Pragmatic Fairness: Developing Policies with Outcome Disparity Control

TL;DR

This paper presents a causal framework for designing fair policies that control outcome disparities using two novel fairness constraints, applicable with limited action space and based on historical data, demonstrated through semi-synthetic experiments.

Contribution

It introduces two new fairness constraints—moderation breaking and equal benefit—and practical methods for their implementation within a causal policy design framework.

Findings

The moderation breaking constraint reduces outcome disparity within available actions.

The equal benefit constraint ensures fair distribution of gains across sensitive groups.

Experimental results validate the effectiveness of the proposed constraints on semi-synthetic models.

Abstract

We introduce a causal framework for designing optimal policies that satisfy fairness constraints. We take a pragmatic approach asking what we can do with an action space available to us and only with access to historical data. We propose two different fairness constraints: a moderation breaking constraint which aims at blocking moderation paths from the action and sensitive attribute to the outcome, and by that at reducing disparity in outcome levels as much as the provided action space permits; and an equal benefit constraint which aims at distributing gain from the new and maximized policy equally across sensitive attribute levels, and thus at keeping pre-existing preferential treatment in place or avoiding the introduction of new disparity. We introduce practical methods for implementing the constraints and illustrate their uses on experiments with semi-synthetic models.