Group Recommendation

Group recommendation aims to provide personalized recommendations to groups of users, considering individual preferences while generating a collective outcome. Current research focuses on improving the accuracy of group preference aggregation, often employing attention mechanisms, hypergraph neural networks, and self-supervised learning techniques to better capture both individual and shared interests, even in scenarios with limited group interaction history. These advancements address challenges like data sparsity and cold-start problems, leading to more effective and personalized recommendations in various applications, such as e-commerce and meal planning. The field's impact extends to enhancing user experience and decision-making in collaborative settings.