A unified optimization toolbox for solving popularity bias, fairness, and diversity in recommender systems

Sinan Seymen, Himan Abdollahpouri, Edward C. Malthouse

Research output: Contribution to journalConference articlepeer-review

Abstract

Historically, the main criterion for a successful recommender system was how accurate the recommendations were according to the user's taste. This emphasis on accuracy was later challenged by researchers asking for other types of metrics such as novelty, diversity, fairness of the recommendations. Researchers have proposed different algorithms to improve these metrics of recommendation, but the problem is that each proposed algorithm improves a certain metric (diversity, novelty, etc.) and, usually, it is difficult to improve two or more aspects simultaneously. In this paper, we unify different considerations into a constrained optimization framework where different sets of metrics can be improved by simply using different sets of constraints. Therefore, our framework improves the non-accuracy metrics of the recommendations by combining different constraints designed for separate metrics. Our biggest contribution is offering models that are simple, easy to combine, and data independent. We create models considering popularity, fairness, and diversity metrics since they are the metrics widely investigated in the literature; however, our framework can include other metrics following the ideas proposed in this paper. Experimental results confirm that our general framework has comparable performance with the state-of-the-art methods designed for improving each individual metric, and offers the benefit of being able to accommodate a wide range of considerations.

Original languageEnglish (US)
JournalCEUR Workshop Proceedings
Volume2959
StatePublished - 2021
Event1st Workshop on Multi-Objective Recommender Systems, MORS 2021 - Amsterdam, Netherlands
Duration: Sep 25 2021 → …

Keywords

  • Diversity
  • Fairness
  • Optimization
  • Popularity bias
  • Recommender systems

ASJC Scopus subject areas

  • Computer Science(all)

Fingerprint

Dive into the research topics of 'A unified optimization toolbox for solving popularity bias, fairness, and diversity in recommender systems'. Together they form a unique fingerprint.

Cite this