Geographic prediction of crimes against property using Neural Networks and the SARIMA model


predictive model
time series
neural networks
crime analytics

How to Cite

Troncoso EspinosaF. H., & Gomez CorreaD. A. (2022). Geographic prediction of crimes against property using Neural Networks and the SARIMA model. Universidad Ciencia Y Tecnología, 26(113), 103-112.


Predicting the number of crimes that will be committed in a certain geographical area is important for the management of resources destined for crime prevention. This research develops two predictive models of time series for the geographic prediction of property crimes in two districts of Chile Talcahuano and Hualpén. The models investigated were Neural Networks and SARIMA. Both models were trained and tested with the information provided by the Regional Prosecutor's Office of BioBío, Chile. The information contains the crimes against property committed in both districts between 2009 and 2019. The models were compared using the MAPE, MAD, and MSE forecast error measures. The comparison of the results does not show statistically significant differences between the results of both models.

Keywords: Predictive Model, Time Series, Neural Networks, Crime Analitycs.


[1]ENUSC, « Síntesis Delictual ENUSC 2020,» PAÍS, 2020.
[2]AMUCH, «Delitos de mayor connotación social en las comunas de Chile,» Santiago, 2018.
[3]Físcalia de Chile, «Fiscalia de Chile,» Abril 2018. [En línea]. Available: [Último
acceso: Diciembre 2021].
[4]C. Á. Vargas, «Sistemas Judiciales,» Mayo 2020.[En línea]. Available: [Último acceso: Diciembre 2021].
[5]P. Chen, Y. Hongyong y S. Xueming , «Forecasting Crime Using the ARIMA Model,» 2008 Fifth International Conference on Fuzzy Systems and Knowledge
Discovery (FSKD), pp. 627-630, 2008.
[6]E. A. Anderson y J. Díaz, «Using Process Control Chart Techniques to Analyse Crime Rates in Houston, Texas,» The Journal of the Operational Research Society,
vol. 47, nº 7, pp. 871-881, 1996.
[7]F. H. T. Espinosa, «Prediction of Recidivism in Thefts and Burglaries Using Machine Learning,» Indian Journal of Science and Technology, vol. 13, p. 696– 711, 2020.
[8]P. P. Ascencio, «Desarrollo de un modelo predictivo de robo a casas basado en redes neuronales,» Santiago, 2020.
[9]R. F. Reier Forradellas y S. L. Náñez Alonso,«Applied Machine Learning in Social Sciences: Neural Networks and Crime Prediction,» Social Sciences,
[10]F. H. Troncoso Espinoza y N. E. Fernández Rozas, «Limpieza, corrección y geocodificación de grandes bases de datos de direcciones mediante minería de texto,»uct, vol. 25, pp. 80-87, junio 2021.
[11]U. Fayyad, G. Piatetsky-Shapiro y P. Smyth, Advances in Knowledge Discovery and Data Mining, American Association for Artificial Intelligence, 1996.
[12]S. Zhang, «Nearest neighbor selection for iteratively kNN imputation,» Journal of Systems and Software, vol. 85, nº 11, pp. 2541-2552, 2012.
[13]J. A. Mauricio, Introducción al Análisis de Series de Tiempo, Madrid: Universidad de Madrid, 2007.
[14]V. Yakovyna y O. Bachkai, «The Comparison of Holt-Winters and Box - Jenkins Methods for Software Failures Prediction,» COLINS, 2018.
[15]D. Gujarati y D. Porter, Econometría, México D.F.: McGRAW-HILL/INTERAMERICANA EDITORES, S.A. DE C.V, 2010.
[16]R. Krispin, Hands-On Time Series Analysis with R: Perform time series analysis and forecasting using R, Birmingham: Packt, 2019.
[17]D. Mercado y L. Pedraza, «Comparación de Redes Neuronales aplicadas a,» PROSPECTIVA, vol. 13, nº 2, pp. 88-95, 2015.
[18]J. Brownlee, «Machine Learning Mastery,» 8 Mayo 2017. [En línea]. Available:
problem-python/. [Último acceso: Diciembre 2021].
[19]E. Ramalle-Gómara y J. Andres de Llano, «Utilización de métodos robustos en la estadísticainferencial,» Atención Primaria, vol. 32, nº 3, pp. 177-181, 2003.
[20]C. Chatfield, «The Holt-Winters Forecasting Procedures,» Applied Statistics, vol. 27, nº 3, pp. 264-279,1978.
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.


Download data is not yet available.