手法を比較

	Crime Prediction Modeling	Crime Hot Spot Analysis
分野	Criminology	Criminology
系統	Process / pipeline	Process / pipeline
提唱年	2011	1995
提唱者	George Mohler, Martin Short & colleagues (self-exciting point process)	Lawrence Sherman & David Weisburd (policing); Arthur Getis & J. Keith Ord (statistic)
種類	Forecasting model for the space-time risk of crime	Spatial cluster detection for crime concentration
原典	Mohler, G. O., Short, M. B., Brantingham, P. J., Schoenberg, F. P., & Tita, G. E. (2011). Self-exciting point process modeling of crime. Journal of the American Statistical Association, 106(493), 100–108.	Sherman, L. W., & Weisburd, D. (1995). General deterrent effects of police patrol in crime "hot spots": A randomized, controlled trial. Justice Quarterly, 12(4), 625–648.
別名	Predictive Policing, Crime Forecasting, Self-Exciting Point Process Crime Modeling, Predictive Crime Mapping	Hot Spot Mapping, Crime Hotspot Detection, Getis-Ord Gi* Crime Analysis, Spatial Cluster Analysis of Crime
関連	4	4
概要	Crime prediction modeling forecasts where and when crime is most likely to occur next, so that limited resources can be directed before incidents happen rather than after. It spans simple historical hot-spot extrapolation, statistical self-exciting point processes that treat crimes as triggering further crimes, and modern machine-learning models that blend spatial, temporal, and environmental features. The statistical foundation was sharpened by Mohler and colleagues' 2011 demonstration that earthquake-style self-exciting (Hawkes) point processes — in which each crime raises the short-term risk of nearby crimes — forecast urban crime more accurately than conventional hot-spot maps.	Crime hot spot analysis identifies the places where crime concentrates far more than chance — the small number of street segments, blocks, or addresses that account for a large share of incidents. Building on Sherman and Weisburd's landmark demonstration that crime clusters tightly in space and that patrolling those clusters deters offending, the method uses spatial statistics such as the Getis-Ord Gi* local statistic to separate genuine, statistically significant clusters from random noise and to classify each place as a hot spot, a cold spot, or neither.