DNN-MF: deep neural network matrix factorization approach for filtering information in multi-criteria recommender systems

Personalization systems have proved to be one of the most powerful tools for e-commerce sites, assisting users in discovering the most relevant products across enormous product catalogues. The formulation of product suggestions in the most widely used collaborative filtering is dependent on ratings contributed by the customer base. Though numerous domains consider allowing users to give an overall rating to products, a burgeoning number of online platforms are allowing users to rate products on a variety of dimensions. According to previous research, these multidimensional ratings offer valuable perceptions that can be used in generating a personalization list for users. Within the personalization systems research domain, multi-criteria systems have garnered significant attention since they use multiple criteria to predict rating scores. New strategies for leveraging information produced from multi-criteria scores to increase the prediction precision of multi-criteria (MC) systems are presented in this paper. In particular, we propose to fuse deep neural networks (DNN), matrix factorization (MF), and social spider optimization (SSO) to exploit nonlinear, non-trivial, and concealed interactions between users in terms of MC preferences. Experimenting on Yahoo! and TripAdvisor datasets reveals that our proposed approach outperforms both modern single-rating recommender systems based on MF and traditional multi-criteria systems. As a result, we believe that using multi-criteria customer evaluations can help e-commerce companies enhance the quality and specificity of their recommended services.