(Un)certainty of (Un)fairness: Preference-Based Selection of Certainly Fair Decision-Makers

Abstract

Fairness metrics are used to assess discrimination and bias in decision-making processes across various domains, including machine learning models and human decision-makers in real-world applications. This involves calculating the disparities between probabilistic outcomes among social groups, such as acceptance rates between male and female applicants. However, traditional fairness metrics do not account for the uncertainty in these processes and lack of comparability when two decision-makers exhibit the same disparity. Using Bayesian statistics, we quantify the uncertainty of the disparity to enhance discrimination assessments. We represent each decision-maker, whether a machine learning model or a human, by its disparity and the corresponding uncertainty in that disparity. We define preferences over decision-makers and utilize brute-force to choose the optimal decision-maker according to a utility function that ranks decision-makers based on these preferences. The decision-maker with the highest utility score can be interpreted as the one for whom we are most certain that it is fair.

Accepted in 27TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE (ECAI 2024)

References in corpus (9)

• Equality of Opportunity in Supervised Learning
• Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment
• De-biasing "bias" measurement
• Can I Trust My Fairness Metric? Assessing Fairness with Unlabeled Data and Bayesian Inference
• On The Impact of Machine Learning Randomness on Group Fairness
• Fairness through Aleatoric Uncertainty
• Towards Fairness and Privacy: A Novel Data Pre-processing Optimization Framework for Non-binary Protected Attributes
• Fairness in Ranking under Disparate Uncertainty
• Measuring and Mitigating Bias for Tabular Datasets with Multiple Protected Attributes