TriMat: Context-aware Recommendation by Tri-Matrix Factorization

TL;DR

This paper introduces TriMat, a tri-matrix factorization approach that effectively incorporates contextual information into recommender systems, improving accuracy and fairness in real-world applications.

Contribution

The paper presents a novel tri-matrix factorization method for context-aware recommendation, addressing the gap between theory and practical deployment.

Findings

Improved recommendation accuracy

Enhanced fairness metrics

Effective incorporation of contextual data

Abstract

Search engine is the symbolic technology of Web 2.0, and many people used to believe recommender systems is the new frontier of Web 3.0. In the past 10 years, with the advent of TikTok and similar apps, recommender systems has materialized the vision of the machine learning pioneers. However, many research topics of the field remain unfixed until today. One such topic is CARS (Context-aware Recommender Systems) , which is largely a theoretical topic without much advance in real-world applications. In this paper, we utilize tri-matrix factorization technique to incorporate contextual information into our matrix factorization framework, and prove that our technique is effective in improving both the accuracy and fairness metrics in our experiments.