2024/2025

Recommender Systems

Type: Mago-Lego

Delivered by: Department of Business Informatics

When: 1, 2 module

Open to: students of one campus

Instructors: Seungmin Jin

Language: English

ECTS credits: 6

Course Syllabus

Abstract

The course is aimed at the formation of sufficient knowledge, skills and competencies for the construction of recommender systems. The course is applied one and covers all advanced topics necessary for successful application both in industry and in academic research. Students of the course will learn the correct formalization of the task, the choice of ranking functions and metrics, the implementation of recommendation ML models in Python - from simple collaborative filtering to modern neural networks.

Learning Objectives

• Formation of knowledge, skills and development skills of recommender systems for research or industrial purposes.

Expected Learning Outcomes

• Explain the key concepts underlying the recommendations
• Demonstrate skills in using meaningful summary statistics
• Сompute product association recommendations
• Build a profile of personal interests
• Build recommendations based on collaborative filtering
• Combine collaborative filtering and content-based recommendations
• Explain the difference between user-based and item-based approaches
• Choose appropriate algorithms for uplift modeling
• Give a definition of the term "uplift"

Course Contents

• Introduction to Recommender Systems
• Content-Based Filtering
• Collaborative Filtering
• Hybrid Recommendation System
• Deep Learning Recommender Systems

Assessment Elements

• Homework
  Building a recommender system of a given type based on the provided dataset
• Exam
  Test with different types of questions
• Project 1
  As part of the project, students are invited individually or in small groups (no more than three people) to choose a dataset and demonstrate the skills of analyzing a data set and implementing a recommender system based on this data.
• Project 2
  Student competes their own RecSys model using LLMs

Interim Assessment

• 2024/2025 2nd module
  0.4 * Exam + 0.2 * Homework + 0.25 * Project 1 + 0.15 * Project 2

Bibliography

Recommended Core Bibliography

• Parul Aggarwal, Vishal Tomar, & Aditya Kathuria. (2017). Comparing Content Based and Collaborative Filtering in Recommender Systems. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.32D5064E
• Rajaraman, A., & Ullman, J. D. (2012). Mining of Massive Datasets. New York, N.Y.: Cambridge University Press. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=408850

Recommended Additional Bibliography

• Manouselis, N., Drachsler, H., Verbert, K., Duval, E. Recommender Systems for Learning. – Springer, 2013. – ЭБС Books 24x7.

Authors

• Джин Сеунгмин -