The Application of Machine Learning to a General Risk–Need Assessment Instrument in the Prediction of Criminal Recidivism
The Application of Machine Learning to a General Risk–Need Assessment Instrument in the Prediction of Criminal Recidivism
Criminal Justice and Behavior, Ahead of Print.
The Level of Service/Case Management Inventory (LS/CMI) is one of the most frequently used tools to assess criminogenic risk–need in justice-involved individuals. Meta-analytic research demonstrates strong predictive accuracy for various recidivism outcomes. In this exploratory study, we applied machine learning (ML) algorithms (decision trees, random forests, and support vector machines) to a data set with nearly 100,000 LS/CMI administrations to provincial corrections clientele in Ontario, Canada, and approximately 3 years follow-up. The overall accuracies and areas under the receiver operating characteristic curve (AUCs) were comparable, although ML outperformed LS/CMI in terms of predictive accuracy for the middle scores where it is hardest to predict the recidivism outcome. Moreover, ML improved the AUCs for individual scores to near 0.60, from 0.50 for the LS/CMI, indicating that ML also improves the ability to rank individuals according to their probability of recidivating. Potential considerations, applications, and future directions are discussed.
The Level of Service/Case Management Inventory (LS/CMI) is one of the most frequently used tools to assess criminogenic risk–need in justice-involved individuals. Meta-analytic research demonstrates strong predictive accuracy for various recidivism outcomes. In this exploratory study, we applied machine learning (ML) algorithms (decision trees, random forests, and support vector machines) to a data set with nearly 100,000 LS/CMI administrations to provincial corrections clientele in Ontario, Canada, and approximately 3 years follow-up. The overall accuracies and areas under the receiver operating characteristic curve (AUCs) were comparable, although ML outperformed LS/CMI in terms of predictive accuracy for the middle scores where it is hardest to predict the recidivism outcome. Moreover, ML improved the AUCs for individual scores to near 0.60, from 0.50 for the LS/CMI, indicating that ML also improves the ability to rank individuals according to their probability of recidivating. Potential considerations, applications, and future directions are discussed.
Mehdi Ghasemi