PEP Scan - A Tool for Assisting in the Identification of Potential Improper Benefits Receipt by PEPs in Brazil
Resumo
Research Context: PEP Scan focuses on the use of technology to combat corruption in Brazil. Its primary objective is the monitoring of Politically Exposed Persons (PEP), aiming to prevent the misuse of public funds and strengthen transparency. Scientific and/or Practical Problem: There is a critical gap in public tools for integrating and analyzing heterogeneous government data. The core challenge lies in adapting data mining techniques to identify fraud, with a specific focus on uncovering complex connections. Proposed Solution and/or Analysis: The proposed solution is PEP Scan, a web-based tool that integrates public data. It employs a Breadth-First Search (BFS) algorithm and Visual Data Mining (VDM) techniques to map suspicious connections, enabling the exploration of patterns through an interactive graph interface. Related IS Theory: Pep Scan aligns with socio-technical IS theory by integrating technical innovations and user-centric needs. Research Method: The methodology involved the development of a prototype that integrated and processed public databases. The research core was the adaptation of the BFS algorithm to map connections. Two kinds of evaluation were performed: an analysis of the architectural quality and another related to usability, employing the heuristics proposed by Jakob Nielsen. Summary of Results: PEP Scan demonstrated its effectiveness by identifying PEPs who received benefits unduly, including over 400 city councilors. The tool also revealed indirect and complex connections, validating its capability to uncover non-trivial patterns. Contributions and Impact to IS area: This research provides a replicable model and a practical tool for combating corruption. The work contributes to the Information Systems field by demonstrating how technical rigor and a focus on usability can promote citizen science and strengthen public transparency.
Referências
Akoglu, L., Tong, H., and Koutra, D. (2015). Graph based anomaly detection and description: a survey. Data mining and knowledge discovery, 29(3):626–688.
Bastian, M., Heymann, S., and Jacomy, M. (2009). Gephi: an open source software for exploring and manipulating networks. In Proceedings of the international AAAI conference on web and social media, volume 3, pages 361–362.
Borgatti, S. P., Mehra, A., Brass, D. J., and Labianca, G. (2009). Network analysis in the social sciences. science, 323(5916):892–895.
Brasil (2017). Resolução nº 29, de 7 de dezembro de 2017. Dispõe sobre os procedimentos a serem observados pela União, pelos Estados, pelo Distrito Federal e pelos Municípios para a identificação, a qualificação e o cadastramento de beneficiários finais de pessoas jurídicas e outras entidades sob sua administração direta e indireta.
Fayyad, U. (1997). Knowledge discovery in databases: An overview. In International Conference on Inductive Logic Programming, pages 1–16. Springer.
Financial Action Task Force (FATF) (2013). Guidance: Politically exposed persons (recommendations 12 and 22). [link]. Accesso em: 30 jun. 2025.
GCU (2023). Pep. Disponível em: [link]. Acesso em: 12 ago. 2023.
Han, J., Pei, J., and Tong, H. (2022). Data mining: concepts and techniques. Morgan kaufmann.
Irio Musskopf (2025). Operação serenata de amor. Disponível em: [link]. Acesso em: 4 fev. 2025.
Keim, D. A. and Kriegel, H.-P. (2002). Visualization techniques for mining large databases: A comparison. IEEE Transactions on knowledge and data engineering, 8(6):923–938.
Kerche, F. and Marona, M. (2022). A política no banco dos réus: a Operação Lava Jato e a erosão da democracia no Brasil. Autêntica Editora.
King, C. and Walker, C. (2016). Dirty assets: Emerging issues in the regulation of criminal and terrorist assets. Routledge.
Newman, M. E. J. (2018). Networks: An Introduction. Oxford University Press.
Nielsen, J. (1994a). Usability engineering. Morgan Kaufmann.
Nielsen, J. (1994b). Usability inspection methods. In Conference companion on Human factors in computing systems, pages 413–414.
Pourhabibi, T., Ong, K.-L., Kam, B. H., and Boo, Y. L. (2020). Fraud detection: A systematic literature review of graph-based anomaly detection approaches. Decision Support Systems, 133:113303.
Sharman, J. C. (2009). Politically exposed persons: from victims to villains to victors. Crime, Law and Social Change, 52(1):67–87.
Transparência Internacional (2024). Índice de percepção da corrupção 2023. [link]. Accesso em: 16 dez. 2024.
von Zitzewitz, A. (2019). Mitigating technical and architectural debt with sonargraph. In 2019 IEEE/ACM International Conference on Technical Debt (TechDebt), pages 66–67. IEEE.
West, D. B. (2001). Introduction to graph theory.
Witten, I. H., Frank, E., Hall, M. A., Pal, C. J., and Data, M. (2005). Practical machine learning tools and techniques. In Data mining, volume 2, pages 403–413. Elsevier Amsterdam, The Netherlands.
