A Deep Learning Based Approach for Context-Aware Multi-Criteria Recommender Systems

Recommender systems are similar to an information filtering system that helps identify items best satisfy the users’ demands based on their preference profiles. Context-aware recommender (CARSs) and multi-criteria (MCRSs) extensions of traditional systems. CARSs have integrated additional contextual such as time, place, so for providing better recommendations. However, majority use ratings a unique criterion building communities. Meanwhile, MCRSs utilize user preferences in multiple criteria generate Up now, how exploit context is still open issue. This paper proposes novel approach, which relies deep learning context-aware We apply neural network (DNN) models predict learn aggregation function. conduct experiments evaluate effect this approach real-world dataset. A significant result our method outperforms other state-of-the-art methods recommendation effectiveness.