A Unifying Human-Centered AI Fairness Framework
Preprint
Abstract
The increasing use of Artificial Intelligence (AI) in critical societal domains has amplified concerns about fairness, particularly regarding unequal treatment across sensitive attributes such as race, gender, and socioeconomic status. While there has been substantial work on ensuring AI fairness, navigating trade-offs between competing notions of fairness as well as predictive accuracy remains challenging, creating barriers to the practical deployment of fair AI systems. To address this, we introduce a unifying human-centered fairness framework that systematically covers eight distinct fairness metrics, formed by combining individual and group fairness, infra-marginal and intersectional assumptions, and outcome-based and equality-of-opportunity (EOO) perspectives. This structure allows stakeholders to align fairness interventions with their values and contextual considerations. The framework uses a consistent and easy-to-understand formulation for all metrics to reduce the learning curve for non-experts. Rather than privileging a single fairness notion, the framework enables stakeholders to assign weights across multiple fairness objectives, reflecting their priorities and facilitating multi-stakeholder compromises. We apply this approach to four real-world datasets: the UCI Adult census dataset for income prediction, the COMPAS dataset for criminal recidivism, the German Credit dataset for credit risk assessment, and the MEPS dataset for healthcare utilization. We show that adjusting weights reveals nuanced trade-offs between different fairness metrics. Finally, through case studies in judicial decision-making and healthcare, we demonstrate how the framework can inform practical and value-sensitive deployment of fair AI systems.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Datasheets for datasetsCommunications of the ACM, 2021
- A Survey on Bias and Fairness in Machine LearningACM Computing Surveys, 2021
- WeBuildAIProceedings of the ACM on Human-Computer Interaction, 2019
- Dissecting racial bias in an algorithm used to manage the health of populationsScience, 2019
- Improving Fairness in Machine Learning Systems2019
- Good intentions are not enough: how informatics interventions can worsen inequalityJournal of the American Medical Informatics Association, 2018
- Fairness Beyond Disparate Treatment & Disparate Impact2017
- Measuring discrimination in algorithmic decision makingData Mining and Knowledge Discovery, 2017
- Three naive Bayes approaches for discrimination-free classificationData Mining and Knowledge Discovery, 2010
- Defining and redirecting a school‐to‐prison pipelineNew Directions for Youth Development, 2003