Predicting Crime Using Spatial Features

TL;DR

This paper develops a machine learning approach for crime prediction using geospatial features, including hotpoints and spatial distances, demonstrating improved accuracy on Halifax crime data.

Contribution

Introduces a novel feature engineering method using hotpoints and spatial distances for crime prediction with machine learning models.

Findings

Significant performance improvement with new spatial features

Effective use of HDBSCAN for identifying crime hotspots

Enhanced prediction accuracy on real-world crime data

Abstract

Our study aims to build a machine learning model for crime prediction using geospatial features for different categories of crime. The reverse geocoding technique is applied to retrieve open street map (OSM) spatial data. This study also proposes finding hotpoints extracted from crime hotspots area found by Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). A spatial distance feature is then computed based on the position of different hotpoints for various types of crime and this value is used as a feature for classifiers. We test the engineered features in crime data from Royal Canadian Mounted Police of Halifax, NS. We observed a significant performance improvement in crime prediction using the new generated spatial features.