Towards more accurate classification of risk of arrest among offenders on community supervision: An application of machine learning versus logistic regression

Abstract

Background: Although there is general consensus about the behavioural, clinical and sociodemographic variables that are risk factors for reoffending, optimal statistical modelling of these variables is less clear. Machine learning techniques offer an approach that may provide greater accuracy than traditional methods. Aim: To compare the performance of advanced machine learning techniques (classification trees and random forests) to logistic regression in classifying correlates of rearrest among adult probationers and parolees in the United States. Method: Data were from the subgroup of people on probation or parole who had taken part in the National Survey on Drug Use and Health for the years 2015-2019. We compared the performance of logistic regression, classification trees and random forests, using receiver operating characteristic curves, to examine the correlates of arrest within the past 12 months. Results: We found that machine learning techniques, specifically random forests, possessed significantly greater accuracy than logistic regression in classifying correlates of arrest.

Digital technology: Transforming delivery of forensic mental healthcare

“…A classification tree approach to violence risk assessment exists, albeit validated in a general psychiatric patient sample (Monahan et al., 2000) and may be more widely implemented in the context of digital technology advances in clinical practice. More recently, it has been further demonstrated that machine learning techniques possess significantly greater accuracy when correlated with rearrest (Maynard et al., CBMH this issue).…”

“…Digital technology is being explored to as a way of improving identification of indicators of relapse of escalating risk (see Maynard et al., this issue). An early attempt to introduce Iterative Classification Trees into clinical practice was promising (Monahan et al., 2000) and might now be revisited as everyday clinical access to digital technology is so improved.…”