Book Title: Computational Criminology: AI Applications in Forensic Science and Criminal Justice
Editors: Dr. Xavier Louis, Dr. Surbhi Girdhar, Ms. Aswathi Chandran Nair, Mr. Ravi Kumar, and Ms. Nandini Katare
Chapter: 8
DOI: https://doi.org/10.59646/704/8
Author: Jismol Thampi
Abstract
Spatial concentration is among the most robust empirical regularities in criminology. A small fraction of street segments, addresses, or grid cells consistently accounts for a disproportionate share of recorded offences across cities, decades, and offence categories. Sherman, Gartin, and Buerger’s landmark 1989 study of Minneapolis call data demonstrated that approximately three percent of street addresses accounted for half of all calls for police service,[1] an empirical claim that has since been replicated across dozens of jurisdictions and that David Weisburd has formalised as the law of crime concentration at place.[2] This regularity underwrote what would become the dominant operational paradigm of contemporary policing place-based crime prevention focused on the small set of micro-locations responsible for most recorded harm.
The computational instruments for identifying and forecasting these concentrations have evolved through three broadly distinguishable generations. The first relied on retrospective kernel density estimation to smooth point patterns of recorded incidents into continuous risk surfaces. The second introduced the risk terrain modelling framework, which identified environmental features independently associated with elevated crime risk and combined them into composite forecasts. The third the subject of this chapter has applied convolutional, recurrent and graph-based neural architectures to integrate static environmental features, dynamic event histories, and human-mobility signals into unified, fine-grained, time-resolved risk forecasts.
[1]Lawrence W Sherman, Patrick R Gartin and Michael E Buerger, “Hot Spots of Predatory Crime: Routine Activities and the Criminology of Place” (1989) 27 Criminology 27, 30.
[2]David Weisburd, “The Law of Crime Concentration and the Criminology of Place” (2015) 53 Criminology 133, 135.