Welcome to FAT Forensics!

FAT Forensics is a Python toolkit for evaluating Fairness, Accountability and Transparency of Artificial Intelligence systems. It is built on top of SciPy and NumPy, and distributed under the 3-Clause BSD license (new BSD).

In addition to the code documentation, this web page also includes a detailed User Guide that describes FAT algorithms on a more theoretical level and talks about best practices when using them.

A great way to get yourself familiar with the package and where it comes from is the Getting Started page.

Source Code

For hosting the source code we use the FAT-Forensics organisation on GitHub, with the source code for the FAT Forensics packed being held in the fat-forensics repository.


We use a range of platforms for communication in the project:

  • for issues with the source code or the documentation please open an issue on our GitHub issue tracker;

  • the code-related development discussion should happen on our gitter channel;

  • the discussion about the project’s future and the direction of the development happens on our slack channel and mailing list.


The project has started as an academic collaboration between the University of Bristol and Thales. You can find all of our contributors and more information about the support we receive here.

Please remember to cite us if you use any part of the package or its documentation.