Spatio-Temporal Pattern Analysis and Prediction for Urban Crime

Zhe Li, Tianfan Zhang, Zhi Yuan, Zhiang Wu, Du Zhen

2018 · 20 citations · 15 references

Concepts

Abstract

This paper aims to analyze the intrinsic characteristics of urban crime in China by quantifying the crime data in the original case record. By comparing the predicted result of the crime situation with the observation, the intrinsic characteristic and its law are validated. Firstly, a quantitative method of case information based on Chinese description is developed, which can be used to transform the unstructured information in the case record to the security degree of the model. Secondly, analysis of the internal characteristics of the case, from the number of cases, the occurrence of time and location. Thirdly, an autoregressive integrated moving average model (ARIMA) based crime prediction model is presented for predict the situation of crime over a period of time. The experimental results demonstrate that the predicted results are in line with the true values, and the predicted results show the same criminal characteristics.

References

15