Back to Publications
journal · 2024

Fairness-Aware Ranking in Multi-Stakeholder Recommender Systems

Lin Chen, Abhiraj Bibhar · IEEE Transactions on Knowledge and Data Engineering

FairnessRecommender Systems

Abstract

Recommender systems increasingly serve multiple stakeholders — consumers, item providers, and platform operators — whose interests are not always aligned. We formalize a fairness-aware ranking objective that balances consumer relevance against provider-side exposure fairness, and propose an efficient re-ranking algorithm that achieves Pareto-improving trade-offs relative to relevance-only baselines on three large-scale recommendation datasets.

Key contributions

  • A formal multi-stakeholder fairness objective for ranking problems.
  • An efficient re-ranking algorithm with provable exposure-fairness guarantees.
  • Empirical validation on three large-scale, publicly available recommendation datasets.
PDF DOI Publisher
Back to all publications

On this page

Authors

  • L Lin Chen
  • A Abhiraj Bibhar (this author)

Cite this paper

Chen, L. & Bibhar, A. (2024). Fairness-Aware Ranking in Multi-Stakeholder Recommender Systems. IEEE Transactions on Knowledge and Data Engineering.

@article{chen2024fairness,
  title     = {Fairness-Aware Ranking in Multi-Stakeholder Recommender Systems},
  author    = {Chen, Lin and Bibhar, Abhiraj},
  journal   = {IEEE Transactions on Knowledge and Data Engineering},
  year      = {2024}
}