Recommender System Syllabus

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 3

Course code Course title L T P J C

CSE4077 Recommender Systems 3 0 0 4 4


Pre-requisite None Syllabus version
v. 1.0
Course Objectives:
12. To provide a foundation of recommender systems concepts
13. To expose to a variety of recommender systems algorithms
14. To provide a knowledge on the different evaluation methods of Recommender Systems
15. To build up the capability to develop a recommender system solution

Expected Course Outcome:


1. Characterize different types of Recommender Systems, map a given real world problem to
appropriate model, understand and identify the stages and issues in the deployment of the system
2. Apply principles and techniques of recommender systems in applications related to recommender
systems design and analysis
3. Analyze and evaluate various recommender algorithms
4. Implement appropriate recommender system for real world applications

Student Learning Outcomes (SLO): 1, 2, 3, 8, 12, 13


1. Having an ability to apply mathematics and science in engineering applications
2. Having a clear understanding of the subject related concepts and of contemporary issues
3. Having Sense-Making Skills of creating unique insights in what is being seen or observed
(Higher level thinking skills which cannot be codified)
8. Having Virtual Collaborating ability
12. Having adaptive thinking and adaptability
13. Having cross cultural competency exhibited by working in teams
Module:1 INTRODUCTION 6 hours
Basic Models – Domain Specific Challenges – Applications - Neighborhood-Based Collaborative
Filtering - Rating Matric - Predicting Ratings with Neighborhood-Based Methods - Clustering -
Dimensionality Reduction and Neighborhood Methods - A Regression Modeling View of
Neighborhood Methods - Graph Models For Neighborhood-Based Methods

Module:2 MODEL-BASED COLLABORATIVE 6 hours


FILTERING
Decision and Regression Trees - Rule-Based Collaborative Filtering – Associative Rule based
Filtering - Naive Bayes Collaborative Filtering - Latent Factor Models -Integrating Factorization
and Neighborhood Models

Module:3 CONTENT-BASED RECOMMENDER 6 hours


SYSTEMS
Basic Components of Content-Based Systems - Preprocessing and Feature Extraction - Learning
User Profiles and Filtering - Content-Based Versus Collaborative Recommendations - Using
Content-Based Models for Collaborative Filtering

Module:4 KNOWLEDGE-BASED RECOMMENDER 6 hours


SYSTEMS
Constraint-Based Recommender Systems - Case-Based Recommenders - Persistent Personalization
in Knowledge-Based Systems
Module:5 CONTEXT SENSITIVE RECOMMENDER 6 hours
SYSTEMS
Context-Sensitive Recommender Systems - The Multidimensional Approach -Contextual Pre-
filtering: A Reduction-Based Approach - Post-Filtering Methods - Contextual Modeling

Module:6 STRUCTURAL RECOMMENDATIONS IN 7 hours


NETWORKS
Ranking Algorithms - Recommendations By Collective Classification - Recommending Friends:
Link Prediction - Social Influence Analysis And Viral Marketing - Social And Trust-Centric
Recommender Systems - Multidimensional Models For Social Context - Network-Centric And
Trust-Centric Methods - User Interaction In Social Recommenders

Module:7 EVALUATING RECOMMENDER 6 hours


SYSTEMS
Evaluating Recommender Systems - Evaluation Paradigms - Design Issues in Offline Recommender
Evaluation - Accuracy Metrics in Offline Evaluation

Module:8 Contemporary issues: 2 hours

Total Lecture Hours: 45 hours

Reference Books
1. Charu C. Aggarwal, “Recommender Systems : The Textbook”, First Ed., Springer, 2016.
2. K. Falk, Practical recommender systems. Shelter Island, NY: Manning Publications Company,
2019.( ISBN : 9781617292705)
3. D. Jannach, Recommender systems. New York: Cambridge University Press, 2011. (ISBN:
9780521493369)
4. D. Agarwal and B. Chung-Chen, Statistical methods for recommender systems. New York,
NY: Cambridge University Press, 2016.( ISBN: 9781107036079)
5. R. Banik, Hands-On Recommendation Systems with Python. Birmingham, United Kingdom:
PACKT Publishing Limited, 2018.( ISBN: 9781788993753)
6. S. Berkovsky, I. Cantador and D. Tikk, Collaborative Recommendations: Algorithms,
Practical Challenges and Applications. UK: World Scientific Publishing Co, 2019.(ISBN:
9789813275348)
Mode of Evaluation: Continuous Assessment Test (CAT), Quizzes, Assignments & Final
Assessment Test (FAT)
List of Projects (Indicative)
1. Movie Recommendation - Dataset: Netflix Prize and MovieLens Datasets
2. Search + Recommendation System -- Dataset: BestBuy
3. Predict Influencers in the Social Network - Dataset: PeerIndex
4. Music Recommender System – Dataset :
5. Recommendation System based on Graph Database
6. Songs Recommendation System in Android
7. YouTube Ad Recommendation
8. Recommender system for recipes with social elements
9. Recommender System for Fonts
10. Recommender Systems for E-learning
11. Recommendation system for Tourist
12. RECOMMENDATIONS FOR SKIN CARE COSMETICS
13. Real estate location recommender system
14. Recommender system for Favourite TV Show for better user Experience
15. Books Recommender System
16. Social Network Recommender System for Infogram
17. Recommending Legislative Candidates Through Bi-Dimensional Political Modelling
18. Recommendation system for Decor Home & Offices
19. Recommender System for Public E-Services
20. Camera settings recommender system for photographers
21. A Course Recommender System for VIT Students
Mode of assessment: Reviews
Recommended by Board of Studies 30-10-2020
Approved by Academic Council No. 60 Date 5-11-2020

You might also like