Predictive and prescriptive analytics, machine learning and child welfare risk assessment: The Broward County experience. (October 2017)

• Record Type: Journal Article
• Authors: Schwartz, Ira M.; York, Peter; Nowakowski-Sims, Eva; Ramos-Hernandez, Ana
• Is Part Of: Children and youth services review. Volume 81(2017:Oct.)
• Page Start: 309
• Page End: 320
• Publication Date: 2017-10
• Subjects: Child Welfare -- Analytics -- Machine Learning; Social work with children -- Periodicals; Social work with youth -- Periodicals; Adolescent -- Periodicals; Child Welfare -- Periodicals; Social Work -- Periodicals; Service social aux enfants -- Périodiques; Service social à la jeunesse -- Périodiques; Electronic journals; 362.705
• DOI: 10.1016/j.childyouth.2017.08.020
• Languages: English
• ISSNs: 0190-7409

Abstract

Highlights: Accuracy of Broward County risk assessment tool improved using analytics and machine learning Improved accuracy will lead to better child and family outcomes Analytics and machine learning algorithms developed increase predictive power of the Broward County risk assessment instrument Issues needing further research identified. Abstract: This paper presents the findings from a study designed to explore whether predictive analytics and machine learning could improve the accuracy and utility of the child welfare risk assessment instrument used in Broward County (Ft. Lauderdale, Florida). The findings from this study indicate that, indeed, predictive analytics and machine learning would significantly improve the accuracy and utility of the child welfare risk assessment instrument being used. If the predictive analytic and machine learning algorithms developed in this study would be deployed, there would be improved accuracy in identifying low, moderate and high risk cases, better matching between the needs of children and families and available services and improved child and family outcomes. This paper also identifies further areas of research and study.