The ACM RecSys Challenge is an international competition organised by the ACM RecSys Conference in cooperation with a sponsoring company. Over 100 teams from universities and large companies from all over the world challenge each other to find solutions for real problems related to recommender systems (content filtering software that create customised user-specific recommendations to help users in their choices). During the competition, participants apply various data science techniques, such as machine learning, data mining, game theory and soft computing. The best teams are invited to present their work at the conference.

The team from Politecnico

Every year since 2016, a new team has represented the Politecnico at the ACM RecSys Challenge: ten students from the Recommender Systems course, coordinated by Professor Maurizio Ferrari Dacrema, researcher at the Department of Electronics, Information and Bioengineering, tackle the challenge, from online advertising to fashion advice and social media engagement.

Our Results

2023: Best Academic Team at the RecSys Challenge, sponsored by ShareChat
Paper: Pessimistic Rescaling and Distribution Shift of Boosting Models for Impression-Aware Online Advertising Recommendation

2022: 9th place at the RecSys Challenge, sponsored by Dressipi
Paper: Lightweight model for session-based recommender systems with seasonality information in the fashion domain

2021: Best Academic Team at the RecSys Challenge, sponsored by Twitter
Paper: Lightweight and Scalable Model for Tweet Engagements Predictions in a Resource-constrained Environment

2020: 4th place at the RecSys Challenge, sponsored by Twitter
Paper: Multi-Objective Blended Ensemble For Highly Imbalanced Sequence Aware Tweet Engagement Prediction

2019: 10th place at the RecSys Challenge, sponsored by Trivago
Paper: Leveraging laziness, browsing-pattern aware stacked models for sequential accommodation learning to rank

2018: 2nd place in the RecSys Challenge, sponsored by Spotify
Paper: Artist-driven layering and user’s behaviour impact on recommendations in a playlist continuation scenario

2017: 1st place on the offline phase and 2nd on the online phase at the RecSys Challenge, sponsored by Xing
Paper: Content-Based approaches for Cold-Start Job Recommendations

2016: Best Academic Team, 4th place overall, at the RecSys Challenge, sponsored by Xing
Paper: RecSys Multi-Stack Ensemble for Job Recommendation