Austin Police Department Staffing Project
Patrol Model and Community Survey
Austin is the first city to use machine learning to model police staffing. The Greater Austin Crime Commission funded research at the University of New Haven and Texas State University to develop a patrol model and conduct a community survey for the Austin Police Department. The next research phase has already started to model administrative and specialized units, including investigations.
The patrol model analyzed more than six million officer responses to nearly two million calls for service. Machine learning suggests responding to urgent calls for service within 6 minutes and 30 seconds for the best public safety outcomes. Modeling projects 882 patrol positions are required to meet the target response time, which is 108 above current authorization.