This report on the winner of the U.S. Justice Department’s National Institute of Justice’s (NIJ’s) Recidivism Forecasting Challenge with Multi-Target Ensembles pertains to male, female, and overall categories in the first year.
Classification- based quantitative data are primarily about feature engineering and model ensembling. The former enriches the existing patterns in the data, and the latter produced robust predictions even from a limited amount of data. The winning solution for the Recidivism Forecasting Challenge included heavy amounts of each. A roadmap to this solution is provided, along with source code and guidance on how to produce similar results on future datasets. Machine learning models are clearly up to the task of predicting recidivism for the purposes of parole judgments or monitoring. The predicted probabilities spanned the full range from near-zero to very likely.
Downloads
Similar Publications
- Longitudinal Cohort Study: Predictive Validity of the Structured Assessment of Violence Risk in Youth Individual/Clinical Risk Factor on Recidivism Among Mississippi Justice-Involved Youth
- Improving and Evaluating Computed Tomography and Magnetic Resonance Imaging in the Investigation of Fatalities Involving Suspected Head Trauma
- Just Science Podcast: Just Resolving a Capital Murder Case in Denton, Texas