Keywords
neural networks
long short-term memory
LSTM
recurrent neural networks
How to Cite
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
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
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
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
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
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
Fan, J., & Yao, Q. (2008). Nonlinear time series: Nonparametric and parametric methods. Springer Science & Business Media.
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
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
Zhou, S. K., Rueckert, D., & Fichtinger, G. (Eds.). (2019). Handbook of medical image computing and computer assisted intervention. Academic Press.
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
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
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
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/
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
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
Brockwell, P. J., & Davis, R. A. (1991). Time Series: Theory and Methods. Springer Science & Business Media.
Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: Principles and Practice. OTexts.
Resnick, S. I. (2013). Adventures in Stochastic Processes. Springer Science & Business Media.
Peña, D. (2005). Análisis de Series Temporales. Alianza Editorial.
Lipton, Z. C., Berkowitz, J., & Elkan, C. (2015). A Critical Review of Recurrent Neural Networks for Sequence Learning. https://arxiv.org/abs/1506.00019
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
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
Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211. https://doi.org/10.1207/ s15516709cog1402_1
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright (c) 2025 Juan Pablo Perez Leal, Andrés Ríos, David Romo-Bucheli