Arquitetura de Tempo Real e Modelo de Aprendizado de Máquina para Detecção de Fraudes de Cartão de Crédito

• Robson S. Santos UFC
• Robesvânia Araújo UFC
• Paulo A. L. Rego UFC
• José M. da S. M. Filho UFC
• Jarélio G. da S. Filho Sidi
• José D. C. Neto Sidi
• Nicksson C. A. de Freitas Sidi
• Emanuel B. Rodrigues UFC

DOI: https://doi.org/10.5753/sbseg.2023.233688

Resumo

Diante da necessidade crescente de sistemas seguros e eficientes para detectar fraudes em transações de cartões de crédito em tempo real, este estudo propõe e avalia uma abordagem de detecção de fraude baseada em aprendizado de máquina, integrada a uma arquitetura em tempo real de um banco virtual. A arquitetura multicamadas utilizada permite uma clara divisão de responsabilidades, resultando em operações otimizadas e eficientes. Com o uso do modelo de aprendizado de máquina Random Forest, o sistema é capaz de fazer previsões precisas sobre possíveis transações fraudulentas. Essa implementação fornece resultados robustos e confiáveis, com acurácia de 99,98%, precisão de 99,97%, revocação de 100% e F1-score de 99,88%, destacando o potencial do aprendizado de máquina para melhorar significativamente a eficácia da detecção de fraudes.

Referências

ABAKARIM, Y.; LAHBY, M.; ATTIOUI, A. An efficient real time model for credit card fraud detection based on deep learning. In: Proceedings of the 12th international conference on intelligent systems: theories and applications. [S.l.: s.n.], 2018. p. 1–7.

BAKHTIARI, S.; NASIRI, Z.; VAHIDI, J. Credit card fraud detection using ensemble data mining methods. Multimedia Tools and Applications, Springer, p. 1–19, 2023.

CARCILLO, F. et al. Scarff: a scalable framework for streaming credit card fraud detection with spark. Information fusion, Elsevier, v. 41, p. 182–194, 2018.

CHEN, Y.; HAN, X. Catboost for fraud detection in financial transactions. In: IEEE. 2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE). [S.l.], 2021. p. 176–179.

CHERIF, A. et al. Credit card fraud detection in the era of disruptive technologies: A systematic review. Journal of King Saud University-Computer and Information Sciences, Elsevier, 2022.

DENG, W. et al. A data mining based system for transaction fraud detection. In: IEEE. 2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE). [S.l.], 2021. p. 542–545.

KEWEI, X. et al. A hybrid deep learning model for online fraud detection. In: IEEE. 2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE). [S.l.], 2021. p. 431–434.

MEGARGEL, A.; POSKITT, C. M.; SHANKARARAMAN, V. Microservices orchestration vs. choreography: A decision framework. In: IEEE. 2021 IEEE 25th International Enterprise Distributed Object Computing Conference (EDOC). [S.l.], 2021. p. 134–141.

MENSHCHIKOV, A. et al. Comparative analysis of machine learning methods application for financial fraud detection. In: IEEE. 2022 32nd Conference of Open Innovations Association (FRUCT). [S.l.], 2022. p. 178–186.

NGUYEN, N. et al. A proposed model for card fraud detection based on catboost and deep neural network. IEEE Access, IEEE, v. 10, p. 96852–96861, 2022.

NI, L. et al. Fraud feature boosting mechanism and spiral oversampling balancing technique for credit card fraud detection. IEEE Transactions on Computational Social Systems, IEEE, 2023.

PRUSTI, D.; DAS, D.; RATH, S. K. Credit card fraud detection technique by applying graph database model. Arabian Journal for Science and Engineering, Springer, v. 46, n. 9, p. 1–20, 2021.

SAPOZHNIKOVA, M. et al. Anti-fraud system on the basis of data mining technologies. In: IEEE. 2017 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT). [S.l.], 2017. p. 243–248.

THENNAKOON, A. et al. Real-time credit card fraud detection using machine learning. In: IEEE. 2019 9th International Conference on Cloud Computing, Data Science & Engineering (Confluence). [S.l.], 2019. p. 488–493.