From Sequences to Profiles: Generating Universal Behavioral Profiles exploiting Recurrent Neural Networks
Simone Colecchia, Mauro Orazio Drago, Jihad Founoun, Paolo Gennaro, Ernesto Natuzzi, Luca Pagano, Sajjad Shaffaf, Giuseppe Vitello, Andrea Pisani, Maurizio Ferrari Dacrema · 2025
This paper presents the solution developed by the EmbedNBreakfast team for the ACM RecSys Challenge 2025, for the construction of Universal Behavioral Profiles: general-purpose user representations derived from historical interactions. We propose a representation-learning framework that combines Recurrent Neural Networks, attention mechanisms, and collaborative filtering to jointly optimize embeddings across several predictive objectives. Our method achieved 2nd place on the Academic Leaderboard and 5th Overall, demonstrating the effectiveness of unified, representation-based modeling for diverse behavior prediction tasks.