Main content
Predicting Juvenile Delinquency and Criminal Behavior in Adulthood Using Machine Learning
Date created: | Last Updated:
: DOI | ARK
Creating DOI. Please wait...
Category: Project
Description: By violating social norms, deviant behavior is an important issue that affects society as a whole and also has serious consequences for its individuals. Different scientific disciplines have proposed theories of deviant behavior that often fall short of predicting actual behavior. In this registered report, we will use data from the longitudinal National Study of Adolescent to Adult Health (Add Health) to examine the predictability of juvenile delinquency and adult criminal behavior, distinguishing between drug, property, and violent offenses. We propose to compare the predictive accuracy of traditional regression models with different machine learning algorithms (elastic net regression and gradient boosting machines). In addition, we will explore the differences in the selection of the key predictors of juvenile delinquency versus adult criminal behavior to account for developmental changes and potentially identify risk factors at an early stage.