A method of identifying dark-time crime locations for street lighting purposes

Abstract

Research on the effect of street lighting on crime and fear of crime has received much attention, especially between 1970s and early 2000s. Yet no study has documented an empirical method for choosing where to best site street lights for the purpose of crime prevention. This study describes a statistical clustering method (Kohonen’s SOM) that can be used to identify microplaces where crimes mostly occur during nighttime within stable crime hot spots. The results of this clustering analysis were visually examined and compared with streets, which are located near the University of Cincinnati West Campus and selected for lighting during early 2014. The findings revealed temporal patterns of crime within crime hot spots. In addition, there is a substantial overlap between the areas identified as heavily dark-time locations by clustering analysis and previously lighted streets determined by the city of Cincinnati managers. Implications of the study are discussed in conclusions.