Generating incident-level artificial data using GIS based crime simulation

Most crime analysis tools used to find criminals of a particular incident or, to find the interrelations among the crime incidents, possibly over a GIS (Geographical Information System) map. The development of these tools require access to incident-level crime data. Obtaining real data is very restricted if not possible due to the official regulations. In this paper, a parametric model is proposed to generate the incident-level crime datasets involving crimes, criminals and criminals´ suspicious acquaintances where the parameters are used for fine tuned adaptation of the model. The motivation for this approach is that unsupervised approaches for crime analysis do not require fully realistic data set in order to develop decision making algorithms. The model is based on GIS by approximating the characteristics of the population in real-life. Then, results of various GIS related queries are demonstrated on the GIS map to enable the visual analysis of the incidents.