Algorithmic Fairness in Performative Policy Learning: Escaping the Impossibility of Group Fairness

TL;DR

This paper explores how leveraging performativity in social classification can improve group fairness, allowing policymakers to steer populations and resolve conflicts between fairness definitions.

Contribution

It introduces a novel approach that uses performativity to enhance group fairness guarantees and resolve fairness conflicts in policy learning.

Findings

Performativity can be exploited to improve fairness outcomes.

Policymakers can steer populations to address inequities.

Conflicting fairness definitions can be reconciled through this approach.

Abstract

In many prediction problems, the predictive model affects the distribution of the prediction target. This phenomenon is known as performativity and is often caused by the behavior of individuals with vested interests in the outcome of the predictive model. Although performativity is generally problematic because it manifests as distribution shifts, we develop algorithmic fairness practices that leverage performativity to achieve stronger group fairness guarantees in social classification problems (compared to what is achievable in non-performative settings). In particular, we leverage the policymaker's ability to steer the population to remedy inequities in the long term. A crucial benefit of this approach is that it is possible to resolve the incompatibilities between conflicting group fairness definitions.