Context-Aware Techniques for Cross-Domain Recommender Systems

In the last few years, cross-domain recommender systems emerged in order to improve and alleviate problems of single-domain recommender systems. Despite the great number of cross-domain recommender system approaches, there is a lack of studies concerned about the use of contextual features in crossdomain recommender systems. The context-aware approach uses different contextual information (e.g., location, time, and mood) in order to improve recommendations, where context can be treated as a bridge between different domains. In this paper, we investigate the adoption of two context-aware approaches in a cross-domain recommender system in order to improve its recommendation accuracy. For that, we describe the context-aware cross-domain recommendation problem and the proposed context-aware algorithms. An experimental evaluation performed using a real dataset indicates that context-aware techniques can be a good approach in order to improve the cross-domain recommendation accuracy.