Wiggum: Simpson’s Paradox Inspired Fairness Forensics
Sarah M. Brown, Ph.D.
Brown University
Both technical limitations and social critiques of current approaches to fair machine learning motivate the need for more collaborative, human driven approaches. We aim to empower human experts to conduct more critical exploratory analyses and support informal audits. I will present Wiggum, a data exploration package with a visual analytics interface for Simpson’s paradox inspired fairness forensics. Wiggum detects and ranks multiple forms of Simpson’s Paradox and related relaxations.
Sarah Brown is a Postdoctoral Research Associate in the Data Science Initiative. She earned her Ph.D. in 2016, MS in 2014, and BS in 2011 all in Electrical Engineering at Northeastern University. Dr. Brown’s research interest is in building machine learning methods to enable data-driven discovery in domains where most current knowledge is qualitative and analyzing machine learning techniques with respect to social values.
