ADVANCEMENTS IN REDUCING BIAS IN RECOMMENDATION SYSTEMS: A TECHNICAL OVERVIEW

Authors

  • Saurabh Kumar TikTok (Bytedance), USA Author

Keywords:

Recommendation Systems, Algorithmic Bias, Fairness Metrics, RBEO (Ranking-based Equal Opportunity), Post-processing Adjustments

Abstract

This article explores recent advancements in addressing bias within recommendation systems, focusing on three key approaches: Ranking-based Equal Opportunity (RBEO), post-processing adjustments, and future challenges in implementation. The article examines how these methods effectively reduce demographic disparities while maintaining recommendation quality across various platforms. It investigates the technical architecture of RBEO, the flexibility of post-processing techniques, and the complex balance between fairness and system performance. The article also addresses critical challenges in scaling bias mitigation techniques and managing ethical considerations in algorithmic decision-making, providing insights into future directions for developing more equitable recommendation systems.

References

Allen Lin et al., "Quantifying and Mitigating Popularity Bias in Conversational Recommender Systems," Information Retrieval (cs.IR), 20 Aug 2022. Available: https://arxiv.org/abs/2208.03298

Eduardo Magrani & Paula Guedes Fernandes da Silva, "The Ethical and Legal Challenges of Recommender Systems Driven by Artificial Intelligence," in Multidisciplinary Perspectives on Artificial Intelligence and the Law, pp 141–168, 27 December 2023. Available: https://link.springer.com/chapter/10.1007/978-3-031-41264-6_8

Riku Togashi, Kenshi Abe, Yuta Saito, "Scalable and Provably Fair Exposure Control for Large-Scale Recommender Systems," Information Retrieval (cs.IR), 22 Feb 2024. Available: https://arxiv.org/abs/2402.14369

Weiwen Liu et al., "Balancing Accuracy and Fairness for Interactive Recommendation with Reinforcement Learning," in arXiv:2106.13386v1 [cs.IR] 25 Jun 2021. Available: https://drl4ir.github.io/paper5.pdf

Felix Petersen et al., "Post-processing for Individual Fairness," arXiv:2110.13796v1 [stat.ML] 26 Oct 2021. Available: https://arxiv.org/pdf/2110.13796

Preetam Nandy et al., "Achieving Fairness via Post-Processing in Web-Scale Recommender Systems," arXiv:2006.11350 [stat.ML], 11 Aug 2022. Available: https://arxiv.org/abs/2006.11350

Yu Xin, "Challenges in Recommender Systems: Scalability, Privacy, and Structured Recommendations," Department of Electrical Engineering and Computer Science in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Computer Science and Engineering, June 2015. Available: https://dspace.mit.edu/bitstream/handle/1721.1/99785/927438195-MIT.pdf?sequence=1

Angelo Trotta, Marta Ziosi & Vincenzo Lomonaco, "The future of ethics in AI: challenges and opportunities," AI & SOCIETY, Volume 38, pages 439–441, (2023), 15 March 2023. Available: https://link.springer.com/article/10.1007/s00146-023-01644-x

Published

2024-12-09

How to Cite

Saurabh Kumar. (2024). ADVANCEMENTS IN REDUCING BIAS IN RECOMMENDATION SYSTEMS: A TECHNICAL OVERVIEW. INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING AND TECHNOLOGY (IJCET), 15(6), 1139-1146. https://mylib.in/index.php/IJCET/article/view/1713