Equality of Effort via Algorithmic Recourse

TL;DR

This paper introduces a novel method to measure fairness called equality of effort using algorithmic recourse, which assesses the minimal intervention cost needed for individuals or groups to change automated system outcomes.

Contribution

It extends the definition of equality of effort and provides an algorithm to assess it through minimal interventions, considering multiple treatment variables and real intervention costs.

Findings

Validated on synthetic data and German credit dataset.

Demonstrated the feasibility of measuring fairness via minimal effort.

Showed how to incorporate feasibility, plausibility, and cost constraints.

Abstract

This paper proposes a method for measuring fairness through equality of effort by applying algorithmic recourse through minimal interventions. Equality of effort is a property that can be quantified at both the individual and the group level. It answers the counterfactual question: what is the minimal cost for a protected individual or the average minimal cost for a protected group of individuals to reverse the outcome computed by an automated system? Algorithmic recourse increases the flexibility and applicability of the notion of equal effort: it overcomes its previous limitations by reconciling multiple treatment variables, introducing feasibility and plausibility constraints, and integrating the actual relative costs of interventions. We extend the existing definition of equality of effort and present an algorithm for its assessment via algorithmic recourse. We validate our approach both on synthetic data and on the German credit dataset.