Aequitas: A Bias and Fairness Audit Toolkit
This toolkit addresses the problem of unintended bias in AI systems for data scientists, researchers, and policymakers, though it is incremental as it builds on existing metrics without introducing new ones.
The authors tackled the lack of standardized tools for auditing bias and fairness in AI systems by developing Aequitas, an open-source toolkit that enables users to test models for multiple bias metrics across population sub-groups, facilitating equitable decisions in algorithmic development and deployment.
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.