Promoting Fairness through Hyperparameter Optimization
This work addresses fairness issues in ML deployment for real-world applications like fraud detection, offering a simple and cost-effective solution, though it is incremental as it builds on existing hyperparameter optimization methods.
The paper tackles the problem of unfairness in machine learning models that are optimized solely for predictive performance by proposing fairness-aware hyperparameter optimization variants, resulting in a 111% mean fairness increase with only a 6% performance decrease in real-world and benchmark datasets.
Considerable research effort has been guided towards algorithmic fairness but real-world adoption of bias reduction techniques is still scarce. Existing methods are either metric- or model-specific, require access to sensitive attributes at inference time, or carry high development or deployment costs. This work explores the unfairness that emerges when optimizing ML models solely for predictive performance, and how to mitigate it with a simple and easily deployed intervention: fairness-aware hyperparameter optimization (HO). We propose and evaluate fairness-aware variants of three popular HO algorithms: Fair Random Search, Fair TPE, and Fairband. We validate our approach on a real-world bank account opening fraud case-study, as well as on three datasets from the fairness literature. Results show that, without extra training cost, it is feasible to find models with 111% mean fairness increase and just 6% decrease in performance when compared with fairness-blind HO.