Multi-interactive deep matrix factorization model based on auxiliary information

Abstract

In the traditional recommendation systems, the approach of matrix factorization collaborative filtering only just considers the single information of rating, it as a shallow model, can hardly learn deeper feature information. This paper propose a multi-interaction deep matrix factorization model based on auxiliary information, firstly through deep learning model and merge more auxiliary information as input, effectively alleviate the problem of data sparsity. Then, we leverage the structure of multi-interactive nonlinear network to learn the deep feature representation of more abstract and dense; through an inner product interactions on the latent features of users and items repeatedly, to obtain the different layers of feature representation results; the finally aggregating all the interaction results to predict. The experiment results on the Movielens latest 100K dataset shown that the proposed model over the state-of-the-art methods in RMSE.