Deep Learning for Real-Time Crime Forecasting and its Ternarization

TL;DR

This paper introduces a deep learning model for real-time crime forecasting that outperforms existing methods and includes a ternarization technique to reduce resource consumption for deployment.

Contribution

It presents a novel spatial-temporal residual network for crime prediction and a ternarization method for efficient deployment in real-world scenarios.

Findings

The proposed model achieves higher accuracy than existing approaches.

Ternarization significantly reduces resource consumption.

Model effectively predicts crime distribution in Los Angeles at hourly scales.

Abstract

Real-time crime forecasting is important. However, accurate prediction of when and where the next crime will happen is difficult. No known physical model provides a reasonable approximation to such a complex system. Historical crime data are sparse in both space and time and the signal of interests is weak. In this work, we first present a proper representation of crime data. We then adapt the spatial temporal residual network on the well represented data to predict the distribution of crime in Los Angeles at the scale of hours in neighborhood-sized parcels. These experiments as well as comparisons with several existing approaches to prediction demonstrate the superiority of the proposed model in terms of accuracy. Finally, we present a ternarization technique to address the resource consumption issue for its deployment in real world. This work is an extension of our short conference proceeding paper [Wang et al, Arxiv 1707.03340].