Search
Browse By Day
Browse By Time
Browse By Person
Browse By Area
Browse By Session Type
Search Tips
ASC Home
Sign In
Session Submission Type: Lightning Talk Session
In 2021, the National Institute of Justice (NIJ) held a data challenge, inviting participants to predict recidivism for a group of Georgia parolees. NIJ offered awards for the teams who were most accurate in predicting recidivism overall, for male individuals on parole, for female individuals on parole, and for the predictions with the least amount of racial bias. This session highlights what was learned from this data challenge with speakers from the National Institute of Justice, Georgia Department of Community Supervision, and five of the winning teams.
Introducing the National Institute of Justice Recidivism Forecasting Challenge - Joel Hunt, National Institute of Justice
Forecasting Criminal Justice Outcomes While Reducing Negative Consequences - Nick Powell, Georgia Department of Community Supervision
The Pros and Cons of Machine-Learning Model Stacking for Predicting Criminal Justice Outcomes - David B. Wilson, George Mason University; Evan Marie Lowder, George Mason University; Peter Phalen, University of Maryland; Ashley Elizabeth Rodriguez, George Mason University
Interpretable Machine Learning Algorithm to Forecast Recidivism - Anuar Assamidanov, Claremont Graduate University
Predicting Recidivism Using Lasso Regression Models - Shana M. Judge, Executive Director, Duddon Evidence to Policy Research
Using Neural Networks for Gender-Responsive Modeling of Recidivism Outcomes - Sara Debus-Sherrill, George Mason University; Colin Sherrill, Google
Predicting Recidivism Fairly: A Machine Learning Application Using Contextual and Individual Data - Eric Sevigny, Georgia State University; Thaddeus Johnson, Georgia State University; Jared Greathouse, Georgia State University