Co-Factorization Model for Collaborative Filtering with Session-based Data

TL;DR

This paper introduces a co-factorization model combining matrix factorization and item2vec to better capture item-item relationships in session-based collaborative filtering, improving recommendation accuracy.

Contribution

It presents a novel co-factorization approach that integrates MF and item2vec to reflect localized item relationships in latent representations.

Findings

Improved recommendation performance over previous methods

Effective modeling of item-item relations in latent space

Demonstrated on multiple datasets

Abstract

Matrix factorization (MF) is a common method for collaborative filtering. MF represents user preferences and item attributes by latent factors. Despite that MF is a powerful method, it suffers from not be able to identifying strong associations of closely related items. In this work, we propose a method for matrix factorization that can reflect the localized relationships between strong related items into the latent representations of items. We do it by combine two worlds: MF for collaborative filtering and item2vec for item-embedding. The proposed method is able to exploit item-item relations. Our experiments on several datasets demonstrates a better performance with the previous work.