Dimensions as Virtual Items: Improving the predictive ability of top-N recommender systems
Information Processing and Management: an International Journal
| Hi-index | 0.00 |
A multidimensional recommendation model based on resource space model (RSM) which is a semantic data model for organizing resources based on the classification semantics is presented in this paper. The RSM-based multidimensional recommendation space (RSMB_MRS) and its semantic representation are defined. The multidimensional recommendation mechanism (MRM) which including multidimensional recommendation operation language (MROL) is established and aggregation calculation is standardized too. A reduction-aggregation algorithm (RAA)-based collaborative filtering (CF) recommendation method is also proposed in the paper. The experiment using a multidimensional movie recommendation system is performed for implementing the above approach and testing its performance. The obtained results show the feasibility and high-performance of the RSM-based multidimensional recommendation model and combined recommendation approach.