Journal of Experimental Criminology Volume: 13 Issue: 2 Dated: June 2017 Pages: 193-216
This study evaluated the Pennsylvania Board of Probation and Parole's use of machine-learning forecasts to assist in informing its parole release decisions, with a focus on the impact of the forecasts and parole board decisions on subsequent recidivism.
A close approximation to a natural, randomized experiment was used to evaluate the impact of the forecasts on parole release decisions. A generalized regression discontinuity design was used to evaluate the impact of the forecasts on recidivism. The forecasts apparently had no effect on the overall parole release rate, but did appear to alter the mix of inmates released. Important distinctions were made between offenders forecasted to be re-arrested for nonviolent crime and offenders forecasted to be re-arrested for violent crime. The balance of evidence indicates that the forecasts led to reductions in re-arrests for both nonviolent and violent crimes. The evaluation concludes that risk assessments based on machine-learning forecasts can improve parole release decisions, especially when distinctions are made between re-arrests for violent and nonviolent crime. (Publisher abstract modified)
Report (Grant Sponsored)
Date Published: June 1, 2017
- Evaluating the Validity and Reliability of Textile and Paper Fracture Characteristics in Forensic Comparative Analysis
- Enhancing resolution and statistical power by utilizing mass spectrometry for detection of SNPs within the short tandem repeats
- Adaptation of the DNase I Procedure to the Biomek® NXP Robotic Platform for More Efficient and Automated Sexual Assault Sample Processing