Latent based temporal optimization approach for improving the performance of collaborative filtering

PeerJ Comput Sci. 2020 Dec 21:6:e331. doi: 10.7717/peerj-cs.331. eCollection 2020.

Abstract

Recommendation systems suggest peculiar products to customers based on their past ratings, preferences, and interests. These systems typically utilize collaborative filtering (CF) to analyze customers' ratings for products within the rating matrix. CF suffers from the sparsity problem because a large number of rating grades are not accurately determined. Various prediction approaches have been used to solve this problem by learning its latent and temporal factors. A few other challenges such as latent feedback learning, customers' drifting interests, overfitting, and the popularity decay of products over time have also been addressed. Existing works have typically deployed either short or long temporal representation for addressing the recommendation system issues. Although each effort improves on the accuracy of its respective benchmark, an integrative solution that could address all the problems without trading off its accuracy is needed. Thus, this paper presents a Latent-based Temporal Optimization (LTO) approach to improve the prediction accuracy of CF by learning the past attitudes of users and their interests over time. Experimental results show that the LTO approach efficiently improves the prediction accuracy of CF compared to the benchmark schemes.

Keywords: Collaborative Filtering; Decay; Drift; Matrix Factorization; Recommender Systems; Temporal factorization.

Grants and funding

This publication is funded by the Asian Office of Airforce Research and Development (AOARD) through a project on Deep Recurrent Q Learning for Recommendation System. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.