Aequitas: A Bias and Fairness Audit Toolkit

TL;DR

Aequitas is an open-source toolkit designed to help developers and policymakers evaluate AI models for bias and fairness across various metrics and subgroups, promoting more equitable AI deployment.

Contribution

The paper introduces Aequitas, a comprehensive, easy-to-use toolkit that operationalizes multiple bias and fairness metrics for AI systems, filling a gap in practical bias auditing resources.

Findings

Enables testing of models for multiple bias metrics

Supports analysis across diverse population subgroups

Facilitates informed decision-making in AI deployment

Abstract

Recent work has raised concerns on the risk of unintended bias in AI systems being used nowadays that can affect individuals unfairly based on race, gender or religion, among other possible characteristics. While a lot of bias metrics and fairness definitions have been proposed in recent years, there is no consensus on which metric/definition should be used and there are very few available resources to operationalize them. Therefore, despite recent awareness, auditing for bias and fairness when developing and deploying AI systems is not yet a standard practice. We present Aequitas, an open source bias and fairness audit toolkit that is an intuitive and easy to use addition to the machine learning workflow, enabling users to seamlessly test models for several bias and fairness metrics in relation to multiple population sub-groups. Aequitas facilitates informed and equitable decisions around developing and deploying algorithmic decision making systems for both data scientists, machine learning researchers and policymakers.