Measuring the unmeasurable - a project of domestic violence risk prediction and management

TL;DR

This paper presents a novel machine learning approach using random forest to predict domestic violence risk, improving prevention efforts and reducing social workers' workload in Taiwan.

Contribution

It introduces the first application of machine learning for domestic violence risk prediction and demonstrates its effectiveness in a real-world social work context.

Findings

Achieved 96.3% accuracy and 62.8% F1-measure in risk prediction

Built a DV risk map using spatial pattern analysis

Significantly reduced social workers' workload

Abstract

The prevention of domestic violence (DV) have aroused serious concerns in Taiwan because of the disparity between the increasing amount of reported DV cases that doubled over the past decade and the scarcity of social workers. Additionally, a large amount of data was collected when social workers use the predominant case management approach to document case reports information. However, these data were not properly stored or organized. To improve the efficiency of DV prevention and risk management, we worked with Taipei City Government and utilized the 2015 data from its DV database to perform a spatial pattern analysis of the reports of DV cases to build a DV risk map. However, during our map building process, the issue of confounding bias arose because we were not able to verify if reported cases truly reflected real violence occurrence or were simply false reports from potential victim's neighbors. Therefore, we used the random forest method to build a repeat victimization risk prediction model. The accuracy and F1-measure of our model were 96.3% and 62.8%. This model helped social workers differentiate the risk level of new cases, which further reduced their major workload significantly. To our knowledge, this is the first project that utilized machine learning in DV prevention. The research approach and results of this project not only can improve DV prevention process, but also be applied to other social work or criminal prevention areas.