Back to top

Predicting Recidivism Risk: New Tool in Philadelphia Shows Great Promise

Accession Number: 027548
Media Type: 
Web Page
Series: 

“As ever-increasing numbers of offenders are supervised in the community — witness the massive “realignment” of prisoners in California — parole and probation departments must find the balance between dwindling dollars and the lowest possible risk to public safety. The good news is that researchers and officials in Philadelphia, Pa., believe they have developed a tool that helps find that balance” (p. 4). This article explains how your jurisdiction can use a random forest risk-forecasting tool. Sections of this article cover: what random forest modeling is; pre-random forest times; getting started; forecast begin- and end-points; determining an acceptable error rate; accuracy; the benefits of random forest modeling; resources, equity, and fairness; the role of ethics in statistical forecasting; the key—a strong partnership; and recommendations from the research.

Predicting Recidivism Risk: New Tool in Philadelphia Shows Great Promise Cover