic Council No. 59 Date 24-09-2020

M.Sc. Data Science Page 64