Skip to Main Content

Fairness, accountability and transparency in automated decision-making

Fairness, accountability and transparency in automated decision-making

Speaker: Suresh Venkatasubramanian, University of Utah
Location: CCP 221

In the last few years we’ve seen the rapid rise of automated decision making systems in all areas that touch our lives, whether it be hiring, credit scoring, university admissions, medical diagnosis and the entire pipeline of criminal justice. We’ve begun to tease out the technical problems arising from the deployment of such systems, focused around issues of fairness, accountability and transparency (FAT).

In this talk I’ll take a look back and a peek forward. I’ll outline the research problems at the core of this new discipline, both in the core area of machine learning and beyond to other areas in CS, and present what we’ve learnt so far. I’ll also present a vision for the next set of challenges on the technical side and beyond.

Suresh Venkatasubramanian is an associate professor at the University of Utah. His background is in algorithms and computational geometry, as well as data mining and machine learning. His current research interests lie in algorithmic fairness, and more generally the problem of understanding and explaining the results of black box decision procedures. Suresh was the John and Marva Warnock Assistant Professor at the U, and has received a CAREER award from the NSF for his work in the geometry of probability. His research on algorithmic fairness has received press coverage including NPR’s Science Friday, as well as in other media outlets. He is a member of the board of the ACLU in Utah, and is a member of New York City’s Failure to Appear Tool (FTA) Research Advisory Council.

This entry was posted in CS Seminar. Bookmark the permalink.