SCALES: From Fairness Principles to Constrained Decision-Making

TL;DR

SCALES is a versatile framework that translates fairness principles into decision-making constraints using CMDPs, enabling fair policies in complex scenarios like healthcare and criminal justice.

Contribution

It introduces a unified approach to encode various fairness principles into CMDPs, bridging procedural and outcome fairness in decision-making.

Findings

Produces fair policies in simulated healthcare scenarios

Effectively encodes multiple fairness principles in real-world datasets

Demonstrates applicability in single-step and sequential decisions

Abstract

This paper proposes SCALES, a general framework that translates well-established fairness principles into a common representation based on the Constraint Markov Decision Process (CMDP). With the help of causal language, our framework can place constraints on both the procedure of decision making (procedural fairness) as well as the outcomes resulting from decisions (outcome fairness). Specifically, we show that well-known fairness principles can be encoded either as a utility component, a non-causal component, or a causal component in a SCALES-CMDP. We illustrate SCALES using a set of case studies involving a simulated healthcare scenario and the real-world COMPAS dataset. Experiments demonstrate that our framework produces fair policies that embody alternative fairness principles in single-step and sequential decision-making scenarios.