PREDICTIVE MODELING FOR THE DETECTION OF ANOMALIES IN PUBLIC CONTRACTS
DOI:
https://doi.org/10.56238/revgeov16n5-072Keywords:
Data Mining, Public Contracts, Anomaly Detection, Explainable AI (XAI), BlockchainAbstract
Public procurement represents one of the most significant areas of government expenditure and, consequently, one of the most vulnerable to inefficiencies and irregularities. This study proposes and validates a predictive data-science framework designed to detect anomalies in public contracts, specifically focusing on the probability of financial amendments (aditivos) as indicators of potential deviations. The research follows an end-to-end methodological structure, encompassing data acquisition from open-government sources, preprocessing, feature engineering, and the implementation of a Gradient Boosting Machine (GBM) model optimized for highly imbalanced datasets. Empirical validation revealed strong performance, with the model achieving a recall rate of 0.85, emphasizing sensitivity over precision to minimize the non-detection of real irregularities. Beyond technical development, the study also discusses the necessity of Explainable Artificial Intelligence (XAI) for algorithmic transparency and explores the Blockchain technology as a potential foundation for next-generation auditing ecosystems. Ultimately, the paper contributes a reproducible roadmap for algorithmic governance, strengthening proactive oversight mechanisms and supporting data-driven decision-making in the public sector.
Downloads
References
Abidi, W. U. H., et al. (2021). Real-time shill bidding fraud detection empowered with fused machine learning. IEEE Access, 9, 113612–113621.
Abreu, B. M. de, Pereira, T. H. S., & Gomes-Jr, L. (2024). Detecção de fraudes em licitações públicas: Uma comparação de modelos de detecção de anomalias. In Anais da XIX Escola Regional de Banco de Dados (ERBD) (pp. 81–90). Farroupilha, RS, Brazil. https://doi.org/10.5753/erbd.2024.238821
Agostino, D., et al. (2022). Data science in promoting the participation of SMEs in public biddings. ResearchGate Preprint. https://www.researchgate.net/publication/385421403
Aldana, A., Falcón-Cortés, A., & Larralde, H. (2022). A machine learning model to identify corruption in Mexico’s public procurement contracts. arXiv preprint, arXiv:2211.01478.
Alghamdi, R., & Khan, F. (2023). Blockchain as a driver for transformations in the public sector. Information Polity, 28(1), 1–20.
Araújo, V. S., Freitas, M. G., & Martin, M. V. A. (2021). Blockchain e o futuro dos contratos administrativos. Revista Quaestio Iuris, 14(1), 481–503. https://doi.org/10.12957/rqi.2021.48956
Bryson, J. J., & Winfield, A. F. T. (2017). Standardizing ethical design for artificial intelligence and autonomous systems. Computer, 50(5), 116–119. https://doi.org/10.1109/MC.2017.154
Carvalho, G. G. de A., & Cunha, M. A. R. de A. (2020). Potenciais aplicações e consequências do uso da blockchain para a administração pública. Revista de Administração Contemporânea, 24(2), 164–178.
Carvalho, S. S. T. (2021). Impacto da inteligência artificial na atividade de auditoria. Cadernos de Finanças Públicas, 21, 1–25.
Dantas, F. F. C. de A., Cerqueira, A. L. O. de, & Aguiar, R. A. de. (2024). Governança algorítmica e inteligência artificial na auditoria governamental: Desafios e oportunidades do sistema Alice. Repositório Institucional da Enap. https://repositorio.enap.gov.br/handle/1/8764
de Carvalho, G. H. F., et al. (2010). Toxicological effects of ethanolic extract of seed and bark of Persea americana (Lauraceae), on larvae and pupae of Aedes albopictus (Skuse, 1894) (Diptera, Culicidae). Vita et Sanitas, 4(1), 21–33.
de Carvalho, G. H. F., et al. (2011). Atividade inseticida do extrato bruto etanólico de Persea americana (Lauraceae) sobre larvas e pupas de Aedes aegypti (Diptera, Culicidae). Revista de Patologia Tropical/Journal of Tropical Pathology, 40(4), 348–361.
de Carvalho, G. H. F., et al. (2019a). Larvicidal and pupicidal activities of eco-friendly phenolic lipid products from Anacardium occidentale nutshell against arbovirus vectors. Environmental Science and Pollution Research, 26(6), 5514–5523.
de Carvalho, G. H. F., et al. (2019b). Ovicidal and deleterious effects of cashew (Anacardium occidentale) nut shell oil and its fractions on Musca domestica, Chrysomya megacephala, Anticarsia gemmatalis, and Spodoptera frugiperda. Chemistry & Biodiversity, 16(5), e1800468.
de Carvalho, G. H. F., de Medeiros, G. G., & Magalhães, R. de L. B. (2024). Subnotificação de doença de Chagas no Estado do Amapá no período da pandemia de COVID-19. Caderno Pedagógico, 21(9), e7609.
Fernandes, L. S., Silva, J. P. R. da, & Oliveira, L. F. de. (2021). Mineração de dados no Portal da Transparência para análise de licitações. Revista de Sistemas e Computação, 11(2).
Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5), 1189–1232.
Grace, E., et al. (2016). Detecting fraud, corruption, and collusion in international development contracts: The design of a proof-of-concept automated system. In IEEE International Conference on Big Data (pp. 1444–1453). Washington, DC: IEEE.
IBM. (2022). What is feature engineering? IBM Knowledge Center. https://www.ibm.com/think/topics/feature-engineering
Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Proceedings of the 31st International Conference on Neural Information Processing Systems (pp. 4768–4777). Long Beach, CA: NIPS.
Moura, L. M. F., et al. (2020). Blockchain e a perspectiva tecnológica para a administração pública: Uma revisão sistemática. Revista de Administração Contemporânea, 24(3), 259–274.
Nai, R., Al-Boni, M. S., & Bifet, A. (2022). Public procurement fraud detection and artificial intelligence techniques: A literature review. In Workshop on Legal Data Analysis and Mining (LeDAM).
Raji, I. D., et al. (2020). Closing the AI accountability gap: Defining an end-to-end framework for internal algorithmic auditing. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency (FAT) (pp. 33–44). Barcelona, Spain: ACM.
Rodríguez, M. J. G., et al. (2022). Collusion detection in public procurement auctions with machine learning algorithms. Automation in Construction, 133, 104055.
Vieira, A. R. M. (2025). Protótipo de um sistema de geração automatizada de pareceres de auditoria baseado em aprendizado de máquina. Repositório Institucional da UFC. https://repositorio.ufc.br/handle/riufc/82469
Williams, P. (2015). Government data does not mean data governance: Lessons from a public sector audit. Government Information Quarterly, 32(3), 324–331.
