Fairness is an increasingly important concern as machine learning models are used to support decision making in high-stakes applications such as mortgage lending, hiring, and prison sentencing. This talk will introduce an open source Python toolkit for algorithmic fairness, AI Fairness 360 (AIF360). The main objectives of this toolkit are to help facilitate the transition of fairness research algorithms to use in an industrial setting and to provide a common framework for fairness researchers to share and evaluate algorithms. Dr. Bellamy is a Principle Research Scientist and Chair of the Exploratory Computer Sciences Council at IBM T J Watson Research Center, Yorktown Heights, New York. Previously she led the IBM Research Human-AI Collaboration group. This group researches user experience for several of IBM’s AI projects, i including the AI Fairness 360 toolkit and rule-based machine-teaching for Watson Assistant. Rachel received her doctorate in cognitive psychology from University of Cambridge, UK in 1991. She holds many patents and has published more than 70 research papers. For more, see her website.

Rachel is a Principle Research Scientist and Chair of the Computer Sciences Council at IBM T J Watson Research Center, Yorktown Heights, New York. In this role she heads a Council that manages a Research portfolio of exploratory science projects. Prior to this, she led an interdisciplinary team of human-computer interaction experts, user experience designers and user experience engineers. That team most recently worked on several IBM Research’s Trusted AI projects, including the AI Fairness 360 and AI Explainability 360.

Rachel received her doctorate in cognitive psychology from University of Cambridge, UK in 1991. She received a Bachelor of Science in psychology with mathematics and computer science from University of London in 1986. Before coming to IBM Research, she was a Project Lead at Apple Computer’s Advanced Technology Group.