Sequence-aware Recommendation Tutorial

Welcome to the page of the Tutorial on Sequence-Aware Recommenders that will be hold Tuesday 2nd October 2018 at ACM RecSys 2018 in Vancouver (Canada).

For the latest news about the organization of the tutorial, we warmly suggest you to check the official page of the conference.

Where and when

Check out the Conference Program

Abstract

Most works in the field of recommender systems are focused on the matrix completion problem, where for each user-item-pair only one interaction (e.g., a rating) is considered. In many application domains, however, multiple user-item interactions of different types can be recorded over time, and this information can be used to build richer individual user models and to discover additional behavioral patterns that can be leveraged in the recommendation process.

In this tutorial, we review existing works that consider information from such sequentially-ordered user-item interaction logs in the recommendation process. Based on this review, we describe a categorization of the corresponding recommendation tasks and goals, present the algorithmic solutions in depth, discuss methodological approaches when benchmarking what we call sequence-aware recommender systems, and outline open challenges in the area.

Instructions for the hands-on session

The code for the hands-on session is hosted on GitHub at: https://github.com/mquad/sars_tutorial

Please make sure to follow the instructions and setup the workspace **BEFORE** the tutorial begins!

Please use Github to ask questions or to report issues about the code.

Other material

• Survey paper "Sequence-Aware Recommender Systems", Quadrana et al., ACM CSUR, 2018 preprint ACM DL
• Slides are available on SlideShare at this page

Authors and contacts

Feel free to reach out for any questions or comments! Thank you for attending the tutorial! :-)