Predictive Risk Modelling to Prevent Child Maltreatment and Other Adverse Outcomes for Service Users: Inside the ‘Black Box’ of Machine Learning

  title={Predictive Risk Modelling to Prevent Child Maltreatment and Other Adverse Outcomes for Service Users: Inside the ‘Black Box’ of Machine Learning},
  author={Philip Gillingham},
  journal={British Journal of Social Work},
  pages={1044 - 1058}
  • P. Gillingham
  • Published 8 April 2015
  • Computer Science, Medicine
  • British Journal of Social Work
Recent developments in digital technology have facilitated the recording and retrieval of administrative data from multiple sources about children and their families. Combined with new ways to mine such data using algorithms which can ‘learn’, it has been claimed that it is possible to develop tools that can predict which individual children within a population are most likely to be maltreated. The proposed benefit is that interventions can then be targeted to the most vulnerable children and… 
Using family network data in child protection services
The results quantify the importance of a child’s family network and show that a better understanding of risk can be achieved by linking other commonly available datasets with child protection records to provide the most up-to-date information possible.
Predictive Risk Modelling to Prevent Child Maltreatment: Insights and Implications from Aotearoa/New Zealand
ABSTRACT Predictive risk modeling to identify children at risk of maltreatment has attracted considerable interest internationally. Using the example of the development of the predictive risk model
A Practical Framework for Considering the Use of Predictive Risk Modeling in Child Welfare
Predictive risk modeling (PRM) is a new approach to data analysis that can be used to help identify risks of abuse and maltreatment among children. Several child welfare agencies have considered,
Algorithmically Based Decision Support Tools: Skeptical Thinking about the Inclusion of Previous Involvement
Decision making in social work, especially in child protection services, is increasingly being assisted by algorithmically based decision support tools. These tools assign a quantified level of risk
The Development of Algorithmically Based Decision-Making Systems in Children’s Protective Services: Is Administrative Data Good Enough?
The aim is to address the question of whether children’s protective services data are good enough to develop accurate and practically useful DSS.
Risk assessment and decision making in child protective services: Predictive risk modeling in context
In an era in which child protective service agencies face increased demands on their time and in an environment of stable or shrinking resources, great interest exists in improving risk assessment


Looks can be deceiving: Using a risk assessment instrument to evaluate the out-comes of child protection services
Abstract This study explores the use of a risk assessment instrument based on the Illinois CANTS-17B in the child protection services division of a large urban public social services agency. It
The ethics of predictive risk modelling in the Aotearoa/New Zealand child welfare context: Child abuse prevention or neo-liberal tool?
The White Paper on Vulnerable Children before the Aotearoa/New Zealand parliament proposes changes that will significantly reconstruct the child welfare systems in this country, including the use of
The limitations of using statutory child protection data for research into child maltreatment
Child protection legislation has undergone a number of changes since its inception, changes that have redefined the population of children in need of protection. However, child protection data on
Differentiating Between Substantiated, Suspected, and Unsubstantiated Maltreatment in Canada
Multivariate analyses reveal that substantiation decisions are generally made in a fashion that is relatively consistent with the clinical characteristics of cases, and police referrals are among the most important predictors of case substantiation.
Computational intelligence techniques for risk assessment and decision support
Abstract This study explores the use of artificial neural networks as a tool to assist child welfare and child protective service organizations in making more precise and more accurate risk
The next step: Integrating actuarial risk assessment and clinical judgment into an evidence-based practice framework in CPS case management
Abstract Assessment in child welfare involves at least two distinct processes: an assessment of risk (prediction of future harm) and a contextual assessment of child and family functioning used to
Time to Leave Substantiation Behind
It is suggested that agencies record service needs in the families they serve, and also record whether or not the family meets criteria for referral to the family court, which would be far more practical and meaningful ways to measure child welfare services.
The use of assessment tools in child protection: an ethnomethodological study
This research focused on how child protection practitioners in the Department of Child Safety, Queensland used the Structured Decision Making (SDM) tools in their practice with children and families.