Counterfactual Fairness

TL;DR

This paper introduces a causal inference-based framework for counterfactual fairness, ensuring machine learning decisions are unbiased across demographic groups, demonstrated through a law school success prediction case.

Contribution

It proposes a novel formalization of fairness using counterfactual reasoning, addressing biases in historical data for fairer machine learning models.

Findings

Framework effectively models fairness using causal inference.

Application to law school success prediction shows improved fairness.

Demonstrates the importance of counterfactual analysis in ethical AI.

Abstract

Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing. In many of these scenarios, previous decisions have been made that are unfairly biased against certain subpopulations, for example those of a particular race, gender, or sexual orientation. Since this past data may be biased, machine learning predictors must account for this to avoid perpetuating or creating discriminatory practices. In this paper, we develop a framework for modeling fairness using tools from causal inference. Our definition of counterfactual fairness captures the intuition that a decision is fair towards an individual if it is the same in (a) the actual world and (b) a counterfactual world where the individual belonged to a different demographic group. We demonstrate our framework on a real-world problem of fair prediction of success in law school.