Explainable Restricted Boltzmann Machines for Collaborative Filtering

TL;DR

This paper introduces an explainable RBM-based collaborative filtering method that enhances transparency without sacrificing accuracy, addressing the interpretability gap in black-box recommender systems.

Contribution

It proposes a novel explainable RBM technique that generates transparent recommendations solely from item interactions, without relying on additional data sources.

Findings

Effective in producing accurate recommendations

Enhances transparency and user trust

Maintains competitive recommendation quality

Abstract

Most accurate recommender systems are black-box models, hiding the reasoning behind their recommendations. Yet explanations have been shown to increase the user's trust in the system in addition to providing other benefits such as scrutability, meaning the ability to verify the validity of recommendations. This gap between accuracy and transparency or explainability has generated an interest in automated explanation generation methods. Restricted Boltzmann Machines (RBM) are accurate models for CF that also lack interpretability. In this paper, we focus on RBM based collaborative filtering recommendations, and further assume the absence of any additional data source, such as item content or user attributes. We thus propose a new Explainable RBM technique that computes the top-n recommendation list from items that are explainable. Experimental results show that our method is effective in generating accurate and explainable recommendations.