Using Machine Learning to Enhance Early Intervention in Juvenile Justice through Survey Optimization

Fuente: Zenodo
Salvato in:
Dettagli Bibliografici
Autori principali: Nathan Green, Erik Alda
Natura: Recurso digital
Pubblicazione: Zenodo 2025
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866901694785257472
author Nathan Green
Erik Alda
author_facet Nathan Green
Erik Alda
contents <p><strong><span>Abstract: </span></strong><span>This paper presents an application of machine learning to optimize a widely used juvenile criminal justice survey in the context of a developing country, towards improving juvenile societal outcomes. The survey, designed to assess the likelihood of youth engaging in risky and delinquent behavior, traditionally suffers from low response rates due to its extensive length. Using machine learning and deep learning methodologies, we demonstrate an approach to streamline the survey process by identifying and prioritizing the most important questions. Our experiments show significant reductions in the number of survey questions needed, while still accurately predicting the likelihood of future delinquency. This optimization addresses the issue of survey fatigue while also enhancing early intervention strategies for at-risk youth. By increasing response rates and facilitating more comprehensive data collection, this approach contributes to the larger social goal of improving outcomes for vulnerable youth populations. This research underscores the potential of AI technologies in the realm of social good, where the convergence of data science and juvenile justice holds promise to create a positive social impact.</span></p> <p><strong><span>Keywords</span></strong><span>: Machine Learning, Deep Learning, Youth-At-Risk, Violence Prevention</span></p> <p><strong><span>JEL Classification Number</span></strong><span>: K42, C45, I38</span></p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_17315022
institution Zenodo
language
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle Using Machine Learning to Enhance Early Intervention in Juvenile Justice through Survey Optimization
Nathan Green
Erik Alda
<p><strong><span>Abstract: </span></strong><span>This paper presents an application of machine learning to optimize a widely used juvenile criminal justice survey in the context of a developing country, towards improving juvenile societal outcomes. The survey, designed to assess the likelihood of youth engaging in risky and delinquent behavior, traditionally suffers from low response rates due to its extensive length. Using machine learning and deep learning methodologies, we demonstrate an approach to streamline the survey process by identifying and prioritizing the most important questions. Our experiments show significant reductions in the number of survey questions needed, while still accurately predicting the likelihood of future delinquency. This optimization addresses the issue of survey fatigue while also enhancing early intervention strategies for at-risk youth. By increasing response rates and facilitating more comprehensive data collection, this approach contributes to the larger social goal of improving outcomes for vulnerable youth populations. This research underscores the potential of AI technologies in the realm of social good, where the convergence of data science and juvenile justice holds promise to create a positive social impact.</span></p> <p><strong><span>Keywords</span></strong><span>: Machine Learning, Deep Learning, Youth-At-Risk, Violence Prevention</span></p> <p><strong><span>JEL Classification Number</span></strong><span>: K42, C45, I38</span></p>
title Using Machine Learning to Enhance Early Intervention in Juvenile Justice through Survey Optimization
url https://doi.org/10.5281/zenodo.17315022