Authors : Kelvin Leong , Stephen Chan , Vincent Ng and Simon Shiu
Abstract: Successful law enforcement depends upon information availability. In criminal knowledge discovery, many techniques have been developed for analysis, mapping, modeling and prediction. However, most approaches treat the spatial and temporal aspects of crime as distinct entities, thus, ignoring the necessary interaction of space and time to produce criminal opportunities. In this study, a new crime pattern analysis model, STEM (Space-Time-Event Model) is presented. The new model allows users to investigate the spatio-temporal patterns of events. We also discuss relevant crime theories and related data mining methods. Two experiments were conduced to test the model. Using STEM, we found strong correlations between holidays and crime clusters. On the other hand, we could not find obvious seasonal dependency, at least in our test data set. These findings are corroborated by related empirical crime studies.
Kelvin Leong , Stephen Chan , Vincent Ng and Simon Shiu , 2008. Introduction of STEM: Space-Time-Event Model for Crime Pattern Analysis. Asian Journal of Information Technology, 7: 516-523.