Evaluating Crime Prediction in Space and Time: A Practical Framework
DOI:
https://doi.org/10.5753/reic.2025.6037Keywords:
Crime Forecasting, Spatio-Temporal Models, Public Safety, Predictive Model EvaluationAbstract
Spatio-temporal predictive models are essential for forecasting crime locations and times, supporting public security in resource management. However, the absence of standardized evaluation criteria limits the comparison of different approaches. To overcome this, we present STEval, a flexible evaluation framework. STEval's robustness was validated through experiments varying time and space granularity. Results showed that no model outperforms others in all scenarios, emphasizing context-specific suitability. The framework aids in selecting and optimizing models through detailed analyses. Additionally, STEval exposes each model's strengths and weaknesses, fostering improvements in crime prediction research.
Downloads
References
Alves, L. G., Ribeiro, H. V., and Rodrigues, F. A. (2018). Crime prediction through urban metrics and statistical learning. Physica A: Statistical Mechanics and its Applications. DOI: 10.1016/j.physa.2018.03.084.
Battersby, S. E., Finn, M. P., Usery, E. L., and Yamamoto, K. H. (2014). Implications of web mercator and its use in online mapping. Cartographica, 49(2):85–101. DOI: 10.3138/carto.49.2.2313.
Butt, U. M., Letchmunan, S., Hassan, F. H., Ali, M., Baqir, A., Koh, T. W., and Sherazi, H. H. R. (2021). Spatio-temporal crime predictions by leveraging artificial intelligence for citizens security in smart cities. IEEE Access, 9:47516–47529. DOI: 10.1109/ACCESS.2021.3068306.
Catlett, C., Cesario, E., Talia, D., and Vinci, A. (2019). Spatio-temporal crime predictions in smart cities: A data-driven approach and experiments. Pervasive and Mobile Computing, 53:62–74. DOI: 10.1016/j.pmcj.2019.01.003.
da Silva, A. R. C., de Paula Júnior, I. C., da Silva, T. L. C., de Macêdo, J. A. F., and Silva, W. C. P. (2020). Prediction of crime location in a brazilian city using regression techniques. In IEEE 32nd International Conference on Tools with Artificial Intelligence. DOI: 10.1109/ICTAI50040.2020.00059.
Du, Y. and Ding, N. (2023). A systematic review of multi-scale spatio-temporal crime prediction methods. ISPRS International Journal of Geo-Information, 12(6). DOI: 10.3390/ijgi12060209.
Han, X., Hu, X., Wu, H., Shen, B., and Wu, J. (2020). Risk prediction of theft crimes in urban communities: An integrated model of lstm and st-gcn. IEEE Access, 8. DOI: 10.1109/ACCESS.2020.3041924.
Hu, Y., Wang, F., and Zhu, H. (2018). A spatio-temporal kernel density estimation framework for predictive crime hotspot mapping and evaluation. Applied Geography. DOI: 10.1016/j.apgeog.2018.08.001.
Li, Z., Huang, C., Xia, L., Xu, Y., and Pei, J. (2022). Spatial-temporal hypergraph self-supervised learning for crime prediction. In 2022 IEEE 38th ICDE. DOI: 10.1109/ICDE53745.2022.00269.
Mandalapu, V., Elluri, L., Vyas, P., and Roy, N. (2023). Crime prediction using machine learning and deep learning: A systematic review. IEEE Access. DOI: 10.1109/ACCESS.2023.3286344.
Santos-Marquez, F. (2022). Spatial beta-convergence forecasting models: Evidence from municipal homicide rates in colombia. Journal of Forecasting, 41(2):294–302. DOI: 10.1002/for.2816.
Villegas, J. R., Pabón, J. S. M., Dulce Rubio, M., Quintero, S., Vargas, J. G., and García, H. (2022). Spatio temporal sparsity in homicide prediction models. IEEE Access, 10. DOI: 10.1109/ACCESS.2022.3143858.
Vinagre, J., Jorge, A. M., Rocha, C., and Gama, J. (2021). Statistically robust evaluation of stream-based recommender systems. IEEE TKDE, 33(7):2971–2982. DOI: 10.1109/TKDE.2019.2960216.
Xia, L., Huang, C., Xu, Y., Dai, P., Bo, L., Zhang, X., and Chen, T. (2021). Spatial-temporal sequential hypergraph network for crime prediction with dynamic multiplex relation learning. In Proceedings of the Thirtieth IJCAI. DOI: 10.24963/ijcai.2021/225.
Zhou, Z. and Matteson, D. S. (2015). Predicting ambulance demand: a spatio-temporal kernel approach. In Proceedings of the 21th ACM SIGKDD. DOI: 10.1145/2783258.2788570.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 The authors
This work is licensed under a Creative Commons Attribution 4.0 International License.
