Mirror Mirror – Reflections on Quantitative Fairness – this is one of the first pieces I read about algorithmic fairness and caught my attention. It surveys the most common definitions of fairness together with relevant examples in a readable format.
https://shiraamitchell.github.io/fairness/
Fairness in Machine Learning book – a WIP of an online textbook about fairness and machine learning by very notable researchers in this field – Solon Barocas, Moritz Hardt, Arvind Narayanan.
Equality of Opportunity in Supervised Learning – if you want to read a research paper about fairness this paper by Moritz Hardt, Eric Price and Nathan Srebro is a good starting point. It is central and relatively easy to read. It defines “Equalized odd” and “Equal opportunity” fairness measures which are commonly used and also gives a geometric intuition.
https://arxiv.org/abs/1610.02413
Responsible Data Science course – a wider view than just fairness. This course is given by Julia Stoyanovich at New York University and includes topics in data cleaning, anonymity explainability, etc. If you look for a pertinent reading list you can find it there.
https://dataresponsibly.github.io/courses/spring20/
AIF360 – A tooling containing metrics for datasets and models to test for biases and algorithms to mitigate bias in datasets and models. The package is available in both Python and R.
AIF360 was originally developed by IBM and was recently donated to Linux Foundation AIAmong the currently available software tools, I find this the most baked and stable one.
Tom Ron 