Abstract

In this paper we present a contextual modeling approach for model-based recommender systems that integrates and exploits both user preferences and contextual signals in a common vector space. Differently to previous work, we conduct a user study acquiring and analyzing a variety of realistic contextual signals associated to user preferences in several domains. Moreover, we report empirical results evaluating our approach in the movie and music domains, which show that enhancing model-based recommender systems with time, location and social companion information improves the accuracy of generated recommendations.