Prediction of crime occurrence from multi-modal data using deep learning

The prediction of crime occurrences [1–7] has received considerable attention on account of its prospective benefits. This predictive capability would notably contribute to effective police patrols. According to the 2014 Chicago crime record, there were a total of 274,064 incidents of crime in 2014 and an average of 750 cases per day in that city. The results of these crimes, including injuries and deaths, are very serious. Fundamental crime prevention requires the strengthening of patrols, which is costly in terms of financial and human resources.