Early Warning System for Crime Hot Spots

Objectives Using violent crime data from Pittsburgh, Pennsylvania we investigate the performance of an “early warning system” (EWS) for starting/stopping police deployments to hot spots for crime prevention. We show that (1) even the hottest chronic hot spots are dynamic with months “on” and “off” and (2) temporary hot spots are also targets for prevention. We compare the performance of EWS to constant deployment at chronic hot spots. Methods We estimate chronic hot spots using kernel density smoothing. We use simple methods for implementing EWS rules for detecting flare-ups, predicting persistence of flare-ups, and stopping deployments. Using 2000–2010 data we run computational experiments varying size of hot spots and rule thresholds to tune EWS. Results Tradeoff curves with crimes exposed to prevention efforts versus area of the city under prevention workload show that static and dynamic deployments have nearly the same efficiency. Different, however, is land-use distribution. While chronic hot spots tend to be in or adjacent to commercial areas, dynamic hot spots have significantly more and widely-scattered residential locations. We argue that dynamic hot spots thus have higher potential for reducing fear of crime and providing responsive police services to neighborhoods. Conclusions Even though police resources are “wasted” during “off” months by constant deployment to chronic hot spots, a dynamic system of deployment with simple methods cannot improve the efficiency of crime prevention. EWS comparably “wastes” resources because of false positives for hot-spot persistence and waiting to confirm hot-spot extinguishment. Nevertheless, EWS is more responsive to residential crime.