Skip to main navigation menu Skip to main content Skip to site footer

Articles

Vol. 17 No. 1 (2025)

A temporal approach to urban crime forecasting using recurrent neural networks

Submitted
November 29, 2024
Published
2025-05-12

Abstract

This study investigates the use of Recurrent Neural Networks (RNNs) and Long ShortTerm Memory (LSTM) networks to predict crime patterns in Bucaramanga, Colombia. A temporal approach is presented, which starts by splitting the city into 17 communes. Using a dataset of robbery incidents from 2016 to January 2023, we developed individual time series models for each commune. Then, we used the Root Mean Squared Error (RMSE) as the evaluation metric in these regression tasks. The LSTM models consistently outperformed both the RNN and ARIMA models, a classical methodology for time series prediction, achieving lower RMSE scores. The LSTM model yielded an average RMSE of 2.875 (with a standard deviation of 1.657), which is considerably lower than that obtained by the RNN model 3.101 (1.82) and the ARIMA model 3.428 (2.57). These results show that LSTM better captures the complex temporal dependencies in the data. Future work should explore hybrid models and the incorporation of additional data sources to enhance predictive accuracy further.

References

  1. Thomas, A., & Sobhana, N. (2022). A survey on crime analysis and prediction. Materials Today: Proceedings, 58, 310– 315. https://doi.org/10.1016/j.matpr.2022.02.170
  2. Ghani, U., Toth, P., & David, F. (2023). Predictive choropleth maps using ARIMA time series forecasting for crime rates in Visegrád group countries. Sustainability, 15(10), 8088. https://doi.org/10.3390/su15108088
  3. Noor, T. H., Almars, A. M., Alwateer, M., Almaliki, M., Gad, I., & Atlam, E. S. (2022). SARIMA: A seasonal autoregressive integrated moving average model for crime analysis in Saudi Arabia. Electronics, 11(23), 3986. https://doi. org/10.3390/electronics11233986
  4. Escudero, I., Angulo, J. M., & Mateu, J. (2022). A spatially correlated model with generalized autoregressive conditionally heteroskedastic structure for counts of crimes. Entropy,24(7), 892. https://doi.org/10.3390/e24070892
  5. Delitos ocurridos en el Municipio de Bucaramanga | Datos Abiertos Colombia. (2018, October 22). Retrieved October 20, 2023 from https://www.datos.gov.co/Seguridad-y-Defensa/Delitos-ocurridos-en-el-Municipio-deBucaramanga/75fz-q98y/about_data
  6. Fan, J., & Yao, Q. (2008). Nonlinear time series: Nonparametric and parametric methods. Springer Science & Business Media.
  7. Al-Selwi, S. M., Hassan, M. F., Abdulkadir, S. J., Muneer, A., Sumiea, E. H., Alqushaibi, A., & Ragab, M. G. (2024). RNNLSTM: From applications to modeling techniques and beyond—Systematic review. Journal of King Saud UniversityComputer and Information Sciences, 36(5), 102068. https://doi.org/10.1016/j.jksuci.2024.102068
  8. Wang, Q., Guo, Y., Yu, L., & Li, P. (2017) Earthquake prediction based on spatio-temporal data mining: An LSTM network approach. IEEE Transactions on Emerging Topics in Computing, 8(1), 148–158. https://doi.org/10.1109/ TETC.2017.2699169
  9. Zhou, S. K., Rueckert, D., & Fichtinger, G. (Eds.). (2019). Handbook of medical image computing and computer assisted intervention. Academic Press.
  10. Zhang, J., Zeng, Y., & Starly, B. (2021). Recurrent neural networks with long term temporal dependencies in machine tool wear diagnosis and prognosis. SN Applied Sciences, 3(4), 442. https://doi.org/10.1007/s42452-021-04427-5
  11. Jiang, N., Miao, K., Chai, Y., Lu, D., & Wu, J. (2023). Spatio-temporal prediction of crime based on data mining and LSTM network. 2023 IEEE 6th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), 6, 672–676. https://doi.org/10.1109/ITNEC56291.2023.10081985
  12. Wang, S., & Yuan, K. (2019). Spatiotemporal analysis and prediction of crime events in Atlanta using deep learning. 2019 IEEE 4th International Conference on Image, Vision and Computing (ICIVC), 346–350. http://dx.doi.org/10.1109/ ICIVC47709.2019.8981090
  13. Zambrano, R. (2022). Un enfoque Espacio Temporal para la predicción de delitos en la ciudad de Buenos Aires. Revista de Investigación de Modelos Matemáticos Aplicados a la Gestión y a la Economía, 2, 38–62. http://www.economicas. uba.ar/institutos_y_centros/revista-modelos-matematicos/
  14. Alcaldía de Bucaramanga: Plan Integral de Seguridad y Convivencia para una Bucaramanga Segura 2020-2023. (2020). https:// www.bomberosdebucaramanga.gov.co/contenido/wp-content/uploads/2023/04/PISCC-Bucaramanga-2020-2023.pdf
  15. Uma Devi, B., Sundar, D., & Alli, P. (2013). An effective time series analysis for stock trend prediction using ARIMA model for nifty midcap-50. International Journal of Data Mining & Knowledge Management Process, 3(1), 65-78. http://dx.doi.org/10.5121/ijdkp.2013.3106
  16. Brockwell, P. J., & Davis, R. A. (1991). Time Series: Theory and Methods. Springer Science & Business Media.
  17. Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: Principles and Practice. OTexts.
  18. Resnick, S. I. (2013). Adventures in Stochastic Processes. Springer Science & Business Media.
  19. Peña, D. (2005). Análisis de Series Temporales. Alianza Editorial.
  20. Lipton, Z. C., Berkowitz, J., & Elkan, C. (2015). A Critical Review of Recurrent Neural Networks for Sequence Learning. https://arxiv.org/abs/1506.00019
  21. Li, J., Xu, H., Deng, J., & Sun, X. (2016). Hyperbolic linear units for deep convolutional neural networks. 2016 International Joint Conference on Neural Networks (IJCNN), 353-359. https://doi.org/10.1109/IJCNN.2016.7727220
  22. Gers, F., Schmidhuber, J., & Cummins, F. (1999). Learning to forget: Continual prediction with LSTM. 1999 Ninth International Conference on Artificial Neural Networks ICANN99, 2, 850–855. https://doi.org/10.1049/cp:19991218
  23. Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211. https://doi.org/10.1207/ s15516709cog1402_1

Downloads

Download data is not yet available.