Cross-Domain Recommendation via Cluster-Level Latent Factor Model

Recommender systems always aim to provide recommendations for a user based on historical ratings collected from a single domain (e.g., movies or books) only, which may suffer from the data sparsity problem. Recently, several recommendation models have been proposed to transfer knowledge by pooling together the rating data from multiple domains to alleviate the sparsity problem, which typically assume that multiple domains share a latent common rating pattern based on the user-item co-clustering. In practice, however, the related domains do not necessarily share such a common rating pattern, and diversity among the related domains might outweigh the advantages of such common pattern, which may result in performance degradations. In this paper, we propose a novel cluster-level based latent factor model to enhance the cross-domain recommendation, which can not only learn the common rating pattern shared across domains with the flexibility in controlling the optimal level of sharing, but also learn the domain-specific rating patterns of users in each domain that involve the discriminative information propitious to performance improvement. To this end, the proposed model is formulated as an optimization problem based on joint nonnegative matrix tri-factorization and an efficient alternating minimization algorithm is developed with convergence guarantee. Extensive experiments on several real world datasets suggest that our proposed model outperforms the state-of-the-art methods for the cross-domain recommendation task.