Bi-convolution matrix factorization algorithm based on improved ConvMF

TL;DR

This paper introduces a Bicon-vMF algorithm that enhances matrix factorization for personalized recommendations by using dual convolutional neural networks to better utilize review data, significantly reducing prediction errors.

Contribution

It proposes a novel Bicon-vMF algorithm that integrates deep review features into matrix factorization, improving recommendation accuracy over existing methods.

Findings

Reduces prediction error by up to 45.8% compared to traditional algorithms.

Outperforms PMF, ConvMF, and DeepCoNN in recommendation accuracy.

Achieves better utilization of review document information.

Abstract

With the rapid development of information technology, "information overload" has become the main theme that plagues people's online life. As an effective tool to help users quickly search for useful information, a personalized recommendation is more and more popular among people. In order to solve the sparsity problem of the traditional matrix factorization algorithm and the problem of low utilization of review document information, this paper proposes a Bicon-vMF algorithm based on improved ConvMF. This algorithm uses two parallel convolutional neural networks to extract deep features from the user review set and item review set respectively and fuses these features into the decomposition of the rating matrix, so as to construct the user latent model and the item latent model more accurately. The experimental results show that compared with traditional recommendation algorithms like PMF, ConvMF, and DeepCoNN, the method proposed in this paper has lower prediction error and can achieve a better recommendation effect. Specifically, compared with the previous three algorithms, the prediction errors of the algorithm proposed in this paper are reduced by 45.8%, 16.6%, and 34.9%, respectively.