Title |
Predictive Risk Modelling to Prevent Child Maltreatment and Other Adverse Outcomes for Service Users: Inside the ‘Black Box’ of Machine Learning
|
---|---|
Published in |
British Journal of Social Work, April 2015
|
DOI | 10.1093/bjsw/bcv031 |
Pubmed ID | |
Authors |
Philip Gillingham |
Abstract |
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 their families to prevent maltreatment from occurring. As expertise in predictive modelling increases, the approach may also be applied in other areas of social work to predict and prevent adverse outcomes for vulnerable service users. In this article, a glimpse inside the 'black box' of predictive tools is provided to demonstrate how their development for use in social work may not be straightforward, given the nature of the data recorded about service users and service activity. The development of predictive risk modelling (PRM) in New Zealand is focused on as an example as it may be the first such tool to be applied as part of ongoing reforms to child protection services. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
New Zealand | 3 | 43% |
United Kingdom | 1 | 14% |
United States | 1 | 14% |
Sri Lanka | 1 | 14% |
Spain | 1 | 14% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Members of the public | 5 | 71% |
Scientists | 1 | 14% |
Science communicators (journalists, bloggers, editors) | 1 | 14% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
United Kingdom | 1 | <1% |
Australia | 1 | <1% |
Unknown | 151 | 99% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Researcher | 21 | 14% |
Student > Ph. D. Student | 20 | 13% |
Student > Master | 18 | 12% |
Lecturer | 14 | 9% |
Other | 9 | 6% |
Other | 28 | 18% |
Unknown | 43 | 28% |
Readers by discipline | Count | As % |
---|---|---|
Social Sciences | 55 | 36% |
Computer Science | 14 | 9% |
Psychology | 11 | 7% |
Economics, Econometrics and Finance | 4 | 3% |
Nursing and Health Professions | 4 | 3% |
Other | 19 | 12% |
Unknown | 46 | 30% |