# Whence Is A Model Fair? Fixing Fairness Bugs via Propensity Score Matching

arXiv: https://arxiv.org/abs/2504.17066 · HTML: https://mlsanity.com/paper/2504.17066/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 62 references that are in the map.
- First posted on arXiv 23 Apr 2025.

## Builds on (most cited first, 28 of 28)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [Fairness Testing: Testing Software for Discrimination](https://mlsanity.com/paper/1709.03221/) (2017)
- [Bias in Machine Learning Software: Why? How? What to do?](https://mlsanity.com/paper/2105.12195/) (2021)
- [Fairness Testing: A Comprehensive Survey and Analysis of Trends](https://mlsanity.com/paper/2207.10223/) (2022)
- [Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairness](https://mlsanity.com/paper/2005.12379/) (2020)
- [The Flaws of Policies Requiring Human Oversight of Government Algorithms](https://mlsanity.com/paper/2109.05067/) (2021)
- [A Comprehensive Empirical Study of Bias Mitigation Methods for Machine Learning Classifiers](https://mlsanity.com/paper/2207.03277/) (2022)
- [Fairness-aware Configuration of Machine Learning Libraries](https://mlsanity.com/paper/2202.06196/) (2022)
- [Making Fair ML Software using Trustworthy Explanation](https://mlsanity.com/paper/2007.02893/) (2020)
- [Marrying Fairness and Explainability in Supervised Learning](https://mlsanity.com/paper/2204.02947/) (2022)
- [Transferring Fairness under Distribution Shifts via Fair Consistency Regularization](https://mlsanity.com/paper/2206.12796/) (2022)
- [FairMask: Better Fairness via Model-based Rebalancing of Protected Attributes](https://mlsanity.com/paper/2110.01109/) (2021)
- [Software Engineering for Fairness: A Case Study with Hyperparameter Optimization](https://mlsanity.com/paper/1905.05786/) (2019)
- [Promoting Fairness through Hyperparameter Optimization](https://mlsanity.com/paper/2103.12715/) (2021)
- [Towards Understanding Fairness and its Composition in Ensemble Machine Learning](https://mlsanity.com/paper/2212.04593/) (2022)
- [Fair Enough: Searching for Sufficient Measures of Fairness](https://mlsanity.com/paper/2110.13029/) (2021)
- [Improving Fair Training under Correlation Shifts](https://mlsanity.com/paper/2302.02323/) (2023)
- [Hyperparameter Optimization for Effort Estimation](https://mlsanity.com/paper/1805.00336/) (2018)
- [Graph Fairness Learning under Distribution Shifts](https://mlsanity.com/paper/2401.16784/) (2024)
- [A Large-Scale Empirical Study on Improving the Fairness of Image Classification Models](https://mlsanity.com/paper/2401.03695/) (2024)
- [Defending IEEE Software Standards in Federal Criminal Court](https://mlsanity.com/paper/2106.11021/) (2021)
- [VEER: Enhancing the Interpretability of Model-based Optimizations](https://mlsanity.com/paper/2106.02716/) (2021)

## Abstract (arXiv)

Fairness-aware learning aims to mitigate discrimination against specific protected social groups (e.g., those categorized by gender, ethnicity, age) while minimizing predictive performance loss. Despite efforts to improve fairness in machine learning, prior studies have shown that many models remain unfair when measured against various fairness metrics. In this paper, we examine whether the way training and testing data are sampled affects the reliability of reported fairness metrics. Since training and test sets are often randomly sampled from the same population, bias present in the training data may still exist in the test data, potentially skewing fairness assessments. To address this, we propose FairMatch, a post-processing method that applies propensity score matching to evaluate and mitigate bias. FairMatch identifies control and treatment pairs with similar propensity scores in the test set and adjusts decision thresholds for different subgroups accordingly. For samples that cannot be matched, we perform probabilistic calibration using fairness-aware loss functions. Experimental results demonstrate that our approach can (a) precisely locate subsets of the test data where the model is unbiased, and (b) significantly reduce bias on the remaining data. Overall, propensity score matching offers a principled way to improve both fairness evaluation and mitigation, without sacrificing predictive performance.