Aequitas: A Bias and Fairness Audit Toolkit

By Pedro Saleiro, Benedict Kuester, Abby Stevens, Ari Anisfeld, Loren Hinkson, Jesse London, Rayid Ghani. 2018

412 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Safety Research, ML Systems & Hardware, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety Research

In ML Systems & Hardware

In AI Ethics, Fairness & Society

Citations in the corpus

A Survey on Bias and Fairness in Machine Learning (2019, background): “For example, Aequitas [110] is a toolkit that lets users to test”
Predictive Multiplicity in Classification (2019, background): “Instead, we argue that one should measure and report multiplicity in the same way that we measure and report other kinds of model statistics [21, 35, 42, 43].”
What We Can't Measure, We Can't Understand: Challenges to Demographic Data Procurement in the Pursuit of Fairness (2020, methodology): “an example, the fairness methods in Fairlearn (Microsoft) [59], AI Fairness 360 (IBM) [10], What-if tool (Google) [83], LiFT (LinkedIn) [80], Aequitas [70], and FAT-forensics [76] all require access to demographic attribute data.”
Six Human-Centered Artificial Intelligence Grand Challenges (2023, background): “The availability of open source bias audit toolkits are a starting point (Bellamy et al., 2018; Saleiro et al., 2018).”
Algorithmic realism: expanding the boundaries of algorithmic thought (2020, background): “Much of the algorithmic fairness literature prioritizes portability of de nitions and methods across contexts [135]; evaluation tools are designed to t into any machine learning pipeline [126].”
Ethical Considerations in AI-Based Recruitment (2019, methodology): “Several toolkits and programs have been released to assist developers in embedding fairness algorithms in their machine learning pipeline [31, 33-49].”
Trustworthy Artificial Intelligence: A Review (2022, methodology): “F, A [22, 171, 226] F, E [14, 179] E, A [75, 108, 186, 206] F, E, A, P, Ac [92] F, E, A, Ac [134] F, Ac [26] A, P, Ac [163, 214] E, A [55, 132] A, Ac [25, 29, 105, 113, 157, 159, 168, 197] F, A, Ac [111, 174] Ac [204]”
Addressing multiple metrics of group fairness in data-driven decision making (2020, methodology): “Speciﬁcally, we propose a framework to analyze for fairness, similarly to other frameworks which test software for discrimination, such as Themis [16], Aequitas [30], and BlackBoxAuditing [1].”