Hybrid Recommendation Based on Matrix Factorization and Deep Learning
Wei Guo Song, Cong Wang · 2022
Deep learning (DL) is playing an increasingly important role in the field of recommender systems (RSs). In this paper, we enhance the performance of a DL-based RS by incorporating matrix factorization (MF), which gained a great deal of popularity as a result of the Netflix Prize competition. Thus, DL is responsible for learning the nonlinear relationship between users and items, whereas MF is used to describe the linear relationship between users and items. We use the typical DL architecture of the multilayer perceptron, and use layer normalization and the residual to improve its performance. Our experimental results showed that the proposed method can make recommendations accurately.