Crime and economic factors in Medellín
a predictive study using machine learning

DOI:  https://doi.org/10.12804/revistas.urosario.edu.co/economia/a.14992

Article Sidebar

PDF (Español (España)) HTML (Español (España)) XML (Español (España))

Published: Nov 11, 2025
Issue: Vol. 27 No. 2 (2024):
Section Articles


Keywords: Machine learning crime patterns classification models crime prediction public policies

Main Article Content

Authors

  Maria Camila Ardila
Magíster en Economía de la Universidad del Rosario

Abstract

Criminal activity hurts the quality of life and economic progress. With advancements in financial research and the use of machine learning to detect patterns, these techniques are now employed in various fields, including crime prevention. This study aims to predict the likelihood of different types of crimes in Medellín, Colombia, based on historical and sociodemographic data. Ordinary Least Squares, Random Forest, and Extreme Gradient Boosting models were used, achieving high accuracy. Key predictors include the proportion of men, people aged 16 to 30, unemployment rates, sisben membership, multidimensional poverty, housing deficits, and socioeconomic strata 1 and 2.

How to Cite
Ardila, M. C. (2025). Crime and economic factors in Medellín: a predictive study using machine learning. Revista Economía Del Rosario, 27(2). https://doi.org/10.12804/revistas.urosario.edu.co/economia/a.14992
References

AL Mansour, H., & Lundy, M. (2019). Crime types prediction. En A. Alfaries, H. Mengash, A. Yasar, & E. Shakshuki (Eds.), Advances in Data Science, Cyber Security and IT Applications: First International Conference on Computing, icc 2019, Riyadh, Saudi Arabia, December 10–12, 2019, Proceedings (Part I, pp. 260-274). Springer. DOI: https://doi.org/10.1007/978-3-030-36365-9_22

Alcaldía de Medellín. (s. f. a). Sistema de Información para la Seguridad y la Convivencia (SISC). https://www.medellin.gov.co/es/secretaria-seguridad/sisc/

Alcaldía de Medellín. (s. f. b.). Encuesta Calidad de Vida. https://www.medellin.gov.co/es/centro-documental/encuesta-calidad-de-vida/

Alcaldía de Medellín. (s. f. c.). Límite Catastral de Comunas y Corregimientos. https://www.medellin.gov.co/geomedellin/datosAbiertos/1043

Alves, L. G., Ribeiro, H. V., & Rodrigues, F. A. (2018, septiembre). Crime prediction through urban metrics and statistical learning. Physica A: Statistical Mechanics and its Applications, 505, 435-443. https://doi.org/10.1016/j.physa.2018.03.084 DOI: https://doi.org/10.1016/j.physa.2018.03.084

Andini, M., Ciani, E., de Blasio, G., D’Ignazio, A., & Salvestrini, V. (2018, diciembre). Targeting with machine learning: An application to a tax rebate program in Italy. Journal of Economic Behavior & Organization, 156, 86-102. https://doi.org/10.1016/j.jebo.2018.09.010 DOI: https://doi.org/10.1016/j.jebo.2018.09.010

Bazzi, S., Blair, R. A., Blattman, C., Dube, O., Gudgeon, M., & Peck, R. (2022). The promise and pitfalls of conflict prediction: evidence from Colombia and Indonesia. Review of Economics and Statistics, 104(4), 764-779. https://doi.org/10.1162/rest_a_01016 DOI: https://doi.org/10.1162/rest_a_01016

Becker, G. S. (1968, marzo-abril). Crime and punishment: An economic approach. Journal of Political Economy, 76(2), 169-217. https://www.jstor.org/stable/1830482 DOI: https://doi.org/10.1086/259394

Blattman, C., Duncan, G., Lessing, B., Tobón, S., & Mesa-Mejía, J. P. (2020). Gobierno criminal en Medellín: panorama general del fenómeno y evidencia empírica sobre cómo enfrentarlo [Nota Política CIEF N.01]. Universidad EAFIT. https://hdl.handle.net/10784/24352

Bogomolov, A., Lepri, B., Staiano, J., Oliver, N., Pianesi, F., & Pentland, A. (2014, 12-16 de noviembre). Once upon a crime: towards crime prediction from demographics and mobile data. 16th International Conference on Multimodal Interaction (pp. 427-434). Special Interest Group on Computer-Human Interaction (SIGCHI), Istanbul Turkey. https://doi.org/10.1145/2663204.2663254 DOI: https://doi.org/10.1145/2663204.2663254

Braga, A. A., Papachristos, A. V., & Hureau, D. M. (2014). The effects of hot spots policing on crime: An updated systematic review and metaanalysis. Justice Quarterly, 31(4), 633-663. https://doi.org/10.1080/07418825.2012.673632 DOI: https://doi.org/10.1080/07418825.2012.673632

Browning, C. R., Byron, R. A., Calder, C. A., Krivo, L. J., Kwan, M.-P., Lee, J.-Y., & Peterson, R. D. (2010). Commercial density, residential concentration, and crime: Land use patterns and violence in neighborhood context. Journal of Research in Crime and Delinquency, 47(3), 329-357. https://doi.org/10.1177/0022427810365906 DOI: https://doi.org/10.1177/0022427810365906

Collazos, D., García, E., Mejía, D., Ortega, D., & Tobón, S. (2021). Hot spots policing in a high-crime environment: An experimental evaluation in Medellín. Journal of Experimental Criminology, 17(3), 473-506. https://doi.org/10.1007/s11292-019-09390-1 DOI: https://doi.org/10.1007/s11292-019-09390-1

Cornish, D. B., & Clarke, R. V. (1989). Crime specialisation, crime displacement and rational choice theory. En H. Wegener, F. Lösel, & J. Haisch (Eds.), Criminal Behavior and the Justice System. Psychological Perspectives (pp. 103-117). Springer. DOI: https://doi.org/10.1007/978-3-642-86017-1_7

Cornish, D. B., & Clarke, R. V. (2016). The rational choice perspective. En R. Wortley, & M. Townsley (Eds.), Environmental Criminology and Crime Analysis (pp. 48-80). Routledge.

De Blasio, G., D’Ignazio, A., & Letta, M. (2022, noviembre). Gotham city. predicting ‘corrupted’ municipalities with machine learning. Technological Forecasting and Social Change, 184. https://doi.org/10.1016/j.techfore.2022.122016 DOI: https://doi.org/10.1016/j.techfore.2022.122016

Deng, Y., He, R., & Liu, Y. (2023, octubre). Crime risk prediction incorporating geographical spatiotemporal dependency into machine

learning models. Information Sciences, 646. https://doi.org/10.1016/j.ins.2023.119414 DOI: https://doi.org/10.1016/j.ins.2023.119414

Departamento Administrativo Nacional de Estadística. (s. f.). Descarga de datos geoestadísticos. https://www.dane.gov.co/files/geoportal-provisional/index.html

Detotto, C., & Otranto, E. (2010, agosto). Does crime affect economic growth? Kyklos, 63(3), 330-345. https://doi.org/10.1111/j.1467-6435.2010.00477.x DOI: https://doi.org/10.1111/j.1467-6435.2010.00477.x

Duarte-Velásquez, Y. A., & Cadavid-Carmona, J. A. (2020, mayo-agosto). Análisis de umbral: técnica diferencial en la interpretación de los registros de criminalidad en Colombia (2019). Revista Criminalidad, 62(2), 9-31. http://www.scielo.org.co/pdf/crim/v62n2/1794-3108-crim-62-02-9.pdf

Falade, A., Azeta, A., Oni, A., & Odun-ayo, I. (2019, septiembre). Systematic literature review of crime prediction and data mining. Review of Computer Engineering Studies, 6(3), 56-63. https://doi.org/10.18280/RCES.060302 DOI: https://doi.org/10.18280/rces.060302

Ferro Briceño, P. V. (2021). Uso de redes neuronales para determinar la influencia del estado del pavimento en siniestros viales de la ciudad de Bogotá [Tesis de maestría, Universidad de Los Andes]. https://repositorio.uniandes.edu.co/server/api/core/bitstreams/1e7ef712-dfaa-42d0-bf90-fe652361aa33/contentGallego, J., Prem, M., & Vargas, J. F. (2022). Predicting politicians’ misconduct: Evidence from Colombia. Data & Policy, 4. https://doi.org/10.1017/dap.2022.35 DOI: https://doi.org/10.1017/dap.2022.35

García, H. I., Giraldo, C. A., López, M. V., Pastor, M. d. P., Cardona, M., Tapias, C. E., Cuartas, D., Gómez, V., & Vera, C. Y. (2012). Treinta años de homicidios en Medellín, Colombia, 1979-2008. Cadernos de Saúde Pública, 28(9), 1699-1712. https://doi.org/10.1590/S0102-311X2012000900009 DOI: https://doi.org/10.1590/S0102-311X2012000900009

Gelvez-Ferreira, J.-D., Nieto-Rodríguez, M.-P., & Rocha-Ruiz, C.-A. (2022). Prediciendo el crimen en ciudades intermedias: un modelo de “machine learning” en Bucaramanga, Colombia. URVIO Revista Latinoamericana de Estudios de Seguridad, (34), 82-98. https://doi.org/10.17141/urvio.34.2022.5395 DOI: https://doi.org/10.17141/urvio.34.2022.5395

Gerber, M. S. (2014, mayo). Predicting crime using twitter and kernel density estimation. Decision Support Systems, 61, 115-125. https://doi.org/10.1016/j.dss.2014.02.003 DOI: https://doi.org/10.1016/j.dss.2014.02.003

Giraldo Alegría, S. A., Ordoñez Palacios, L. E., 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 DOI: https://doi.org/10.17081/invinno.8.3.4702

Giraldo Ramírez, J. (2008). Conflicto armado urbano y violencia homicida. el caso de Medellín. URVIO Revista Latinoamericana de Estudios de Seguridad, (5), 99-113. https://doi.org/10.17141/urvio.5.2008.1098 DOI: https://doi.org/10.17141/urvio.5.2008.1098

Goin, D. E., Rudolph, K. E., & Ahern, J. (2018, mayo). Predictors of firearm violence in urban communities: a machine-learning approach. Health & Place, 51, 61-67. https://doi.org/10.1016/j.healthplace.2018.02.013 DOI: https://doi.org/10.1016/j.healthplace.2018.02.013

Gordon, M. B. (2010). A random walk in the literature on criminality: A partial and critical view on some statistical analyses and modelling approaches. European Journal of Applied Mathematics, 21(4-5), 283-306. https://doi.org/10.1017/S0956792510000069 DOI: https://doi.org/10.1017/S0956792510000069

He, L., Páez, A., & Liu, D. (2017, enero). Persistence of crime hot spots: an ordered probit analysis. Geographical analysis, 49(1), 3-22. https://doi.org/10.1111/gean.12107 DOI: https://doi.org/10.1111/gean.12107

Hino, K., & Amemiya, M. (2019, julio). Spatiotemporal analysis of burglary in multifamily housing in Fukuoka City, Japan. Cities, 90, 15-23. https://doi.org/10.1016/j.cities.2019.01.030 DOI: https://doi.org/10.1016/j.cities.2019.01.030

Ingilevich, V., & Ivanov, S. (2018). Crime rate prediction in the urban environment using social factors. Procedia Computer Science, 136, 472-478.https://doi.org/10.1016/j.procs.2018.08.261 DOI: https://doi.org/10.1016/j.procs.2018.08.261

Kajita, M., & Kajita, S. (2020, abril-junio). Crime prediction by data-driven green’s function method. International Journal of Forecasting, 36(2), 480-488. https://doi.org/10.1016/j.ijforecast.2019.06.005 DOI: https://doi.org/10.1016/j.ijforecast.2019.06.005

Khanna, G., Medina, C., Nyshadham, A., Ramos, D., Tamayo, J., & Tiew, A. (2022). Spatial mobility, economic opportunity, and crime [Harvard Business School Working Paper, No. 24-016]. https://www.hbs.edu/ris/Publication%20Files/24-016_eb4b5875-f71d-428b-b7bc-071b7872c0f8.pdf

Kounadi, O., Ristea, A., Araujo, A., & Leitner, M. (2020). A systematic review on spatial crime forecasting. Crime Science, 9(7), 1-22. https://doi.org/10.1186/s40163-020-00116-7 DOI: https://doi.org/10.1186/s40163-020-00116-7

Kshatri, S. S., & Narain, B. (2020). Analytical study of some selected classification algorithms and crime prediction. International Journal of Engineering and Advanced Technology (IJEAT), 9(6), 241-247. https://doi.org/10.35940/ijeat.F1370.089620 DOI: https://doi.org/10.35940/ijeat.F1370.089620

Levine, N. (2008). The “hottest” part of a hotspot: comments on “the utility of hotspot mapping for predicting spatial patterns of crime”. Security Journal, 21(4), 295-302. https://link.springer.com/article/10.1057/sj.2008.5#citeas DOI: https://doi.org/10.1057/sj.2008.5

Liang, W., Wang, Y., Tao, H., & Cao, J. (2022). Towards hour-level crime prediction: A neural attentive framework with spatial-temporal-categorical fusion. Neurocomputing, 486, 286-297. https://doi.org/10.1016/j.neucom.2021.11.052 DOI: https://doi.org/10.1016/j.neucom.2021.11.052

Lim, N. (2007). Classification by ensembles from random partitions using logistic regression models [Tesis doctoral, Stony Brook University]. SBU Academic Commons. https://commons.library.stonybrook.edu/stony-brooktheses-and-dissertations-collection/1423

Lima, M. S. M., & Delen, D. (2020, enero). Predicting and explaining corruption across countries: A machine learning approach. Government Information Quarterly, 37(1). https://doi.org/10.1016/j.giq.2019.101407 DOI: https://doi.org/10.1016/j.giq.2019.101407

Lin, Y.-L., Yen, M.-F., & Yu, L.-C. (2018). Grid-based crime prediction using geographical features. ISPRS International Journal of Geo-Information, 7(8). https://doi.org/10.3390/ijgi7080298 DOI: https://doi.org/10.3390/ijgi7080298

Lu, R., & Li, L. (2019). Crime prediction model based on Random Forest. Journal of China Interpol Academy, 5(3), 108-112.

Maloof, M. A. (2003). Learning when data sets are imbalanced and when costs are unequal and unknown. Workshop on Learning from Imbalanced Data Sets II, icml. https://www.site.uottawa.ca/~nat/Workshop2003/maloof-icml03-wids.pdf

Martin, G. (2012). Medellín, tragedia y resurrección: mafias, ciudad y Estado, 1975- 2013. Planeta.

Mejía, D., Ortega, D., & Ortiz, K. (2015). Un análisis de la criminalidad urbana en Colombia [Documento de trabajo N.o 2015/06]. Banco de desarrollo de América Latina, CAF. https://scioteca.caf.com/handle/123456789/810

Merton, R. K. (1938, octubre). Social structure and anomie. American sociological review, 3(5), 672-682. https://www.jstor.org/stable/2084686 DOI: https://doi.org/10.2307/2084686

Mittal, M., Goyal, L. M., Sethi, J. K., & Hemanth, D. J. (2019). Monitoring the impact of economic crisis on crime in India using machine learning. Computational Economics, 53, 1467-1485. https://doi.org/10.1007/s10614-018-9821-x DOI: https://doi.org/10.1007/s10614-018-9821-x

Mojica-Muñoz, K. S. (2021). Inteligencia artificial para detectar corrupción en la administración pública municipal de Colombia [Documentos CEDE # 31]. Universidad de los Andes. https://doi.org/10.57784/1992/50541

Muñoz, V., Vallejo, M., & Aedo, J. E. (2021, 25-27 de agosto). Exploratory analysis of crime behavior in the city of Medellín. 2nd Sustainable Cities Latin America Conference (SCLA) (pp. 1-5). IEEE. https://doi.org/10.1109/SCLA53004.2021.9540095 DOI: https://doi.org/10.1109/SCLA53004.2021.9540095

Mustard, D. B. (2010). How do labor markets affect crime? New evidence on an old puzzle. En B. L. Benson, & P. R. Zimmerman (Eds.), Handbook on the economics of crime (pp. 342-358). Edward Elgar Publishing DOI: https://doi.org/10.2139/ssrn.1584187

Okonkwo, R. O., & Enem, F. O. (2011, 25-29 de julio). Combating crime and terrorism using data mining techniques. 10th International Conference. Nigeria Computer Society (NCS). https://www.ncs.org.ng/wp-content/uploads/2011/08/ITePED2011-Paper10.pdf

Ordoñez-Eraso, H.-A., Pardo-Calvache, C.-J., & Cobos-Lozada, C.-A. (2020). Detection of homicide trends in Colombia using machine learning. Revista Facultad de Ingeniería, 29(54). https://dialnet.unirioja.es/servlet/articulo?codigo=7712425 DOI: https://doi.org/10.19053/01211129.v29.n54.2020.11740

Raza, D. M., & Victor, D. B. (2021, 25-27 de marzo). Data mining and region prediction based on crime using Random Forest. 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS) (pp. 980-987). IEEE. https://ieeexplore.ieee.org/document/9395989 DOI: https://doi.org/10.1109/ICAIS50930.2021.9395989

Reier-Forradellas, R. F., Náñez Alonso, S. L., Jorge-Vazquez, J., & Rodriguez, M. L. (2020). Applied machine learning in social sciences: Neural Networks and crime prediction. Social Sciences, 10(1). https://doi.org/10.3390/socsci10010004 DOI: https://doi.org/10.3390/socsci10010004

Rojas-Guerrero, M., & Grautoff Laverde, M. (2022). Predicción de las masacres en Colombia empleando inteligencia artificial [Tesis de maestría en Economía Aplicada, Universidad de Los Andes]. https://repositorio.uniandes.edu.co/server/api/core/bitstreams/1726f23e-cd47-4bbc-a4de182f44eb4ae3/content

Rosser, G., Davies, T., Bowers, K. J., Johnson, S. D., & Cheng, T. (2017). Predictive crime mapping: Arbitrary grids or street networks? Journal of Quantitative Criminology, 33, 569-594. https://doi.org/10.1007/s10940-016-9321-x DOI: https://doi.org/10.1007/s10940-016-9321-x

Rumi, S. K., Deng, K., & Salim, F. D. (2018). Crime event prediction with dynamic features. epj Data Science, 7(1). https://doi.org/10.1140/epjds/s13688-018-0171-7 DOI: https://doi.org/10.1140/epjds/s13688-018-0171-7

Sánchez-Jabba, A. (2013, enero-junio). La reinvención de Medellín. Lecturas de Economía, (78), 185-227. https://doi.org/10.17533/udea.le.n78a15768 DOI: https://doi.org/10.17533/udea.le.n78a15768

Sánchez-Torres, F. J., & Núñez-Méndez, J. A. (2001). Determinantes del crimen violento en un país altamente violento: el caso de Colombia. [Documentos CEDE 2001-02]. Coyuntura Económica, 31(1). https://www.repository.fedesarrollo.org.co/handle/11445/2098?show=full

Shaw, C. R., & McKay, H. D. (1931). Report on the causes of crime. United States Government Printing Office.

Stalidis, P., Semertzidis, T., & Daras, P. (2021). Examining deep learning architectures for crime classification and prediction. Forecasting, 3(4), 741-762. https://doi.org/10.3390/forecast3040046 DOI: https://doi.org/10.3390/forecast3040046

Sun, Y., Chen, T., & Yin, H. (2023). Spatial-temporal meta-path guided explainable crime prediction. World Wide Web Internet and Web Information Systems, 26, 2237-2263. https://doi.org/10.1007/s11280-023-01137-3 DOI: https://doi.org/10.1007/s11280-023-01137-3

Thuraisingham, B. (2004). Data mining for counter-terrorism. En H. Kargupta, A. Joshi, K. Sivakumar, & Y. Yesha (Eds.), Data Mining: Next Generation Challenges and Future Directions (pp. 157-183). AAAI Press.

Tobler, W. R. (1979). Cellular geography. En S. Gale., & G. Olsson (Eds.), Philosophy in Geography. Theory and Decision Library [Series Theory and Decision Library] (pp. 379-386). Springer. DOI: https://doi.org/10.1007/978-94-009-9394-5_18

Varian, H. R. (2014, primavera). Big data: New tricks for econometrics. Journal of Economic Perspectives, 28(2), 3-28. http://dx.doi.org/10.1257/jep.28.2.3 DOI: https://doi.org/10.1257/jep.28.2.3

Wang, S., Cao, J., & Yu, P. S. (2020). Deep learning for spatio-temporal data mining: A survey. IEEE Transactions on Knowledge and Data Engineering, 34(8), 3681-3700. https://doi.org/10.1109/tkde.2020.3025580 DOI: https://doi.org/10.1109/TKDE.2020.3025580

Weisburd, D., & Green, L. (1995). Policing drug hot spots: The Jersey City drug market analysis experiment. Justice Quarterly, 12(4), 711-735. https://doi.org/10.1080/07418829500096261 DOI: https://doi.org/10.1080/07418829500096261

Weisburd, D., Maher, L., Sherman, L., Buerger, M., Cohn, E., & Petrosino, A. (2023). Contrasting crime general and crime specific theory: The case of hot spots of crime. En F. A. William, & S. Laufer (Eds.), New Directions in Criminological Theory (Cap. 3, pp. 45-70). Routledge. DOI: https://doi.org/10.4324/9781003421139-3

Wheeler, A. P., & Steenbeek, W. (2021). Mapping the risk terrain for crime using machine learning. Journal of Quantitative Criminology, 37, 445-480. https://doi.org/10.1007/s10940-020-09457-7 DOI: https://doi.org/10.1007/s10940-020-09457-7

Yao, S., Wei, M., Yan, L., Wang, C., Dong, X., Liu, F., & Xiong, Y. (2020, 18-22 de agosto). Prediction of crime hotspots based on spatial factors of Random Forest. 15th International Conference on Computer Science & Education (ICCSE) (pp. 811-815). IEEE. https://ieeexplore.ieee.org/document/9201899 DOI: https://doi.org/10.1109/ICCSE49874.2020.9201899

Yi, F., Yu, Z., Zhuang, F., Zhang, X., & Xiong, H. (2018, 17-20 de noviembre). An integrated model for crime prediction using temporal and spatial factors. International Conference on Data Mining (ICDM) (pp. 1386-1391). IEEE. https://ieeexplore.ieee.org/document/8594999 DOI: https://doi.org/10.1109/ICDM.2018.00190

Zaidi, N. A. S., Mustapha, A., Mostafa, S. A., & Razali, M. N. (2020). A classification approach for crime prediction. En M. I. Khalaf, D. Al-Jumeily, & A. Lisitsa (Eds.), Applied Computing to Support Industry: Innovation and Technology (pp. 68-78) [First International Conference, ACRIT 2019, Ramadi, Iraq, September 15–16, 2019, Revised Selected Papers]. Springer; ACRIT 2019. https://doi.org/10.1007/978-3-030-38752-5_6

Zhang, X., Liu, L., Lan, M., Song, G., Xiao, L., & Chen, J. (2022, enero). Interpretable machine learning models for crime prediction. Computers, Environment and Urban Systems, 94. https://doi.org/10.1016/j.compenvurbsys.2022.101789 DOI: https://doi.org/10.1016/j.compenvurbsys.2022.101789

Zhao, X., & Tang, J. (2017, 06-10 noviembre). Modeling temporal-spatial correlations for crime prediction. CIKM ‘17: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management (pp. 497-506). Special Interest Group on Hypertext, Hypermedia and Web (SIGWEB); Special Interest Group on Information Retrieval (SIGIR), Singapur. https://dl.acm.org/doi/pdf/10.1145/3132847.3133024 DOI: https://doi.org/10.1145/3132847.3133024

Zou, K. H., Tuncali, K., & Silverman, S. G. (2003). Correlation and simple linear regression. Radiology, 227(3), 617-628. https://doi.org/10.1148/radiol.2273011499 DOI: https://doi.org/10.1148/radiol.2273011499

Query Statistics

Downloads

Download data is not yet available.
Publcation metrics

0




 

Creative Commons License

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

Los autores conservan los derechos de autor y garantizan a la revista el derecho de ser la primera publicación del trabajo al igual que licenciado bajo una Creative Commons Attribution License que permite a otros compartir el trabajo con un reconocimiento de la autoría del trabajo y la publicación inicial en esta revista.