Hypothetical tensor-based multi-criteria recommender system for new users with partial preferences

Multi-Criteria Recommender Systems (MCRSs) have been developed to improve the accuracy of single-criterion rating-based recommender systems that could not express and reflect users? fine-grained rating behaviors. In most MCRSs, new users are asked their preferences on multi-criteria items, address cold-start problem. However, some collected usually complete due cognitive limitation and/or unfamiliarity item domains, which is called ?partial preferences?. The fundamental challenge then negatively affects accurately recommend items according through MCRSs. this paper, we propose a Hypothetical Tensor Model (HTM) leverage auxiliary data complemented three intuitive rules dealing with user?s unfamiliarity. First, find four patterns partial caused by And defined considering relationships between multi-criteria. Lastly, modeled tensor maintain an inherent structure correlations Experiments TripAdvisor dataset showed HTM improves MSE performances from 40 47% comparing other baseline methods. particular, effectivenesses each rule regarding clearly revealed.