National Computing Education Accreditation Council

NCEAC NCEAC.FORM.0
01-D
COURSE DESCRIPTION FORM

INSTITUTION National University of Computer and Emerging Sciences (NUCES-FAST)

PROGRAM (S) TO BE EVALUATED BS (CS)

A. Course Description

Course Code CS-4053

Course Title Recommender Systems
Credit Hours 3+0
Prerequisites by -
Course(s) and
Topics
Assessment Midterm I: 15 marks
Instruments with Midterm II: 15 marks
Weights Course Project: 10 marks
(homework, quizzes,
Assignments: 5 marks
midterms, final,
programming Quizzes: 5 marks
assignments, lab Finals: 50 marks
work, etc.)
Course
Coordinator
URL (if any) -
Current Catalog -
Description
Textbook (or Recommender systems handbook, by F. Ricci, L Rokach, B. Shapira and P.B. Kantor,
Laboratory Manual (Springer)
for Laboratory
Courses)
Reference Material To be provided in the form of slides and tutorials.

Resources link: TBA

1
NCEAC.FORM.001.D
 National Computing Education Accreditation Council
NCEAC NCEAC.FORM.0
01-D
Course Goals
A. Course Learning Outcomes (CLOs)

1. Describe different techniques in making automatic personalized recommendations

in various scenarios
[Bloom's Taxonomy Level: 3, Learning Domain: Cognitive]
2. Solve mathematical optimization problems pertaining to recommender systems
[Bloom's Taxonomy Level: 3, Learning Domain: Cognitive]
3. Discuss how a recommender system should be evaluated in terms of the system's
performance and the user's satisfaction with the system
[Bloom's Taxonomy Level: 6, Learning Domain: Cognitive]
4. Learn about advanced topics and current applications of recommender systems in
realms like social networks and communities
[Bloom's Taxonomy Level: 6, Learning Domain: Cognitive]

B. Program Learning Outcomes

CLO-1
1. Computing Apply knowledge of mathematics, natural
Knowledge sciences, computing fundamentals, and a
computing specialization to the solution of
complex computing problems.
CLO-2
2. Problem Identify, formulate, research literature, and analyze
Analysis complex computing problems, reaching
substantiated conclusions using first principles of
mathematics, natural sciences, and computing
sciences.
CLO-3
3.Design/Develop Design solutions for complex computing problems
Solutions and design systems, components, and processes
that meet specified needs with appropriate
consideration for public health and safety, cultural,
societal, and environmental considerations.
CLO-4
4. Investigation Conduct investigation of complex computing
& problems using research-based knowledge and
Experimentation research based methods

2
NCEAC.FORM.001.D
 National Computing Education Accreditation Council
NCEAC NCEAC.FORM.0
01-D
C. Relation between CLOs and PLOs
(CLO: Course Learning Outcome, PLOs: Program Learning Outcomes)
PLOs

1 2 3 4 5 6 7 8 9 10 11 12

1 ✓
C
L
2 ✓
O 3 ✓
s
4 ✓

Topics Covered in
the Course, with 1. Topics to be covered:
Number of Lectures
on Each Topic No. of Contact
List of Topics
(assume 16-week Weeks Hours CLO
instruction and one- Introduction to Recommender System
hour lectures) (RS), goals, applications, and taxonomy
of RS techniques
Recommender Systems Function, Data
and Knowledge Sources, 1 3 1
Recommendation Techniques
Applications and Evaluations, RS and
Human Interaction

Introduction and basic components of

Content-based recommendation system
1 3 1
State of the art of content-based RS –
Item Representation, methods for
learning user profiles
Neighborhood based methods, similarity
measures, Long-tail principle, and curse 1 3 1
of dimensionality
Collaborative Filtering, types of rankings,
1 3 1
cold start problem and serendipity
Content-based Filtering, Content-based
1 3 2
vs CF recommendations
Mid-term I

Probabilistic Naïve Bayes Collaborative

1 3 1
Filtering
Knowledge-based recommendations,
Constraint-based and case-based 1 3 1
recommendation system
Case study
1 3 1
3
NCEAC.FORM.001.D
 National Computing Education Accreditation Council
NCEAC NCEAC.FORM.0
01-D
Matrix Factorization
1 3 3
Mid-term II

Social tagging
1 3 4
Neural Recommender systems, Case
study, state-of-the-art neural based 1
methods for RS
Generative recommendations, case study
1 3 4
State-of-the-art generative based methods
1 3 4
for RS
Context-aware RS, Evaluation measures
for recommendation systems and 1 3 3
performance issues
Final Exam

Total
16 48 -

Laboratory The lab work to be done in the course include hands-on exercises for the following topics:
Projects/Experiments ▪ Simple CF Recommender System for products recommendation
Done in the Course ▪ Feature selection
▪ Social media recommendation

One group project will be submitted by the students in the penultimate week of the
semester.

Programming Assignments related to collaborative filtering, similarity measures, knowledge-based

Assignments Done in recommendations, and evaluation techniques
the Course
Class Time Spent on Theory Problem Analysis Solution Design Social and Ethical
(in credit hours) Issues
15 15 13 0
Oral and Written A project report detailing the problem, tools, methods used in the course project to be
Communications submitted by every student.

Instructor Name: Syed Zain Ul Hassan

Instructor Signature: ____________________________

Dated: 22nd August 2024

4
NCEAC.FORM.001.D