Spatiotemporal prediction of theft risk with deep inception-residual networks

Spatiotemporal prediction of crime is crucial for public safety and smart cities operation. As crime incidents are distributed sparsely across space and time, existing deep-learning methods constrained by coarse spatial scale offer only limited values in prediction of crime density. This paper proposes the use of deep inception-residual networks (DIRNet) to conduct fine-grained, theft-related crime prediction based on non-emergency service request data (311 events). Specifically, it outlines the employment of inception units comprising asymmetrical convolution layers to draw low-level spatiotemporal dependencies hidden in crime events and complaint records in the 311 dataset. Afterward, this paper details how residual units can be applied to capture high-level spatiotemporal features from low-level spatiotemporal dependencies for the final prediction. The effectiveness of the proposed DIRNet is evaluated based on theft-related crime data and 311 data in New York City from 2010 to 2015. The results confirm that the DIRNet obtains an average F1 of 71%, which is better than other prediction models.