Recommender Systems

Recommender Systems (RecSys) are ubiquitous and have become inseparable parts of our everyday lives. They are central to our experience with the digital world in everything we do and every service we consume. They help us find our favourite items to purchase, our friends on social networks, our favourite movies to watch, music to listen to, and books to read. Nowadays, RecSys have numerous applications that transcend these classic taste-driven domains of social media and entertainment and are revolutionising several sectors. Education, industriy, healthcare, tourism, transport and logistics are among the areas where the applications of RecSys have gained momentum.
Read More    Enroll Now
Explore

Recommender Systems: an Overview (Second Edition)

This course is designed to get you introduced to Recommender systems and provide you with the state-of-the-art tools and algorithms to design and build RecSys engines. By the end of this course you will be able to:

  • Develop foundational knowledge on Recommendation systems.
  • Understand a wide variety of Recommendation system algorithms.
  • Understand how to design and evaluate Recommendation systems in different application domains.
  • Apply the learned skills to design Recommendation engines using real datasets, evaluate the designed engines and report results.

Checkout our Blog to see featured student projects from the first edition of the course.

First Edition


A compressed (one day) version of this course is also avialbe at the 7th Summer School on Computational Interaction.


Computational Methods for Designing Recommender Systems

(June 19 – 23, 2023, University of Michigan in Ann Arbor, Michigan, USA).

Program

May 22 - 26,2023, Belval campus (MSA), University of Luxembourg
- Limited number of participants.
Enrolment via Moodle opens on 30/03/2023


Enroll Now
Day 1

Introduction to Recommender Systems

  • Personalisation: The Big Picture
  • Overview of SOTA RecSys Methods (ML, DL, RL) based approaches.

    • Day 2

    Content-Based (CB) & Collaborative Filtering (CF)

  • Lecture
  • Invited talk
  • Hands-on Case-Studies (CB & CF)

    • Day 3

    Hybrid Approaches & Reinforcement Learning (RL) based RecSys

  • Lecture
  • Invited talk
  • Hands-on Case-Studies (Hybrid & RL)

    • Day 4

    Modern RecSys & Open Chalenges

  • Lecture
  • Course project topics
  • Hands-on (Course Project)

    • Day 5

    Project presentation & Closing

  • Invited talk
  • Student Presentations

    • Meet Our Speakers

    Course Instructor

    Dr. Bereket YILMA

    University of Luxembourg, Luxembourg


    Course Instructor

    Invited Talks

    Invited talk
    Generating Recommendation Explanations with Transformer and Pre-trained Model

    Dr. Lei Li

    Hong Kong Baptist University (HKBU) &
    Rutgers University, New Jersey, USA


    Dr. Lei Li is a Post-doctoral Research Fellow advised by Dr. Li Chen at the Department of Computer Science, Hong Kong Baptist University. His research interests lie in recommender systems and natural language processing. Recently, he has been investigating pre-trained language models for recommender systems (such as explanation generation and sequential recommendation), and his research has been supported by Hong Kong Research Grants Council (RGC) since 2022. He is currently visiting Rutgers University, and doing research with Dr. Yongfeng Zhang. Previously, he obtained his Ph.D. degree from Hong Kong Baptist University, where he was involved in explainable recommendation research. His major research outcomes are integrated into a small ecosystem for recommender systems-based natural language generation, which includes benchmark datasets, evaluation metrics and representative models, and is open-sourced at https://github.com/lileipisces/NLG4RS.


    Title: Generating Recommendation Explanations with Transformer and Pre-trained Model


    • ©2023 Bereket A. YILMA.