GNN model adapts recommendations for individuals and groups
A Flexible Recommendation System for Individuals and Groups
Information Retrieval
Summary
Recommending items to groups is tricky because people’s tastes can change when they are together. The authors present a new method that learns each person’s preferences both alone and as part of a group. It compares these preferences to understand how people behave in groups and then uses this to offer better recommendations. Their system works well for both individuals and groups, solving some common problems with older methods.
What this means in practice
- •For online retailers: Tailor product suggestions for single shoppers or shopping groups using dynamic user behavior modeling.$Commercial implications: Enables unified, precise recommendations for individual and group buyers, improving sales and user experience.
- •For streaming service developers: Create flexible content recommendations that adapt to both solitary viewers and groups watching together.
Authors
Yacine Mokhtari, Grégory Smits
Abstract
Group recommender systems typically rely on either aggregating individual preferences or treating groups as distinct meta-users. However, these methods often suffer from static aggregation strategies or data sparsity issues within group histories. This paper introduces a novel approach, that relies on a GNN-based architecture to learn a dual representation of each user's preferences, capturing their behavior as an independent individual from one side and as a member of a collective from the other side. By performing a differential analysis of these individual and group-oriented preferences, our system then determines the behavioral profile of each user when joining a group. Finally, specific preference aggregation strategies are defined to cope with the behavioral profiles of the users composing a group. Consequently, the system is equally capable of delivering precise recommendations to individuals and to arbitrary groups, effectively unifying the two traditional paradigms of recommendation. Experiments on synthetic data simulating diverse group settings and behaviors confirm the flexibility and relevance of the proposed approach compared to state-of-the-art methods.