Crime Prediction with Graph Neural Networks and Multivariate Normal Distributions

TL;DR

This paper presents a novel high-resolution crime prediction model using graph neural networks and multivariate Gaussian distributions, effectively capturing spatiotemporal details and addressing data sparsity.

Contribution

Introduces a new GCN-based architecture with a subdivision algorithm and multivariate Gaussian modeling for precise, high-resolution crime forecasting.

Findings

Achieves superior validation and test scores compared to baseline models.

Effectively models spatiotemporal relations in crime data.

Demonstrates both generative capability and high accuracy.

Abstract

Existing approaches to the crime prediction problem are unsuccessful in expressing the details since they assign the probability values to large regions. This paper introduces a new architecture with the graph convolutional networks (GCN) and multivariate Gaussian distributions to perform high-resolution forecasting that applies to any spatiotemporal data. We tackle the sparsity problem in high resolution by leveraging the flexible structure of GCNs and providing a subdivision algorithm. We build our model with Graph Convolutional Gated Recurrent Units (Graph-ConvGRU) to learn spatial, temporal, and categorical relations. In each node of the graph, we learn a multivariate probability distribution from the extracted features of GCNs. We perform experiments on real-life and synthetic datasets, and our model obtains the best validation and the best test score among the baseline models with significant improvements. We show that our model is not only generative but also precise.