Deep Learning for Real-Time Crime Forecasting and its Ternarization
This work addresses crime prediction for public safety in Los Angeles, but it is incremental as it extends a previous conference paper.
The authors tackled real-time crime forecasting by adapting a spatial temporal residual network on a new representation of sparse crime data, achieving superior accuracy compared to existing methods. They also introduced a ternarization technique to reduce resource consumption for deployment.
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].