Online Program Home
My Program

Abstract Details

Activity Number: 577 - Statistical Methods for Interpreting Machine Learning Algorithms - with Implications for Targeting
Type: Topic Contributed
Date/Time: Wednesday, August 1, 2018 : 2:00 PM to 3:50 PM
Sponsor: Section on Statistical Learning and Data Science
Abstract #329634 Presentation
Title: An Algorithm for Removing Sensitive Information
Author(s): James Johndrow* and Kristian Lum
Companies: Stanford University and Human Rights Data Analysis Group
Keywords: algorithmic fairness; machine learning; risk assessment

Predictive modeling is increasingly being employed to assist human decision-makers. One purported advantage of replacing or augmenting human judgment with computer models is the perceived "neutrality" of computers. There is growing recognition that employing algorithms does not remove the potential for bias, and can even amplify it if the training data were generated by a process that is itself biased. In this paper, we provide a probabilistic notion of algorithmic bias. We propose a method to eliminate bias from predictive models by removing all information regarding protected variables from the data to which the models will ultimately be trained. Unlike previous work in this area, our procedure accommodates data on any measurement scale. Motivated by models currently in use in the criminal justice system that inform decisions on pre-trial release and parole, we apply our proposed method to a dataset on the criminal histories of individuals at the time of sentencing to produce "race-neutral" predictions of re-arrest.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program