Author(s)

SuZhen Luo¹, ZhiSong Wu², LiNing Yuan^3*

Affiliation(s)

¹Ministry of Public Sports, Guangxi Police College, Nanning 53028, Guangxi, China.

²School of Public Policy and Management, Guangxi Police College, Nanning 53028, Guangxi, China.

³School of Information Technology, Guangxi Police College, Nanning 53028, Guangxi, China.

Corresponding Author

LiNing Yuan

ABSTRACT

The data on theft crimes exhibits characteristics such as dynamism, correlation, and uncertainty in both temporal and spatial dimensions. The factors influencing the occurrence of these crimes are complex and include various elements such as population density, education levels, poverty rates, employment status, and climate conditions. The volume and diversity of this data often pose challenges for traditional situational awareness technologies, which rely on criminological theories and case analyses, making it difficult to meet the actual needs of public security agencies. Consequently, crime data mining algorithms based on machine learning and deep learning have gradually become mainstream. This article analyzes the temporal and spatial characteristics of theft crimes, utilizes the Prophet model to predict future incidents, and employs kernel density estimation functions to identify spatial hotspots of theft crimes.

KEYWORDS

Theft crime; Prophet model; Kernel density estimation; Spatial hotspots

CITE THIS PAPER

SuZhen Luo, ZhiSong Wu, LiNing Yuan. Predicting and analyzing theft crime through temporal and spatial dimensions. Journal of Computer Science and Electrical Engineering. 2025, 7(1): 64-67. DOI: https://doi.org/10.61784/jcsee3038.

REFERENCES

[1] Chainey S, Tompson L, Uhlig S. The utility of hotspot mapping for predicting spatial patterns of crime. Security journal, 2008, 21(1): 4-28.

[2] Travaini G V, Pacchioni F, Bellumore S, et al. Machine learning and criminal justice: A systematic review of advanced methodology for recidivism risk prediction. International journal of environmental research and public health, 2022, 19(17): 10594.

[3] Jenga K, Catal C, Kar G. Machine learning in crime prediction. Journal of Ambient Intelligence and Humanized Computing, 2023, 14(3): 2887-2913.

[4] Johnson S D, Summers L, Pease K. Offender as forager? A direct test of the boost account of victimization. Journal of Quantitative Criminology, 2009, 25: 181-200.

[5] Mondal S, Singh D, Kumar R. Crime hotspot detection using statistical and geospatial methods: a case study of Pune City, Maharashtra, India. GeoJournal, 2022, 87(6): 5287-5303.

[6] Ratcliffe J. Crime mapping: Spatial and temporal challenges. Handbook of quantitative criminology, 2010: 5-24.

[7] Predictive policing and artificial intelligence. Routledge, Taylor & Francis Group, 2021.

[8] Craglia M, Haining R, Wiles P. A comparative evaluation of approaches to urban crime pattern analysis. Urban Studies, 2000, 37(4): 711-729.

[9] Mityagin S A, Ivanov S V, Boukhanovsky A V. Multi-factorial predictive modelling of drug addiction for large urban areas. 2014 IEEE 8th International Conference on Application of Information and Communication Technologies (AICT). IEEE, 2014: 1-7.

[10] Lin H. Unraveling Crime Dynamics: A Spatiotemporal Analysis of Crime Hotspots. Kent State University, 2024.

[11] Taylor S J, Letham B. Forecasting at scale. The American Statistician, 2018, 72(1): 37-45.

[12] Chen Y C. A tutorial on kernel density estimation and recent advances. Biostatistics & Epidemiology, 2017, 1(1): 161-187.