Spatio-Temporal Modeling of Criminal Activity

Accurate crime forecasting can allow law enforcement to more effectively plan their resource allocation such as patrol routes and placements. We study the effectiveness of traditional regression approaches in forecasting crime occurrences in Portland, Oregon. We divide the area of interest into equally spaced cells and investigate the spatial autocorrelation between the crime occurrence rates of neighboring cells. We also attempt to use neighboring cells' information in the regression models along with the cell's own time series to enhance the forecast results. Our results show that regression is a promising method that outperforms a moving window averaging method, especially when the future horizon to be predicted increases. However, addition of neighborhood cells decreased the quality of predictions, suggesting that spatial correlation in crime is more complex than geographical neighborhood. We also explore a possibility of connection of criminal activities and popularity of crime incidents in Portland on the Web, and discuss future directions we will take to improve crime prediction.