RecSys Challenge 2025

The RecSys 2025 Challenge is organized by Synerise (Poland), the sponsoring company, in partnership with an academic team consisting of Francesco Barile (Maastricht University, the Netherlands), Marco Polignano (University of Bari Aldo Moro, Italy), Claudio Pomo (Politecnico di Bari, Italy), and Abhishek Srivastava (IIM Visakhapatnam, India). The Synerise organizing team includes Maria Janicka, Jacek Dabrowski, Łukasz Sienkiewicz, and Dietmar Jannach (Klagenfurt University, Austria), who serves as Faculty Advisor for sponsor company. The challenge data is provided by Synerise.

The challenge is designed to promote a unified approach to behavior modeling. Many modern enterprises rely on machine learning and predictive analytics for improved business decisions. Common predictive tasks in such organizations include recommendation, propensity prediction, churn prediction, user lifetime value prediction, and many others. A central piece of information that is used for these predictive tasks are logs of past behavior of users e.g., what they bought, what they added to their shopping cart, which pages they visited. Rather than treating these tasks as separate problems, a unified modeling approach is proposed.

To achieve this, the concept of Universal Behavioral Profiles is introduced. These are user representations that encode essential aspects of each individual’s past interactions. Such profiles are designed to be universally applicable across multiple predictive tasks, such as churn prediction and product recommendations. By developing representations that capture fundamental patterns in user behavior, models can generalize effectively across different applications. The objective of this challenge is to develop Universal Behavioral Profiles based on the provided data, which includes various types of events such as product buy, add to cart, remove from cart, page visit, and search query. These user representations will be evaluated based on their ability to generalize across a range of predictive tasks. The task of the challenge participants is to submit user representations, which will serve as inputs to a simple neural network architecture. Based on the submitted representations, models will be trained on several tasks. The final performance score will aggregate results from all tasks. Iterated model training and evaluation will be performed automatically upon submission, and the task of the participants is to submit universal user representations.

A detailed description of the challenge is available on the RecSys Challenge 2025 website.
Accepted contributions will be presented at the RecSys Challenge Workshop during the 19th ACM Recommender Systems Conference in September 2025 in Prague, Czech Republic.

Challenge Organizers