Exploring Machine Learning to Support Decision-Making for Placement Stabilization and Preservation in Child Welfare.
Saved in:
| Title: | Exploring Machine Learning to Support Decision-Making for Placement Stabilization and Preservation in Child Welfare. |
|---|---|
| Authors: | Chor, Ka Ho Brian, Luo, Zhidi, Rodolfa, Kit T., Ghani, Rayid |
| Source: | Journal of Child & Family Studies. Jan2025, Vol. 34 Issue 1, p282-297. 16p. |
| Subjects: | Child welfare, Random forest algorithms, Prediction models, Research funding, Logistic regression analysis, Decision making in clinical medicine, Descriptive statistics, Foster home care, Health planning, Machine learning, Decision trees, Residential care, Regression analysis, Health care rationing |
| Abstract: | The Family First Prevention Services Act requires youth's placement in residential care to be clinically appropriate, time-limited, and only when youth's needs cannot be met in family-like settings in foster care. State child welfare agencies can benefit from upstream, empirical decision support to preempt youth's placement disruption, coordinate proactive placement stabilization services, prevent unnecessary step-up to residential care, and improve outcomes for the youth. This statewide case study explores the potential benefit to child welfare decision support for placement stabilization and diversion from residential care, by comparing predictive machine learning (ML) models with conventional regression models. We analyzed child welfare spells of 12,621 youth in one large Midwestern state between January 2017 and January 2020. Caseworkers could refer youth to a placement stabilization and preservation program. To predict youth's monthly program need in the next 6 months, we developed and validated a wide grid of ML models—random forest, regularized logistic regression, decision tree, dummy classifier—and a conventional unregularized logistic regression model, using literature-informed predictors from child welfare administrative data. We retrained, retested, and compared all models over time using temporal hold-out sets. Based on anticipated program capacity, model evaluation focused on accuracy in identifying the 100 highest-need youth, fairness, and equity of resource allocation. Random forest models produced the best performance with a precision (positive predictive value) 10 times greater than baseline precision. Common important predictors across models included youth's age, history of placement changes, and emotional/behavioral needs. We discuss potential applications of ML to support preventive child welfare decisions, adapt to policy changes, and allocate limited resources. Highlights: Machine learning (ML) predictions can inform preventive services for youth at risk placement disruption in foster care. A wide grid of ML and regression predictive models predicted youth's need for a Midwestern state placement stabilization program. Random forest models consistently outperformed other models; all models were further compared on fairness and equity. Well-designed ML predictive models can support proactive casework decision-making and preventive resource allocation. [ABSTRACT FROM AUTHOR] |
| Copyright of Journal of Child & Family Studies is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Psychology and Behavioral Sciences Collection |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | The Family First Prevention Services Act requires youth's placement in residential care to be clinically appropriate, time-limited, and only when youth's needs cannot be met in family-like settings in foster care. State child welfare agencies can benefit from upstream, empirical decision support to preempt youth's placement disruption, coordinate proactive placement stabilization services, prevent unnecessary step-up to residential care, and improve outcomes for the youth. This statewide case study explores the potential benefit to child welfare decision support for placement stabilization and diversion from residential care, by comparing predictive machine learning (ML) models with conventional regression models. We analyzed child welfare spells of 12,621 youth in one large Midwestern state between January 2017 and January 2020. Caseworkers could refer youth to a placement stabilization and preservation program. To predict youth's monthly program need in the next 6 months, we developed and validated a wide grid of ML models—random forest, regularized logistic regression, decision tree, dummy classifier—and a conventional unregularized logistic regression model, using literature-informed predictors from child welfare administrative data. We retrained, retested, and compared all models over time using temporal hold-out sets. Based on anticipated program capacity, model evaluation focused on accuracy in identifying the 100 highest-need youth, fairness, and equity of resource allocation. Random forest models produced the best performance with a precision (positive predictive value) 10 times greater than baseline precision. Common important predictors across models included youth's age, history of placement changes, and emotional/behavioral needs. We discuss potential applications of ML to support preventive child welfare decisions, adapt to policy changes, and allocate limited resources. Highlights: Machine learning (ML) predictions can inform preventive services for youth at risk placement disruption in foster care. A wide grid of ML and regression predictive models predicted youth's need for a Midwestern state placement stabilization program. Random forest models consistently outperformed other models; all models were further compared on fairness and equity. Well-designed ML predictive models can support proactive casework decision-making and preventive resource allocation. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 10621024 |
| DOI: | 10.1007/s10826-024-02993-x |
