364
Views
1
CrossRef citations to date
0
Altmetric
Articles

The Built Environment and Predicting Child Maltreatment: An Application of Random Forests to Risk Terrain Modeling

Pages 67-78 | Received 03 Dec 2020, Accepted 26 Jun 2021, Published online: 13 Oct 2021
 

Abstract

An estimated one third of children in the United States will suffer from maltreatment. The use of spatial predictive analytics offers an opportunity to delineate places at elevated risk of child abuse. Risk terrain modeling is a spatial analytic framework for predicting instances of varied types of crime. This article compares a random forest negative binomial model in a risk terrain modeling framework to the question of predicting counts of substantiated child abuse in Portland, Oregon. The final model specification includes domestic incident data from the Portland Police Bureau, built environment data from the City of Portland, OpenStreetMap data, and a neighborhood deprivation index derived from American Community Survey data predicting counts of substantiated child maltreatment from the Oregon Department of Human Services administrative data. The random forest outperforms the negative binomial model, showing its superiority in a risk terrain modeling framework, though the relative lack of predictive importance of the built environment variables compared to the domestic incident neighborhood deprivation variables should encourage researchers to further investigate the role of the built environment in the problem of predicting child abuse and maltreatment.

据估计, 美国有三分之一的儿童受到虐待。空间预测分析能划分虐待儿童高风险地区。风险建模是预测各种犯罪案件的空间分析框架。本文比较了风险建模框架的随机森林负二项式模型、预测美国俄勒冈州波特兰市已证实虐待儿童数量。模型包括了波特兰警察局的案件数据、波特兰的建筑环境数据、OpenStreetMap数据。模型还从美国社区调查数据提取了社区剥夺指数, 用于预测俄勒冈州公共服务部行政数据中已证实的虐待儿童数量。随机森林优于负二项式模型, 显示了随机森林在风险建模框架中的优势。但是, 与案件社区剥夺变量相比, 随机森林没有考虑建筑环境变量的重要性, 研究人员应深入研究建筑环境在预测虐待儿童中的作用。

Se calcula que un tercio de los niños de Estados Unidos padecerán de maltrato. El uso de analíticas predictivas espaciales ofrece la oportunidad de delinear lugares que presentan un riesgo pronunciado de abuso de menores. La modelización de terrenos riesgosos es un marco analítico espacial, que sirve para predecir instancias de tipos variados de crimen. Este artículo compara un modelo binomial negativo de bosque aleatorio dentro de un marco de modelización de terreno riesgoso con el interrogante de predecir recuentos de abuso infantil sustanciados en Portland, Oregón. La especificación final del modelo incluye datos de incidentes domésticos del Bureau Policial de Portland, datos sobre el entorno edificado de la Ciudad de Portland, datos del OpenStreetMap, y un índice de privación vecinal derivado de los datos de la Encuesta Americana de la Comunidad, que predice los recuentos de maltrato infantil sustanciados a partir de datos administrativos del Departamento de Servicios Humanos de Oregón. El bosque aleatorio supera al modelo binomial negativo, mostrando su superioridad en un marco de modelización de terreno riesgoso, aunque la relativa falta de importancia predictiva de las variables del entorno edificado, en comparación con las variables de privación vecinal de los incidentes domésticos, debería estimular a los investigadores a indagar mucho más sobre el papel del entorno construido en el problema de la predicción del abuso y el maltrato infantil.

Additional information

Notes on contributors

Jamaal W. Green

JAMAAL GREEN is a Postdoctoral Scholar in the Department of City and Regional Planning, University of Pennsylvania, Philadelphia, PA 19104. E-mail: [email protected]. His research interests include the application of spatial analysis to urgent questions in urban planning, local labor market change, and social inequality.

Reprints and Corporate Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

To request a reprint or corporate permissions for this article, please click on the relevant link below:

Academic Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

Obtain permissions instantly via Rightslink by clicking on the button below:

If you are unable to obtain permissions via Rightslink, please complete and submit this Permissions form. For more information, please visit our Permissions help page.