Bias vs Bias -- Dawn of Justice: A Fair Fight in Recommendation Systems

2025-06-23

AI Summary

Existing fairness-aware recommendation research predominantly focuses on binary sensitive attributes (e.g., gender), overlooking the compound bias arising from multiple categorical sensitive attributes (e.g., gender, age, occupation) in multi-class item domains. Method: We propose a fairness-aware re-ranking framework that jointly models multiple sensitive attributes for the first time within re-ranking. Leveraging observed biases as prior knowledge, we design a novel bias compensation mechanism that enforces multi-group fairness constraints while preserving recommendation quality—without modifying the underlying recommendation model. Contribution/Results: Our approach achieves a balanced trade-off between cross-category fairness and ranking performance. Extensive experiments on real-world datasets from e-commerce, job recruitment, and entertainment domains demonstrate that it significantly mitigates societal bias (average reduction of 32.7%) with negligible impact on recommendation accuracy (NDCG@10 degradation < 0.5%). The method is computationally efficient, lightweight, and production-ready.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Ethics, Bias, and Fairness
• Data Mining & Knowledge Management: Recommender Systems

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems

Abstract

Recommendation systems play a crucial role in our daily lives by impacting user experience across various domains, including e-commerce, job advertisements, entertainment, etc. Given the vital role of such systems in our lives, practitioners must ensure they do not produce unfair and imbalanced recommendations. Previous work addressing bias in recommendations overlooked bias in certain item categories, potentially leaving some biases unaddressed. Additionally, most previous work on fair re-ranking focused on binary-sensitive attributes. In this paper, we address these issues by proposing a fairness-aware re-ranking approach that helps mitigate bias in different categories of items. This re-ranking approach leverages existing biases to correct disparities in recommendations across various demographic groups. We show how our approach can mitigate bias on multiple sensitive attributes, including gender, age, and occupation. We experimented on three real-world datasets to evaluate the effectiveness of our re-ranking scheme in mitigating bias in recommendations. Our results show how this approach helps mitigate social bias with little to no degradation in performance.

Problem

• Addressing overlooked bias in item categories in recommendation systems
• Mitigating bias across multiple sensitive attributes like gender and age
• Ensuring fair recommendations without performance degradation

Innovation

• Fairness-aware re-ranking for bias mitigation
• Leverages existing biases to correct disparities
• Mitigates bias across multiple sensitive attributes