Item Association Factorization Mixed Markov Chains for Sequential Recommendation

TL;DR

This paper proposes a novel sequential recommendation algorithm that integrates item association graphs with user behavior sequences, significantly improving recommendation accuracy without increasing model complexity.

Contribution

It introduces Item Association Factorization Mixed Markov Chains, combining item association data with Markov chains for enhanced sequential recommendation.

Findings

Significant improvement in recommendation ranking results.

Effective incorporation of item association information.

Model maintains low parameter count.

Abstract

Sequential recommendation refers to recommending the next item of interest for a specific user based on his/her historical behavior sequence up to a certain time. While previous research has extensively examined Markov chain-based sequential recommendation models, the majority of these studies has focused on the user's historical behavior sequence but has paid little attention to the overall correlation between items. This study introduces a sequential recommendation algorithm known as Item Association Factorization Mixed Markov Chains, which incorporates association information between items using an item association graph, integrating it with user behavior sequence information. Our experimental findings from the four public datasets demonstrate that the newly introduced algorithm significantly enhances the recommendation ranking results without substantially increasing the parameter count. Additionally, research on tuning the prior balancing parameters underscores the significance of incorporating item association information across different datasets.