# Privilege Scores

arXiv: https://arxiv.org/abs/2502.01211 · HTML: https://mlsanity.com/paper/2502.01211/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 55 references that are in the map.
- First posted on arXiv 3 Feb 2025.

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

- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [Fairness in Machine Learning: A Survey](https://mlsanity.com/paper/2010.04053/) (2020)
- [Multiaccuracy: Black-Box Post-Processing for Fairness in Classification](https://mlsanity.com/paper/1805.12317/) (2018)
- [Avoiding Discrimination through Causal Reasoning](https://mlsanity.com/paper/1706.02744/) (2017)
- [Path-Specific Counterfactual Fairness](https://mlsanity.com/paper/1802.08139/) (2018)
- [ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R](https://mlsanity.com/paper/1508.04409/) (2015)
- [Fair Inference On Outcomes](https://mlsanity.com/paper/1705.10378/) (2017)
- [FlipTest: Fairness Testing via Optimal Transport](https://mlsanity.com/paper/1906.09218/) (2019)
- [Causal normalizing flows: from theory to practice](https://mlsanity.com/paper/2306.05415/) (2023)
- [Learning Optimal Fair Policies](https://mlsanity.com/paper/1809.02244/) (2018)
- [A Short-term Intervention for Long-term Fairness in the Labor Market](https://mlsanity.com/paper/1712.00064/) (2017)
- [Empirical observation of negligible fairness-accuracy trade-offs in machine learning for public policy](https://mlsanity.com/paper/2012.02972/) (2020)
- [Multi-Objective Hyperparameter Optimization in Machine Learning -- An Overview](https://mlsanity.com/paper/2206.07438/) (2022)
- [The Unfairness of Fair Machine Learning: Levelling down and strict egalitarianism by default](https://mlsanity.com/paper/2302.02404/) (2023)
- [Fair Data Adaptation with Quantile Preservation](https://mlsanity.com/paper/1911.06685/) (2019)
- [Transport-based Counterfactual Models](https://mlsanity.com/paper/2108.13025/) (2021)
- [Does enforcing fairness mitigate biases caused by subpopulation shift?](https://mlsanity.com/paper/2011.03173/) (2020)
- [Algorithmic Unfairness through the Lens of EU Non-Discrimination Law: Or Why the Law is not a Decision Tree](https://mlsanity.com/paper/2305.13938/) (2023)
- [The Long Arc of Fairness: Formalisations and Ethical Discourse](https://mlsanity.com/paper/2203.06038/) (2022)
- [A Guide to Feature Importance Methods for Scientific Inference](https://mlsanity.com/paper/2404.12862/) (2024)
- [Optimal Training of Fair Predictive Models](https://mlsanity.com/paper/1910.04109/) (2019)
- [Counterfactual Situation Testing: Uncovering Discrimination under Fairness given the Difference](https://mlsanity.com/paper/2302.11944/) (2023)
- [What Is Fairness? On the Role of Protected Attributes and Fictitious Worlds](https://mlsanity.com/paper/2205.09622/) (2022)
- [Overcoming Fairness Trade-offs via Pre-processing: A Causal Perspective](https://mlsanity.com/paper/2501.14710/) (2025)
- [Causal Fair Machine Learning via Rank-Preserving Interventional Distributions](https://mlsanity.com/paper/2307.12797/) (2023)
- [Bridging Research and Practice Through Conversation: Reflecting on Our Experience](https://mlsanity.com/paper/2409.05880/) (2024)

## Built on by (most cited first, 1 of 1)

- [Implementing Causal Perception: Competing SCMs and Situated Fairness](https://mlsanity.com/paper/2608.03917/) (2026)

## Abstract (arXiv)

Bias-transforming methods of fairness-aware machine learning aim to correct a non-neutral status quo with respect to a protected attribute (PA). Current methods, however, lack an explicit formulation of what drives non-neutrality. We introduce privilege scores (PS) to measure PA-related privilege by comparing the model predictions in the real world with those in a fair world in which the influence of the PA is removed. At the individual level, PS can identify individuals who qualify for affirmative action; at the global level, PS can inform bias-transforming policies. After presenting estimation methods for PS, we propose privilege score contributions (PSCs), an interpretation method that attributes the origin of privilege to mediating features and direct effects. We provide confidence intervals for both PS and PSCs. Experiments on simulated and real-world data demonstrate the broad applicability of our methods and provide novel insights into gender and racial privilege in mortgage and college admissions applications.