Spatiotemporal Analysis and Prediction of Crime Events in Atlanta Using Deep Learning

Abstract

As a major social problem in Atlanta, one of the cities with high criminal rates in United States, crime has been threatening public security for a long time. Many researches proposed that crime events have characteristics of spatial aggregation and temporal dependence. Therefore, criminal events are predictable, and criminal analysis and prediction is very helpful for law enforcement agencies to more efficiently allocate the limited police forces. In this paper, we use the real crime data set in Atlanta area from 2009 to 2016 to obtain the criminal spatiotemporal distribution features, and make spatiotemporal statistics and visualizations. To predict the daily occurrences of Atlanta crime events, we choose LSTM (long-short term memory) to capture the dependence in time lag and spatial distribution of criminal events. In addition, we discuss the effects of different spatiotemporal scales on the accuracy of crime prediction. When the input time series length is 50 days and the spatial cell size is 0.05 degree, the correlation coefficient R value between the predicted value and the observed records reaches over 0.87. The results provide references for citizens or travelers to avoid hazardous locations, and help law enforcement agencies to allocate resources appropriately.