Interactive Human-Centric Bias Mitigation

Abstract

Bias mitigation algorithms differ in their definition of bias and how they achieve that objective. Bias mitigation algorithms impact different cohorts differently and allowing end-users and data scientists to understand the impact of these differences in order to make informed choices is a relatively unexplored domain. This demonstration presents an interactive bias mitigation pipeline that allows users to understand the cohorts impacted by their algorithm choice and provide feedback in order to provide a bias mitigated pipeline that most aligns with their goals.