Table of Contents
The Fairlearn User Guide not only gives an overview of the functionality of the library, but also contains a high-level overview of fairness in machine learning.
Similarly, the AI Fairness 360 Resources contain worked examples and discussion of concepts from fairness in machine learning.
Google published an interactive visualisation that serves as a companion to Equality of Opportunity in Supervised Learning by Hardt et al. It explains a few different notions of fairness and the tension between them.
Our code
All of the code for our experiments and this site are available on GitHub. You can run any of the notebooks we used to clean data or train models directly in your browser on Binder