EUVIMEDEUVIMED entdecken
Crossref

Machine Learning and Risk Assessment: Random Forest Does Not Outperform Logistic Regression in the Prediction of Sexual Recidivism

Sonja Etzler, Felix D Schönbrodt, Florian Pargent, Reinhard Eher, Martin Rettenberger iD

Assessment · 2024

DOI: 10.1177/10731911231164624 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Assessment, 2024. Verfasst von Sonja Etzler und 4 weiteren Autor:innen. Beteiligte Einrichtung: Goethe-University Frankfurt am Main, Germany. Hauptthemen laut MEDLINE: Recidivism, Sex Offenses. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 95 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Although many studies supported the use of actuarial risk assessment instruments (ARAIs) because they outperformed unstructured judgments, it remains an ongoing challenge to seek potentials for improvement of their predictive performance. Machine learning (ML) algorithms, like random forests, are able to detect patterns in data useful for prediction purposes without explicitly programming them (e.g., by considering nonlinear effects between risk factors and the criterion). Therefore, the current study aims to compare conventional logistic regression analyses with the random forest algorithm on a sample of N = 511 adult male individuals convicted of sexual offenses. Data were collected at the Federal Evaluation Center for Violent and Sexual Offenders in Austria within a prospective-longitudinal research design and participants were followed-up for an average of M = 8.2 years. The Static-99, containing static risk factors, and the Stable-2007, containing stable dynamic risk factors, were included as predictors. The results demonstrated no superior predictive performance of the random forest compared with logistic regression; furthermore, methods of interpretable ML did not point to any robust nonlinear effects. Altogether, results supported the statistical use of logistic regression for the development and clinical application of ARAIs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RecidivismSex OffensesAdultHumansMaleRandom ForestLogistic ModelsProspective StudiesRisk Assessment

Stichwörter der Autor:innen

Stable-2007Static-99actuarial instrumentsmachine learningpredictive validityrisk assessmentsexual offenses

Autor:innen und Institutionen

  • Goethe-University Frankfurt am Main, Germany.
  • Centre for Criminology (Kriminologische Zentralstelle-KrimZ), Wiesbaden, Germany.
  • Ludwig-Maximilians-Universität München, Germany.
  • Federal Evaluation Centre for Violent and Sexual Offenders, Austrian Ministry of Justice, Vienna, Austria.
  • Johannes Gutenberg-University Mainz (JGU), Germany.

ORCID-Profile: Martin Rettenberger

Zitieren

APA

Etzler, S., Schönbrodt, F. D., Pargent, F., Eher, R., & Rettenberger, M. (2024). Machine Learning and Risk Assessment: Random Forest Does Not Outperform Logistic Regression in the Prediction of Sexual Recidivism. Assessment. https://doi.org/10.1177/10731911231164624

Vancouver

Etzler S, Schönbrodt FD, Pargent F, Eher R, Rettenberger M. Machine Learning and Risk Assessment: Random Forest Does Not Outperform Logistic Regression in the Prediction of Sexual Recidivism. Assessment. 2024. doi:10.1177/10731911231164624

BibTeX
@article{Etzler2024,
  author = {Etzler, Sonja and Schönbrodt, Felix D and Pargent, Florian and Eher, Reinhard and Rettenberger, Martin},
  title = {Machine Learning and Risk Assessment: Random Forest Does Not Outperform Logistic Regression in the Prediction of Sexual Recidivism},
  journal = {Assessment},
  year = {2024},
  doi = {10.1177/10731911231164624}
}
Kostenlos starten →