# When Post-Processing Fairness Constraints Help and When They Harm: Evidence from Eight Cross-Domain Evaluations

arXiv: https://arxiv.org/abs/2609.26955 · HTML: https://mlsanity.com/paper/2609.26955/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 9 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Builds on (most cited first, 5 of 5)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [A Comprehensive Empirical Study of Bias Mitigation Methods for Machine Learning Classifiers](https://mlsanity.com/paper/2207.03277/) (2022)
- [Bias Begins with Data: The FairGround Corpus for Robust and Reproducible Research on Algorithmic Fairness](https://mlsanity.com/paper/2510.22363/) (2025)

## Abstract (arXiv)

Fairness audits in production ML typically occur once, at deployment, on a single domain. Both fail in practice: fairness can shift after retraining or a changing user base, and interventions validated on one dataset are rarely tested across the heterogeneous domains an organization deploys. We present FAPE (Fairness Auditing for Production Environments), a four-stage framework evaluating a single post-processing intervention, Fairlearn's ThresholdOptimizer, across eight domain evaluations: criminal justice, income prediction, legal admissions, credit lending, agricultural lending, a multi-domain benchmark corpus, healthcare, and education. Each is scored on demographic parity and equalized odds difference, plus disparate impact ratio and accuracy cost where computable. Intervention effectiveness tracks baseline disparity magnitude: across model-domain pairs the constraint improved disparity in 9 of 14 high-disparity cases and worsened it in 3 of 4 near-fair ones. Each of the five high-disparity exceptions reverses under one of two measurement checks, a minimum group size or thresholds fit on held-out data. A CUSUM monitor started at deployment, tested on a simulated shift, separates constrained models that never met a 0.1 parity convention from those that met it and later regressed. A single deployment-time audit is therefore an unreliable guide, which argues for baseline-disparity screening and continuous monitoring