Fairness and Bias


Algorithmic bias describes systematic and repeatable errors in a computer system that create unfair outcomes, such as privileging one arbitrary group of users over others. Bias can emerge due to many factors, including but not limited to the design of the algorithm or the unintended or unanticipated use or decisions relating to the way data is coded, collected, selected or used to train the algorithm.

Overview

Fairness and Machine Learning
This book gives a perspective on machine learning that treats fairness as a central concern rather than an afterthought.
fairness machine-learning bias privacy

Tutorials

Fairness Indicators: Scalable Infrastructure for Fair ML Systems
Algorithms and the datasets on which ML models are trained on also have the ability to reflect or reinforce unfair biases.
fairness bias machine-learning tutorial
Lessons from the PULSE Model and Discussion
Elements of the recent discussion that happened among AI researchers as a result of bias found in the model associated with the PULSE paper.
ethics bias fairness paper

Libraries

General
AI Fairness 360 Open Source Toolkit
A comprehensive set of fairness metrics for datasets and ML models, explanations for metrics, and algorithms to mitigate bias in datasets and models.
bias fairness ibm article
Table of Contents
Share a project
Share something you or the community has made with ML.
Topic experts
Share