AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias

by   Rachel K. E. Bellamy, et al.

Fairness is an increasingly important concern as machine learning models are used to support decision making in high-stakes applications such as mortgage lending, hiring, and prison sentencing. This paper introduces a new open source Python toolkit for algorithmic fairness, AI Fairness 360 (AIF360), released under an Apache v2.0 license The main objectives of this toolkit are to help facilitate the transition of fairness research algorithms to use in an industrial setting and to provide a common framework for fairness researchers to share and evaluate algorithms. The package includes a comprehensive set of fairness metrics for datasets and models, explanations for these metrics, and algorithms to mitigate bias in datasets and models. It also includes an interactive Web experience ( that provides a gentle introduction to the concepts and capabilities for line-of-business users, as well as extensive documentation, usage guidance, and industry-specific tutorials to enable data scientists and practitioners to incorporate the most appropriate tool for their problem into their work products. The architecture of the package has been engineered to conform to a standard paradigm used in data science, thereby further improving usability for practitioners. Such architectural design and abstractions enable researchers and developers to extend the toolkit with their new algorithms and improvements, and to use it for performance benchmarking. A built-in testing infrastructure maintains code quality.


Aequitas: A Bias and Fairness Audit Toolkit

Recent work has raised concerns on the risk of unintended bias in algori...

Uncertainty Quantification 360: A Holistic Toolkit for Quantifying and Communicating the Uncertainty of AI

In this paper, we describe an open source Python toolkit named Uncertain...

BiaScope: Visual Unfairness Diagnosis for Graph Embeddings

The issue of bias (i.e., systematic unfairness) in machine learning mode...

Fair Enough: Searching for Sufficient Measures of Fairness

Testing machine learning software for ethical bias has become a pressing...

Dbias: Detecting biases and ensuring Fairness in news articles

Because of the increasing use of data-centric systems and algorithms in ...

LAMDA-SSL: Semi-Supervised Learning in Python

LAMDA-SSL is open-sourced on GitHub and its detailed usage documentation...

PyOED: An Extensible Suite for Data Assimilation and Model-Constrained Optimal Design of Experiments

This paper describes the first version (v1.0) of PyOED, a highly extensi...

Code Repositories


A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.

view repo


Emb(race): Diverse representation. Leverage technology to prevent, detect, and remediate bias and misrepresentation in the workplace, products, and society. For corporations to succeed, it is critical to have Black representation at every level.

view repo

Please sign up or login with your details

Forgot password? Click here to reset