Predictive Policing

Runaway Feedback Loops in Predictive Policing

Predictive policing systems are increasingly used to determine how to allocate police across a city in order to best prevent crime. Observed crime data (arrest counts) are used to update the model, and the process is repeated. Such systems have been shown susceptible to runaway feedback loops, where police are repeatedly sent back to the same neighborhoods regardless of the true crime rate. In ...

Predicting Financial Crime: Augmenting the Predictive Policing Arsenal

Financial crime is a rampant but hidden threat. In spite of this, predictive policing systems disproportionately target “street crime” rather than white collar crime. This paper presents the White Collar Crime Early Warning System (WCCEWS), a white collar crime predictive model that uses random forest classifiers to identify high risk zones for incidents of financial crime.

A Plea for Harm Reduction Policing Involving People Who Use Drugs

Grid Service Level Agreements Combining Resource Reservation and Predictive Run-time Adaptation

Resource reservation and performance prediction of execution run-times are key components in delivering timely application services for decision support systems. The provision of Service Level Agreements (SLA) and components to manage tasks such as resource negotiation, monitoring and policing are needed to help meet this requirement. This paper presents an SLA management architecture for use i...

Randomized Controlled Field Trials of Predictive Policing

The concentration of police resources in stable crime hotspots has proven effective in reducing crime, but the extent to which police can disrupt dynamically changing crime hotspots is unknown. Police must be able to anticipate the future location of dynamic hotspots to disrupt them. Here we report results of two randomized controlled trials of near real-time epidemic-type aftershock sequence (...