Privilege Scores for Fairness-Aware ML
MCML Authors
Ludwig Bothmann
Dr.
Philip Amir Boustani
Bernd Bischl
Prof. Dr.
Director
Abstract
Ludwig Bothmann
Dr.
Philip Amir Boustani
Bernd Bischl
Prof. Dr.
Director
Abstract
Bias-preserving methods in fairness-aware machine learning (fairML) focus on metrics that prioritize formal equality by balancing error rates across subgroups. These methods can perpetuate historical discrimination embedded in real-world data. In contrast, bias-transforming methods aim for substantive equality by actively addressing historical inequalities. As a contribution to bias-transforming methods, we introduce the concept of privilege scores, a novel approach to identifying and quantifying individual privilege in machine learning tasks. Privilege scores use causal inference techniques to compare real-world outcomes to those in a 'fair' world in which the protected attributes do not influence the target variable. This individual-level perspective provides actionable insights for applications such as affirmative action and beyond. Key contributions include (1) the formalization of privilege scores, (2) a methodological framework for estimation with uncertainty quantification via confidence intervals, (3) an interpretable machine learning approach for understanding privilege score contributions, and (4) a novel in-processing method, Multi-PrivScore, to mitigate model-level discrimination during model training. Experiments on simulated and real-world data demonstrate the usefulness of privilege scores. Overall, our work highlights privilege scores as a versatile tool for assessing and mitigating historical discrimination in various machine learning applications.
inproceedings
DAGStat 2025
7th Joint Statistical Meeting of the Deutsche Arbeitsgemeinschaft Statistik. Berlin, Germany, Mar 24-28, 2025. Poster presentation. Full paper available.Authors
L. Bothmann • S. Dandl • J. M. Alvarez • P. A. Boustani • B. BischlLinks
Research Area
BibTeXKey: BDA+25