# "And the Winner Is...": Dynamic Lotteries for Multi-group Fairness-Aware Recommendation

arXiv: https://arxiv.org/abs/2009.02590 · HTML: https://mlsanity.com/paper/2009.02590/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2020.

## Built on by (most cited first, 5 of 5)

- [Fairness in Recommender Systems: Research Landscape and Future Directions](https://mlsanity.com/paper/2205.11127/) (2022)
- [Dynamic fairness-aware recommendation through multi-agent social choice](https://mlsanity.com/paper/2303.00968/) (2023)
- [FairFML: Fair Federated Machine Learning with a Case Study on Reducing Gender Disparities in Cardiac Arrest Outcome Prediction](https://mlsanity.com/paper/2410.17269/) (2024)
- [Who Pays? Personalization, Bossiness and the Cost of Fairness](https://mlsanity.com/paper/2209.04043/) (2022)
- [Exploring Social Choice Mechanisms for Recommendation Fairness in SCRUF](https://mlsanity.com/paper/2309.08621/) (2023)

## Abstract (arXiv)

As recommender systems are being designed and deployed for an increasing number of socially-consequential applications, it has become important to consider what properties of fairness these systems exhibit. There has been considerable research on recommendation fairness. However, we argue that the previous literature has been based on simple, uniform and often uni-dimensional notions of fairness assumptions that do not recognize the real-world complexities of fairness-aware applications. In this paper, we explicitly represent the design decisions that enter into the trade-off between accuracy and fairness across multiply-defined and intersecting protected groups, supporting multiple fairness metrics. The framework also allows the recommender to adjust its performance based on the historical view of recommendations that have been delivered over a time horizon, dynamically rebalancing between fairness concerns. Within this framework, we formulate lottery-based mechanisms for choosing between fairness concerns, and demonstrate their performance in two recommendation domains.