Predicting and analyzing crime—Environmental design relationship via GIS‐based machine learning approach

Abstract

Correlation between burglary crime and urban environmental characteristics is crucial for understanding the causes of crime events. Mathematical relationships can be linked between crime and crime‐causing events with the help of the machine learning (ML) model and geographic information system (GIS). The main objective of this research is to analyze and predict burglary crime events by applying ML‐based GIS models for Trabzon and Turkey. Random forest regression (RFR) and support vector regression (SVR) were implemented to predict crime. Correlation between crime and urban physical environmental metrics was used in the prediction model. Due to the result of the analysis, the R2 value was measured as 0.78 with the RFR and 0.71 with the SVR algorithm. The height of the building, the proportion of floor area, the density of buildings, and the density of intersection of streets are the four most important variables that affect the burglary crime rate positively. Conversely, the variable with the lowest effect on burglary crime is the ratio of the park to the residential area.