Network-based space-time search-window technique for hotspot detection of street-level crime incidents

This study proposes a street-level space-time hotspot detection method to analyse crime incidents recorded at the street-address level and provides description of the micro-level variation of crime incidents over space and time. It expands the notion of search-window techniques widely used in crime science by developing a method that can account for the spatial-temporal distribution of crime incidents measured in network distance. The study first describes the methodological framework by presenting the concept of a new type of search window and how it is used in the process of statistical testing for detecting crime hotspots. This is followed by analyses using (1) a simulated distribution of points along the street network, and (2) a set of real street-crime incident data. The simulation study demonstrates that the proposed method is effective in identifying space-time hotspots, which include those that are not detected by a non-temporal method. The empirical analysis of the drug markets and assaults in downtown Buffalo, New York, revealed a detailed space-time signature of each type of crime, highlighting the recurrent nature of drug dealing at specific locations as well as the sporadic tendency of assault incidents.