Skip to main navigation Skip to search Skip to main content

RecSys Challenge 2025: Universal Behavioral Profiles for Recommender Systems

  • Jacek Dabrowski*
  • , Maria Janicka
  • , Lukasz Sienkiewicz
  • , Gergely Stomfai
  • , Dietmar Jannach
  • , Francesco Barile
  • , Marco Polignano
  • , Claudio Pomo
  • , Abhishek Srivastava
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

Abstract

The RecSys Challenge 2025 promotes a unified approach to behavior modeling by introducing Universal Behavioral Profiles. These user representations encode essential aspects of past interactions and are designed for universal applicability across different downstream tasks, thereby promoting generalization across applications and addressing the need for portable and efficient recommender systems.The participants task was to create universal user embeddings from detailed e-commerce activity logs. These embeddings were then fed into a small neural network to predict customer behavior in subsequent timeframes. The provided challenge dataset was large and sparse, requiring innovative methods to leverage the available interaction data in an effective way. Overall, the challenge was highly attractive with 400 teams participating in the competition.
Original languageEnglish
Title of host publicationProceedings of the Nineteenth ACM Conference on Recommender Systems
Place of PublicationNew York, NY, USA
PublisherAssociation for Computing Machinery
Pages1389–1393
Number of pages5
ISBN (Print)9798400713644
DOIs
Publication statusPublished - 2025

Publication series

SeriesRecSys : Proceedings of the ACM Conference on Recommender Systems

Keywords

  • Recommender Systems
  • Evaluation
  • Universal Behavior Modeling

Fingerprint

Dive into the research topics of 'RecSys Challenge 2025: Universal Behavioral Profiles for Recommender Systems'. Together they form a unique fingerprint.

Cite this