University of Minnesota
Software Engineering Center

You are here

Fair AI in Practice

Date of Presentation: 
Wednesday, January 16, 2019
Presented By: 
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. During the talk, an interactive Web experience will be used to introduce algorithmic fairness concepts and capabilities of the toolkit. Usage guidance, and industry-specific tutorials will also be discussed. The goal of the talk is to enable data scientists and practitioners to incorporate the most appropriate approach to algorithmic fairness for their problem into their work products.