Fairness for Whom? Critically reframing fairness with Nash Welfare Product

TL;DR

This paper introduces a novel fairness framework based on Nash Welfare Product, integrating welfare economics and game theory to achieve fairer, bias-corrected predictions without sacrificing accuracy.

Contribution

It formalizes a Nash Welfare Product approach for fairness in machine learning, expanding utility concepts and explicitly balancing fairness and welfare trade-offs.

Findings

Achieves fairer bias correction without accuracy loss

Demonstrates effectiveness on UCI Adult Income dataset

Shows improved fairness in recidivism prediction

Abstract

Recent studies on disparate impact in machine learning applications have sparked a debate around the concept of fairness along with attempts to formalize its different criteria. Many of these approaches focus on reducing prediction errors while maximizing sole utility of the institution. This work seeks to reconceptualize and critically frame the existing discourse on fairness by underlining the implicit biases embedded in common understandings of fairness in the literature and how they contrast with its corresponding economic and legal definitions. This paper expands the concept of utility and fairness by bringing in concepts from established literature in welfare economics and game theory. We then translate these concepts for the algorithmic prediction domain by defining a formalization of Nash Welfare Product that seeks to expand utility by collapsing that of the institution using the prediction tool and the individual subject to the prediction into one function. We then apply a modulating function that makes the fairness and welfare trade-offs explicit based on designated policy goals and then apply it to a temporal model to take into account the effects of decisions beyond the scope of one-shot predictions. We apply this on a binary classification problem and present results of a multi-epoch simulation based on the UCI Adult Income dataset and a test case analysis of the ProPublica recidivism dataset that show that expanding the concept of utility results in a fairer distribution correcting for the embedded biases in the dataset without sacrificing the classifier accuracy.