Análise de Risco Criminal em Grafos Viários usando Marcações Territoriais de Facções como Features Preditivas
Resumo
Este trabalho investiga a associação entre pichações de organizações criminosas e padrões espaciais de criminalidade em Teresina-PI. Utilizando dados georreferenciados de pichações das facções PCC, B40 e GDE, registros criminais (2022-2023) e POIs urbanos, desenvolveu-se modelo de classificação de risco em grafos viários. Mediante LightGBM e análise SHAP, demonstrou-se associação robusta entre proximidade a pichações e ocorrência de crimes. Features de territorialização apresentaram ganho substancial em AUPRC sobre modelos baseados apenas em POIs e características viárias, com maior impacto em crimes não-violentos. Esta é a primeira incorporação sistemática de marcações territoriais criminosas em modelos de risco espacial, oferecendo metodologia replicável para análise criminal urbana no Brasil.
Palavras-chave:
Ciência de Dados, Inteligência Artificial, Mineração de Dados
Referências
Bogomolov, A., Lepri, B., Staiano, J., Oliver, N., Pianesi, F., and Pentland, A. (2014). Once upon a crime: Towards crime prediction from demographics and mobile data. In Proc. of the ACM Int. Joint Conference on Pervasive and Ubiquitous Computing.
Brantingham, P. J., Tita, G. E., Short, M. B., and Reid, S. (2012). The ecology of gang territorial boundaries. Criminology, 50(3):851–885.
Brasil (1940). Decreto-lei nº 2.848, de 7 de dezembro de 1940. código penal. [link].
Garcia-Zanabria, G. and Nonato, L. (2022). Visual crime pattern analysis. In Anais Estendidos da SIBGRAPI, Porto Alegre, RS, Brasil. SBC.
García-Zanabria, G., Raimundo, M., Poco, J., Nery, M., Silva, C., Adorno, S., and Nonato, L. (2022). Cripav: Street-level crime patterns analysis and visualization. IEEE Transactions on Visualization and Computer Graphics, 28(12):4000–4015.
Gerber, M. (2014). Predicting crime using twitter and kernel density estimation. Decision Support Systems, 61.
Hassan, W., Cabral, M., Ramos, T., Filho, A. C., and Nonato, L. (2024). Modeling and predicting crimes in the city of são paulo using graph neural networks. In Proc. XXXIV Brazilian Conference on Intelligent Systems (BRACIS), pages 372–386.
Hou, M., Hu, X., Cai, J., Han, X., and Yuan, S. (2022). An integrated graph model for spatial–temporal urban crime prediction based on attention mechanism. ISPRS International Journal of Geo-Information, 11(5):294.
Hughes, L. A., Schaible, L. M., and Kephart, T. (2022). Gang graffiti, group process, and gang violence. Journal of Quantitative Criminology, 38:365–384.
IBGE (2023). Censo demográfico 2022: Primeiros resultados. [link].
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems, pages 3146–3154.
Kronkvist, K., Borg, A., Boldt, M., and Gerell, M. (2025). Predicting public violent crime using register and openstreetmap data: A risk terrain modeling approach across three cities of varying size. Applied Spatial Analysis and Policy, 18(9).
Ley, D. and Cybriwsky, R. (1974). Urban graffiti as territorial markers. Annals of the Association of American Geographers, 64(4):491–505.
Lundberg, S. and Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems 30, pages 4765–4774.
Pocco, X., Hassan, W., Salinas, K., Molchanov, V., and Nonato, L. G. (2025). Exploring urban factors with autoencoders: Relationship between static and dynamic features.
Raimundo, M., Garcia-Zanabria, G., Nonato, L., and Poco, J. (2025). Countercrime using counterfactual explanations to explore crime reduction scenarios. IEEE Transactions on Visualization and Computer Graphics, 31(10):9008–9023.
Salinas, K., Gonçalves, T., Barella, V., Vieira, T., and Nonato, L. (2022). Cityhub: A library for urban data integration. In Anais da Conf. on Graphics, Patterns and Images.
Silva, D., Vieira, T., Costa, E., Paiva, A., and Nonato, L. (2025). A street corner-level methodology to analyze the influence of points of interest on urban crime. SocioEconomic Planning Sciences, 102:102297.
Wang, H., Kifer, D., Graif, C., and Li, Z. (2016). Crime rate inference with big data. In Proc. of the ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining.
Weisburd, D. (2015). The law of crime concentration and the criminology of place. Criminology, 53.
Brantingham, P. J., Tita, G. E., Short, M. B., and Reid, S. (2012). The ecology of gang territorial boundaries. Criminology, 50(3):851–885.
Brasil (1940). Decreto-lei nº 2.848, de 7 de dezembro de 1940. código penal. [link].
Garcia-Zanabria, G. and Nonato, L. (2022). Visual crime pattern analysis. In Anais Estendidos da SIBGRAPI, Porto Alegre, RS, Brasil. SBC.
García-Zanabria, G., Raimundo, M., Poco, J., Nery, M., Silva, C., Adorno, S., and Nonato, L. (2022). Cripav: Street-level crime patterns analysis and visualization. IEEE Transactions on Visualization and Computer Graphics, 28(12):4000–4015.
Gerber, M. (2014). Predicting crime using twitter and kernel density estimation. Decision Support Systems, 61.
Hassan, W., Cabral, M., Ramos, T., Filho, A. C., and Nonato, L. (2024). Modeling and predicting crimes in the city of são paulo using graph neural networks. In Proc. XXXIV Brazilian Conference on Intelligent Systems (BRACIS), pages 372–386.
Hou, M., Hu, X., Cai, J., Han, X., and Yuan, S. (2022). An integrated graph model for spatial–temporal urban crime prediction based on attention mechanism. ISPRS International Journal of Geo-Information, 11(5):294.
Hughes, L. A., Schaible, L. M., and Kephart, T. (2022). Gang graffiti, group process, and gang violence. Journal of Quantitative Criminology, 38:365–384.
IBGE (2023). Censo demográfico 2022: Primeiros resultados. [link].
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems, pages 3146–3154.
Kronkvist, K., Borg, A., Boldt, M., and Gerell, M. (2025). Predicting public violent crime using register and openstreetmap data: A risk terrain modeling approach across three cities of varying size. Applied Spatial Analysis and Policy, 18(9).
Ley, D. and Cybriwsky, R. (1974). Urban graffiti as territorial markers. Annals of the Association of American Geographers, 64(4):491–505.
Lundberg, S. and Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems 30, pages 4765–4774.
Pocco, X., Hassan, W., Salinas, K., Molchanov, V., and Nonato, L. G. (2025). Exploring urban factors with autoencoders: Relationship between static and dynamic features.
Raimundo, M., Garcia-Zanabria, G., Nonato, L., and Poco, J. (2025). Countercrime using counterfactual explanations to explore crime reduction scenarios. IEEE Transactions on Visualization and Computer Graphics, 31(10):9008–9023.
Salinas, K., Gonçalves, T., Barella, V., Vieira, T., and Nonato, L. (2022). Cityhub: A library for urban data integration. In Anais da Conf. on Graphics, Patterns and Images.
Silva, D., Vieira, T., Costa, E., Paiva, A., and Nonato, L. (2025). A street corner-level methodology to analyze the influence of points of interest on urban crime. SocioEconomic Planning Sciences, 102:102297.
Wang, H., Kifer, D., Graif, C., and Li, Z. (2016). Crime rate inference with big data. In Proc. of the ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining.
Weisburd, D. (2015). The law of crime concentration and the criminology of place. Criminology, 53.
Publicado
04/12/2025
Como Citar
DE ARAÚJO, Victor Carvalho Soares; MOURA, Raimundo Santos.
Análise de Risco Criminal em Grafos Viários usando Marcações Territoriais de Facções como Features Preditivas. In: ESCOLA REGIONAL DE COMPUTAÇÃO DO CEARÁ, MARANHÃO E PIAUÍ (ERCEMAPI), 13. , 2025, São Luís/MA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 1-10.
DOI: https://doi.org/10.5753/ercemapi.2025.17487.
