Identifying domestic violence victims at high risk of future harm is one possible way to reduce female homicides, half of which are precipitated by domestic violence. Targeted approaches — which attempt to identify high-risk victims and intervene effectively — offer a potential solution but have not been rigorously evaluated. We study this approach in Chicago, where domestic violence victims gauged to be at high risk by prosecutors are selected for additional outreach as well as prosecutorial and advocacy resources. Using a rigorous quasi-experimental research design, we show that this approach rapidly and persistently lowers the likelihood of homicide for victims at high risk of future harm. Additionally, we compare how efficiently prosecutors target this resource relative to a standard machine learning algorithm that predicts homicide risk.
The Impact of Specialized Prosecution on the Safety of Domestic Violence Victims
10-minute talk about the evaluation