Work

A framework for unbiased explainable pairwise ranking for recommendation

Year: 2021

Type: article

Abstract: Recent research in recommender systems has demonstrated the advantages of pairwise ranking in recommendation. In this work, we focus on the state-of-the-art pairwise ranking loss function, Bayesian Personalized Ranking (BPR), and aim to address two of its limitations, namely: (1) the lack of explainability and (2) exposure bias. We propose a recommendation framework that encompasses various loss functions that are based on BPR and which aim to mitigate the aforementioned limitations. Our open-source framework includes code to train and tune state-of-the-art pairwise ranking recommender systems on benchmark datasets and evaluate them based on the three criteria of ranking accuracy, explainability, and popularity debiasing.

Source: Software Impacts

DOI: 10.1016/j.simpa.2021.100208

Authors: Khalil Damak, Sami Khenissi, Olfa Nasraoui

Institution: University of Louisville

Language: English

Topic: Recommender Systems and Techniques

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $250

Funder: National Science Foundation