GEVR: An Event Venue Recommendation System for Groups of Mobile Users
This addresses the problem of group event planning for mobile users, offering a novel approach that improves recommendation accuracy in real-world scenarios.
The paper tackles the problem of recommending event venues for groups of mobile users by developing GEVR, a system that uses individual location traces and social context to predict group meeting locations, achieving over 80% accuracy in location prediction and outperforming comparative models in venue recommendations.
In this paper, we present GEVR, the first Group Event Venue Recommendation system that incorporates mobility via individual location traces and context information into a "social-based" group decision model to provide venue recommendations for groups of mobile users. Our study leverages a real-world dataset collected using the OutWithFriendz mobile app for group event planning, which contains 625 users and over 500 group events. We first develop a novel "social-based" group location prediction model, which adaptively applies different group decision strategies to groups with different social relationship strength to aggregate each group member's location preference, to predict where groups will meet. Evaluation results show that our prediction model not only outperforms commonly used and state-of-the-art group decision strategies with over 80% accuracy for predicting groups' final meeting location clusters, but also provides promising qualities in cold-start scenarios. We then integrate our prediction model with the Foursquare Venue Recommendation API to construct an event venue recommendation framework for groups of mobile users. Evaluation results show that GEVR outperforms the comparative models by a significant margin.