An Adaptive Spatial Resolution Method Based on the ST-ResNet Model for Hourly Property Crime Prediction

Hong Zhang,Jie Zhang,Zengli Wang,Hao Yin

doi:10.3390/ijgi10050314

Abstract

Effective predictive policing can guide police patrols and deter crime. Hourly crime prediction is expected to save police time. The selection of spatial resolution is important due to its strong relationship with the accuracy of crime prediction. In this paper, we propose an adaptive spatial resolution method to select the best spatial resolution for hourly crime prediction. The ST-ResNet model is applied to predict crime risk, with historical crime data and weather data as predictive variables. A prediction accuracy index (PAI) is used to evaluate the accuracy of the results. Data on property crimes committed in Suzhou, a big city in China, were selected as the research data. The experiment results indicate that a 2.4 km spatial resolution leads to the best performance for crime prediction. The adaptive spatial resolution method can be used to guide police deployment.

Highlights

One of the main goals of crime prediction is to efficiently guide police deployment such that predicted crimes can be dealt with effectively [1]
We focus on the accuracy of hourly crime prediction when selecting the optimal unit, and choose the prediction accuracy index (PAI), which can measure the accuracy level of model results, as a criterion to meet the needs of the actual patrol [6]
The STTo improve the effectiveness of hourly crime prediction, we proposed an adaptive

Summary

Introduction

One of the main goals of crime prediction is to efficiently guide police deployment such that predicted crimes can be dealt with effectively [1]. Hotspots are detected and mapped to identify emerging crimes [6,7]. In this context, crime hotspots are assumed to be stable over time [8,9]. Crime hotspots are assumed to be stable over time [8,9] This assumption may work well for long-term high-crime areas due to the concentrated disadvantages [10]. The dynamic nature of crime calls for more proactive methods [19,20]

Methods

Results

Conclusion