Differential Parity: Relative Fairness Between Two Sets of Decisions

TL;DR

This paper introduces differential parity, a fairness measure comparing two decision sets relative to each other, addressing subjective fairness standards and enabling bias detection without requiring absolute fairness definitions.

Contribution

It proposes a new fairness concept called differential parity, which compares decision sets relative to each other, and offers methods to estimate it even with different data subjects.

Findings

Differential parity avoids the need for absolute fairness standards.

It can serve as a new group fairness measure when a reference set is available.

A machine learning approach can estimate differential parity across different data subjects.

Abstract

With AI systems widely applied to assist humans in decision-making processes such as talent hiring, school admission, and loan approval; there is an increasing need to ensure that the decisions made are fair. One major challenge for analyzing fairness in decisions is that the standards are highly subjective and contextual -- there is no consensus for what absolute fairness means for every scenario. That is not to say that different fairness standards often conflict with each other. To bypass this issue, this work aims to test relative fairness in decisions. That is, instead of defining what are ``absolutely'' fair decisions, we propose to test the relative fairness of one decision set against another with differential parity -- the difference between two sets of decisions should be independent of a certain sensitive attribute. This proposed notion of differential parity fairness has the following benefits: (1) it avoids the ambiguous and contradictory definition of what absolutely fair decisions are; (2) when a reference set (of ground truth or reliable fair decisions) is available, differential parity can serve as a new group fairness notion (similar to but different from separation and sufficiency); (3) even when no reference set is available, it reveals the relative preference or bias between different decision sets. One limitation for differential parity is that it requires the two sets of decisions under comparison to be made on the same data subjects. To overcome this limitation, we propose to utilize a machine learning model to bridge the gap between the two sets of decisions made on difference data and estimate the differential parity.