The term “Fairness Forensics” was first coined by Kate Crawford during her NIPS 2017 Keynote The Trouble with Bias. The phrase represents a call for researchers to investigate possible bias in deployed systems

This site aims to collect projects under this umbrella. Add an issue on the repo to have your project added.


Detecting Simpson's Paradox

published in FLAIRS 2018

Toward scalable, interactive detection of Simpson’s Paradox.

Simpson’s paradox is the phenomenon that a trend of an association in the whole population reverses within the subpopulations defined by a categorical variable. Detecting Simpson’s paradox indicates surprising and interesting patterns of the data set for the user. We show that our approach detects cases in real data sets as well as synthetic data sets, and demonstrate that our approach can uncover the hidden surprising pattern by detecting occurrences of Simpson’s paradox.