Abstract
This article reviews recent studies on the use of artificial intelligence (AI) for crime prediction and its potential contributions to public security. It analyzes empirical research published between 2019 and 2025 that applies AI, machine learning, or deep learning to crime analysis. Conducted in countries across the Americas and Asia, the studies use supervised and unsupervised methods, neural networks, spatiotemporal analysis, and computer vision. The literature reports applications for identifying patterns and risk areas, estimating crime trends, and supporting resource allocation. However, approaches and findings are heterogeneous, and most models require validation in real-world settings. The review concludes that integrating these tools into public security requires attention to data quality and representativeness, interpretability, bias, and privacy, as well as evaluation of their impact on public policies.
References
Bheemalingaiah, M., Nageswara Rao, E., Srirama Kanaka Ratnam, A., & Vecha, S. (2022). Advanced cyber crime rate prediction using deep learning & AI based algorithm. Journal of Harbin Institute of Technology, 54(3), 140–146. https://doi.org/10.11720/JHIT.54032022.17
Burgos Alarcón, S. R. (2025). Análisis predictivo en seguridad pública: Generación de alertas con datos históricos del departamento de Córdoba [Proyecto aplicado, Especialización en Ciencia de Datos y Analítica, Universidad Nacional Abierta y a Distancia]. Repositorio Institucional UNAD. https://repository.unad.edu.co/handle/10596/73242
Calderon-Vilca, H. D., Carhuaricra Rivera, L., Abad Nauto, O., Carrillo Estrada, J., Calderon-Vilca, E. F., & Ibarra, M. (2021, septiembre). Review of crimes in Peru and proposal of a neural network architecture to predict if a person could commit a crime. En Proceedings of the 29th Conference of the Open Innovations Association FRUCT (pp. 416–422). Open Innovations Association FRUCT. https://doi.org/10.5281/zenodo.4770802
Díaz Linares, N. A. (2023). Entorno urbano y delincuencia: Robo de vehículo y calidad de vida urbana en la Ciudad de México, 2018–2020 [Tesis de maestría, Universidad Autónoma del Estado de México].
Egger, J., Pepe, A., Gsaxner, C., Jin, Y., Li, J., & Kern, R. (2021). Deep learning—a first meta-survey of selected reviews across scientific disciplines, their commonalities, challenges and research impact. PeerJ Computer Science, 7, e773. https://doi.org/10.7717/peerj-cs.773
Giraldo-Alegría, S., Ordoñez-Palacios, L., Bucheli-Guerrero, V., & Ordoñez-Erazo, H. (2020). Modelo de redes neuronales para predecir la tendencia de víctimas de secuestro en Colombia. Investigación e Innovación en Ingenierías, 8(3), 38–49. https://doi.org/10.17081/invinno.8.3.4702
Gupta, M. K., & Chandra, P. (2020). A comprehensive survey of data mining. International Journal of Information Technology, 12, 1243–1257. https://doi.org/10.1007/s41870-020-00427-7
Iberdrola. (2023). Aplicaciones del deep learning. https://www.iberdrola.com/conocenos/nuestro-modelo-innovacion/deep-learning
Khan, M., Ali, A., & Alharbi, Y. (2022). Predicting and preventing crime: A crime prediction model using San Francisco crime data by classification techniques. Complexity, 2022, Article 4830411. https://doi.org/10.1155/2022/4830411
Kim, K.-S., & Jeong, Y.-H. (2021). A study on crime prediction to reduce crime rate based on artificial intelligence. Korean Journal of Artificial Intelligence, 9(1), 15–20. https://doi.org/10.24225/kjai.2021.9.1.15
Lira Cortés, A. L., & Fuentes Silva, C. (2021). Artificial intelligence models for crime prediction in urban spaces. Machine Learning and Applications: An International Journal, 8(1), 1–15. https://doi.org/10.5121/mlaij.2021.8101
Martínez, J. (2020). Deep learning: Fundamentos y aplicaciones.
Navarro Espindola, J. (2024). Análisis espacio-temporal de actividades delictivas en Morelia con un enfoque de aprendizaje automático no supervisado [Tesis de licenciatura, Universidad Nacional Autónoma de México]. Repositorio Institucional de la UNAM. https://repositorio.unam.mx/contenidos/3713132
Ordóñez, H., Cobos, C., & Bucheli, V. (2020). Modelo de machine learning para la predicción de las tendencias de hurto en Colombia. Revista Ibérica de Sistemas e Tecnologias de Informação, (E29), 494–506.
Pacheco Olivo, R. V., Vallejo Villavicencio, V. G., Enríquez Gutiérrez, D. A., Rojas Cevallos, A. V., & Bonilla Peñaherrera, J. O. (2025). Diseño de un modelo de aprendizaje automático para videovigilancia inteligente para la detección automática de armas de fuego enfocado a restaurantes ubicados en el cantón Quito. Ciencia Latina Revista Científica Multidisciplinar, 9(5), 11182–11205. https://doi.org/10.37811/cl_rcm.v9i5.20463
Raghu, M., & Schmidt, E. (2020). A survey of deep learning for scientific discovery [Preprint]. arXiv. https://arxiv.org/abs/2003.11755
Reier Forradellas, R. F., Náñez Alonso, S. L., Jorge-Vázquez, J., & Rodríguez, M. L. (2021). Applied machine learning in social sciences: Neural networks and crime prediction. Social Sciences, 10(1), Article 4. https://doi.org/10.3390/socsci10010004
Safat, W., Asghar, S., & Gillani, S. A. (2021). Empirical analysis for crime prediction and forecasting using machine learning and deep learning techniques. IEEE Access, 9, 70080–70094. https://doi.org/10.1109/ACCESS.2021.3078117
Villavicencio Benalcázar, W. A. (2023). Estudio de técnicas de aprendizaje automático utilizadas en ciberseguridad [Tesis de maestría, Universidad Politécnica Salesiana]. Repositorio Institucional de la Universidad Politécnica Salesiana. https://dspace.ups.edu.ec/bitstream/123456789/26498/1/UPS-CT011003.pdf

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright (c) 2026 Omar Manzano Silva
