Crime Hotspot Prediction Using Deep Graph Convolutional Networks

TL;DR

This paper introduces a graph convolutional network framework for crime hotspot prediction, effectively modeling spatial dependencies and outperforming traditional methods in accuracy and interpretability.

Contribution

The novel GCN-based approach explicitly captures spatial relationships in crime data, improving prediction accuracy and hotspot visualization over classical algorithms.

Findings

Achieved 78% classification accuracy on Chicago Crime Dataset.

Generated interpretable heat maps of crime hotspots.

Outperformed traditional methods like KDE and SVM.

Abstract

Crime hotspot prediction is critical for ensuring urban safety and effective law enforcement, it remains challenging due to complex spatial dependencies that are inherent in criminal activities. The traditional approaches use classical algorithms such as the KDE and SVM to model data distributions and decision boundaries. The methods often fail to capture these spatial relationships, treating crime events as independent and ignoring geographical interactions. To address this, we propose a novel framework based on Graph Convolutional Networks (GCNs), which explicitly model all of spatial dependencies by representing crime data as a graph. In this graph, nodes represent discrete geographic grid cells and edges capture proximity relationships. The spatial features from Chicago Crime Dataset are used in this system, a multi-layer GCN model is trained to classify crime types and predict high-risk zones. Our approach significantly outperforms traditional approaches, achieving 78% classification accuracy. Moreover, the model generates interpretable heat maps of crime hotspots, demonstrating the usefulness of graph-based learning for predictive policing and spatial criminology.