Top k Recommendations using Contextual Conditional Preferences Model

Recommender systems are software tools and techniques which aim at suggesting to users items they might be interested in. Context-aware recommender systems are a particular category of recommender systems which exploit contextual information to provide more adequate recommendations. However, recommendation engines still suffer from the cold-start problem, namely where not enough information about users and their ratings is available. In this paper we introduce a method for generating a list of top k recommendations in a new user cold-start situations. It is based on a user model called Contextual Conditional Preferences and utilizes a satisfiability measure proposed in this paper. We analyze accuracy measures as well as serendipity, novelty and diversity of results obtained using three context-aware publicly available datasets in comparison with several contextual and traditional state-of-the-art baselines. We show that our method is applicable in the new user cold-start situations as well as in typical scenarios.