A twist in Intimate Partner Violence Risk Assessment Tools: Gauging the contribution of exogenous and historical variables

作者：

Highlights：

• Analysis of the largest dataset in IPVRAT to date: 2-year evolution of 46,047 cases.

• Study of the predictive value of exogenous and historical variables.

• New research paradigm: the direct estimation of the Optimal Protection Level.

• Comparison of multiclass vs ordinal classification paradigms in the context of IPV.

• New model that corrects over 25% of the cases infra-protected by the original system.

摘要

•Analysis of the largest dataset in IPVRAT to date: 2-year evolution of 46,047 cases.•Study of the predictive value of exogenous and historical variables.•New research paradigm: the direct estimation of the Optimal Protection Level.•Comparison of multiclass vs ordinal classification paradigms in the context of IPV.•New model that corrects over 25% of the cases infra-protected by the original system.

论文关键词：Police Risk Assessment,Reassault Risk Assessment,Machine learning,VioGén system,Intimate Partner Violence,Gender violence

论文评审过程：Received 24 June 2021, Revised 4 September 2021, Accepted 6 October 2021, Available online 13 October 2021, Version of Record 22 October 2021.

论文官网地址：https://doi.org/10.1016/j.knosys.2021.107586