I'm trying to find some fair/accountable/transparent (FAC) algorithms, and the "Equality of Opportunity in Supervised Learning" seems pretty promissing. I was wondering if there's an implementation of the algorithms somewhere (I personally prefer python, but [almost] any language would do).

[1] Hardt, Moritz, Eric Price, and Nati Srebro. "Equality of opportunity in supervised learning." Advances in neural information processing systems. 2016.


It turns out people at IBM have implemented it in the AIF360 package (github link).

The resources page lists the paper as one of the algorithms they've implemented.

It's implemented in aif360.algorithms.postprocessing.EqOddsPostprocessing

| cite | improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.