Comparação de Métodos de Otimização de Hiperparâmetros Baseados em Meta-Heurísticas e Estratégias Convencionais para Modelos de Detecção de Fraudes
##plugins.themes.bootstrap3.article.sidebar##
Publicado
Sep 15, 2026
##plugins.themes.bootstrap3.article.main##
Resumen
otimização de hiperparâmetros é importante na detecção de fraudes em cartões de crédito porque é um problema raro, dinâmico e altamente sensível a erros, e pequenos ajustes nos modelos podem gerar grandes diferenças nos resultados. Com isso, a otmização é crucial porque eleva o desempenho, a robustez e a capacidade de capturar padrões raros, evitando tanto perdas financeiras quanto alarmes falsos. Assim, este estudo avalia diferentes estratégias de otimização de hiperparâmetros aplicadas à detecção de fraudes em cartões de crédito, um problema marcado por forte desbalanceamento e elevada complexidade. Técnicas tradicionais são comparadas à otimização bayesiana e a meta-heurísticas bioinspiradas. Para isso, foi utilizado o conjunto de dados Credit Card Fraud Detection e modelos de machine learning. O desempenho foi mensurado por métricas adequadas a eventos raros, como F1-Score, Recall e AUC-ROC, e a significância estatística foi analisada pelo teste de Wilcoxon. A comparação entre métodos revelou diferenças relevantes e padrões que motivam uma análise mais aprofundada apresentada ao longo do estudo.
Descargas
La descarga de datos todavía no está disponible.
##plugins.themes.bootstrap3.article.details##
Cómo citar
Lopes, C., & Fagundes, R. (2026). Comparação de Métodos de Otimização de Hiperparâmetros Baseados em Meta-Heurísticas e Estratégias Convencionais para Modelos de Detecção de Fraudes. Revista De Engenharia E Pesquisa Aplicada, 11(3), 55-64. https://doi.org/10.25286/repa.v11i3.3971
Sección
Edição Especial Ingenia
Citas
CAVALCANTI, A.; BRANDÃO, D.; BEZERRA, E.; COUTINHO, R. Avaliação de Técnicas de Balanceamento de Dados na Detecção de Fraude em Transações Online de Cartão de Crédito. In: SIMPÓSIO BRASILEIRO DE BANCO DE DADOS (SBBD), 39., 2024, Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2024. DOI: 10.5753/sbbd.2024.243462.
[2] LOU, Y.; LIU, J.; SHENG, Y.; WANG, J.; ZHANG, Y.; REN, Y. Addressing Class Imbalance with Probabilistic Graphical Models and Variational Inference. arXiv, [S. l.], 2025. Disponível em: https://doi.org/10.48550/arXiv.2504.05758. Acesso em:20/11/2025.
[3] BTOUSH EAL, et al. A systematic review of literature on credit card cyber fraud detection using machine and deep learning. 2023 doi:10.7717/peerj-cs.1278
[4] PATHAK, A. K. et al. Randomized-Grid Search for Hyperparameter Tuning in Decision Tree Model to Improve Performance of Cardiovascular Disease Classification. S. l., 2024. Disponível em: arxiv:2411.18234
[5] OAKIBA, T.; SANO, S.; YANASE, T.; OHTA, T.; KOYAMA, M. Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA, 2019. 2019. DOI: 10.1145/3292500.3330701.
[6] AYOUB, M. et al. Granular computing framework for credit card fraud detection. Alexandria Engineering Journal, 2025. Disponível em: https://www.sciencedirect.com/science/article/pii/S1110016825001863.
[7] SURE, P.; PANDEY, S.; PARNAMI, T.; SAXENA, A. Feature selection techniques for enhancing credit card fraud detection performance: a hybrid metaheuristic approach using nature-inspired algorithms. IJRASET Journal for Research in Applied Science and Engineering Technology, 2024. DOI: 10.22214/ijraset.2024.58549.
[8] ULB, Machine Learning Group. Credit Card Fraud Detection. Kaggle, 2023. Disponível em: https://www.kaggle.com/datasets/mlg-ulb/creditcardfraud. Acesso em: 14/10/2025
[9] BHATTACHARYA, S. et al. Fraud detection using optimized machine learning tools under imbalanced classes. Engineering Applications of Artificial Intelligence, v. 120, p. 106013, 2023.
[10] SOUZA, A. M.; BORDIN JR., L. Planejamento de Experimentos Aplicado à Detecção de Fraude em Cartão de Crédito Utilizando Aprendizado Supervisionado: Uma Abordagem Metodológica. Revista Brasileira de Computação Aplicada, v. 15, n. 3, 2023.
[11] SANTOS, A. et al. Geração de Dados Sintéticos para Avaliação de Modelos de Classificação e Detecção de Anomalias Voltados à Detecção de Fraude em Cartão de Crédito. Anais do Simpósio Brasileiro em Segurança da Informação e de Sistemas Computacionais (SBSeg), 2024. Sociedade Brasileira de Computação.
[12] CAVALCANTI, M.; BRANDÃO, A.; BEZERRA, E. Avaliação de Estratégias de Balanceamento e Seleção de Atributos com Classificadores em Bases Desbalanceadas. Anais do Simpósio Brasileiro de Banco de Dados (SBBD), 2024. Sociedade Brasileira de Computação.
[13] ALKURDI, M. et al. Credit Card Fraud Detection using Point-Biserial Correlation Feature Selection. Revista Gestão & Tecnologia, v. 24, n. 2, 2024.
[14] ALZAHRANI, A. et al. Meta-Heuristic Optimization for Feature Selection in Credit Card Fraud Detection Using Random Forest and SVM. Mathematics, v. 12, n. 14, 2250, 2024. MDPI. DOI: 10.3390/math12142250.
[15] MARAZQAH BTOUSH, EYAD ABEL LATIF et al. A systematic review of literature on credit card cyber fraud detection using machine and deep learning. PeerJ. Computer science vol. 9 e1278. 17 Apr. 2023, doi:10.7717/peerj-cs.1278
[16] SHIMAOKA, A. M.; FERREIRA, R. C.; GOLDMAN, A. The evolution of CRISP-DM for Data Science: Methods, Processes and Frameworks. SBC Computing Reviews, v. 4, n. 1, p. 28–43, 2024. DOI: https://doi.org/10.5753/reviews.2024.3757.
[17] WILCOX, R. R. Winsorize. Encyclopedia of Research Design, 2024.
[18] ZHANG, Y. et al. Hybrid feature selection framework for enhanced credit card fraud detection. PLOS ONE, 2024.
[19] HAWKINS, D. Outlier Impact and Accommodation Methods: Multiple Comparisons. Wayne State University, 2024.
[20] AMORIM, L. B. V. et al. The choice of scaling technique matters for classification performance. Applied Soft Computing, v. 133, p. 109924, jan. 2023. Sociedade Brasileira de Computação.
[21] HAMPEL, F. R. et al. Robust Statistics: The Approach Based on Influence Functions. John Wiley & Sons, 1986.
[22] HOSMER, D.; LEMESHOW, S.; STURDIVANT, R. Applied Logistic Regression. Wiley, 2013.
[23] BREIMAN, L. Random Forests. Machine Learning, 2001. Springer.
[24] CHEN, T.; GUESTRIN, C. XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2016. ACM.
[25] KE, G.; MENG, Q.; FINLEY, T.; WANG, T.; CHEN, W.; MA, W.; YE, Q.; LIU, T. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. Proceedings of the 30th Conference on Neural Information Processing Systems (NeurIPS), 2017. MIT Press.
[26] BERGSTRA, J.; BENGIO, Y. Random Search for Hyper-Parameter Optimization. Journal of Machine Learning Research (JMLR), 2012. Microtome Publishing.
[27] ZHANG, L. et al. Improved LightGBM for extremely imbalanced data and application to credit card fraud detection. Expert Systems with Applications, v. 242, p. 122987, 2025.
[28] WANG, Y.; NI, X. S. A XGBoost risk model via feature selection and Bayesian hyper-parameter optimization. arXiv preprint, arXiv:1901.08433, 2019.
[29] ABURBEIAN, A. H.; ASHQAR, H. I. Credit card fraud detection using enhanced Random Forest classifier for imbalanced data. arXiv preprint, arXiv:2303.06514, 2023.
[30] KHEKARE, G.; SUNDA, S.; BOTHRA, Y. A comprehensive performance comparison of traditional and ensemble machine learning models for online fraud detection. arXiv preprint, arXiv:2509.17176, 2025.
[31] MITCHELL, M. An Introduction to Genetic Algorithms. MIT Press, 1998.
[32] MIRJALILI, S.; MIRJALILI, S. M.; LEWIS, A. Grey Wolf Optimizer. Advances in Engineering Software, 2014. Elsevier.
[33] KENNEDY, J.; EBERHART, R. Particle Swarm Optimization. Proceedings of the IEEE International Conference on Neural Networks (ICNN), 1995. IEEE.
[34] AKIBA, T.; SANO, S.; YANASE, T.; OHTA, T.; KOHN, K. Optuna: A Next-Generation Hyperparameter Optimization Framework. Proceedings of the 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2019. ACM.
[35] GARCÍA, V.; SÁEZ, J. A.; HERRERA, F. An Updated Review on Imbalanced Data Learning: Taxonomy, Challenges, and Solutions. ACM Computing Surveys, v. 54, n. 2, p. 1–36, 2021.
[36] SOKOLOVA, M.; LAPLANTE, F. On the Use of ROC Analysis for Binary Classification under Class Imbalance. Information Processing & Management, v. 58, n. 3, p. 102–152, 2021.
[37] KRAWIEC, K. et al. Handling Imbalanced Data in Classification: A Review. Expert Systems with Applications, v. 206, p. 117–240, 2022.
[38] BENAVOLI, A.; CORANI, G.; MANGILI, F. A New Look at Statistical Comparison of Machine Learning Algorithms: Bayesian Perspective. Machine Learning, v. 109, p. 199–223, 2020.
[39] DERRAC, J.; GARCÍA, S.; MOLINA, D.; HERRERA, F. A practical tutorial on the use of nonparametric statistical tests for evaluating machine learning algorithms. Information Sciences, v. 512, p. 248-284, 2020.
[40] GARCÍA, S.; FERNÁNDEZ, A.; LUENGO, J.; HERRERA, F. A tutorial on the use and a
ssessment of statistical tests in machine learning. Journal of Systems and Software, v. 162, p. 110516, 2019.
[41] BRASCHKA, S. Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning. arXiv preprint arXiv:1811.12808, 2020.
[42] ZHANG, Y.; YANG, Q.; LI, X. Cross-validation and statistical testing in machine learning experiments. ACM Computing Surveys, v. 54, n. 6, p. 1-36, 2021.
[43] GARCÍA, V.; SÁNCHEZ, J. S.; MARTÍN-FÉLEZ, R.; MOLLINEDA, R. A. Surrounding neighborhood-based SMOTE for learning from imbalanced data sets. Progress in Artificial Intelligence, Springer, 2012.
[2] LOU, Y.; LIU, J.; SHENG, Y.; WANG, J.; ZHANG, Y.; REN, Y. Addressing Class Imbalance with Probabilistic Graphical Models and Variational Inference. arXiv, [S. l.], 2025. Disponível em: https://doi.org/10.48550/arXiv.2504.05758. Acesso em:20/11/2025.
[3] BTOUSH EAL, et al. A systematic review of literature on credit card cyber fraud detection using machine and deep learning. 2023 doi:10.7717/peerj-cs.1278
[4] PATHAK, A. K. et al. Randomized-Grid Search for Hyperparameter Tuning in Decision Tree Model to Improve Performance of Cardiovascular Disease Classification. S. l., 2024. Disponível em: arxiv:2411.18234
[5] OAKIBA, T.; SANO, S.; YANASE, T.; OHTA, T.; KOYAMA, M. Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA, 2019. 2019. DOI: 10.1145/3292500.3330701.
[6] AYOUB, M. et al. Granular computing framework for credit card fraud detection. Alexandria Engineering Journal, 2025. Disponível em: https://www.sciencedirect.com/science/article/pii/S1110016825001863.
[7] SURE, P.; PANDEY, S.; PARNAMI, T.; SAXENA, A. Feature selection techniques for enhancing credit card fraud detection performance: a hybrid metaheuristic approach using nature-inspired algorithms. IJRASET Journal for Research in Applied Science and Engineering Technology, 2024. DOI: 10.22214/ijraset.2024.58549.
[8] ULB, Machine Learning Group. Credit Card Fraud Detection. Kaggle, 2023. Disponível em: https://www.kaggle.com/datasets/mlg-ulb/creditcardfraud. Acesso em: 14/10/2025
[9] BHATTACHARYA, S. et al. Fraud detection using optimized machine learning tools under imbalanced classes. Engineering Applications of Artificial Intelligence, v. 120, p. 106013, 2023.
[10] SOUZA, A. M.; BORDIN JR., L. Planejamento de Experimentos Aplicado à Detecção de Fraude em Cartão de Crédito Utilizando Aprendizado Supervisionado: Uma Abordagem Metodológica. Revista Brasileira de Computação Aplicada, v. 15, n. 3, 2023.
[11] SANTOS, A. et al. Geração de Dados Sintéticos para Avaliação de Modelos de Classificação e Detecção de Anomalias Voltados à Detecção de Fraude em Cartão de Crédito. Anais do Simpósio Brasileiro em Segurança da Informação e de Sistemas Computacionais (SBSeg), 2024. Sociedade Brasileira de Computação.
[12] CAVALCANTI, M.; BRANDÃO, A.; BEZERRA, E. Avaliação de Estratégias de Balanceamento e Seleção de Atributos com Classificadores em Bases Desbalanceadas. Anais do Simpósio Brasileiro de Banco de Dados (SBBD), 2024. Sociedade Brasileira de Computação.
[13] ALKURDI, M. et al. Credit Card Fraud Detection using Point-Biserial Correlation Feature Selection. Revista Gestão & Tecnologia, v. 24, n. 2, 2024.
[14] ALZAHRANI, A. et al. Meta-Heuristic Optimization for Feature Selection in Credit Card Fraud Detection Using Random Forest and SVM. Mathematics, v. 12, n. 14, 2250, 2024. MDPI. DOI: 10.3390/math12142250.
[15] MARAZQAH BTOUSH, EYAD ABEL LATIF et al. A systematic review of literature on credit card cyber fraud detection using machine and deep learning. PeerJ. Computer science vol. 9 e1278. 17 Apr. 2023, doi:10.7717/peerj-cs.1278
[16] SHIMAOKA, A. M.; FERREIRA, R. C.; GOLDMAN, A. The evolution of CRISP-DM for Data Science: Methods, Processes and Frameworks. SBC Computing Reviews, v. 4, n. 1, p. 28–43, 2024. DOI: https://doi.org/10.5753/reviews.2024.3757.
[17] WILCOX, R. R. Winsorize. Encyclopedia of Research Design, 2024.
[18] ZHANG, Y. et al. Hybrid feature selection framework for enhanced credit card fraud detection. PLOS ONE, 2024.
[19] HAWKINS, D. Outlier Impact and Accommodation Methods: Multiple Comparisons. Wayne State University, 2024.
[20] AMORIM, L. B. V. et al. The choice of scaling technique matters for classification performance. Applied Soft Computing, v. 133, p. 109924, jan. 2023. Sociedade Brasileira de Computação.
[21] HAMPEL, F. R. et al. Robust Statistics: The Approach Based on Influence Functions. John Wiley & Sons, 1986.
[22] HOSMER, D.; LEMESHOW, S.; STURDIVANT, R. Applied Logistic Regression. Wiley, 2013.
[23] BREIMAN, L. Random Forests. Machine Learning, 2001. Springer.
[24] CHEN, T.; GUESTRIN, C. XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2016. ACM.
[25] KE, G.; MENG, Q.; FINLEY, T.; WANG, T.; CHEN, W.; MA, W.; YE, Q.; LIU, T. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. Proceedings of the 30th Conference on Neural Information Processing Systems (NeurIPS), 2017. MIT Press.
[26] BERGSTRA, J.; BENGIO, Y. Random Search for Hyper-Parameter Optimization. Journal of Machine Learning Research (JMLR), 2012. Microtome Publishing.
[27] ZHANG, L. et al. Improved LightGBM for extremely imbalanced data and application to credit card fraud detection. Expert Systems with Applications, v. 242, p. 122987, 2025.
[28] WANG, Y.; NI, X. S. A XGBoost risk model via feature selection and Bayesian hyper-parameter optimization. arXiv preprint, arXiv:1901.08433, 2019.
[29] ABURBEIAN, A. H.; ASHQAR, H. I. Credit card fraud detection using enhanced Random Forest classifier for imbalanced data. arXiv preprint, arXiv:2303.06514, 2023.
[30] KHEKARE, G.; SUNDA, S.; BOTHRA, Y. A comprehensive performance comparison of traditional and ensemble machine learning models for online fraud detection. arXiv preprint, arXiv:2509.17176, 2025.
[31] MITCHELL, M. An Introduction to Genetic Algorithms. MIT Press, 1998.
[32] MIRJALILI, S.; MIRJALILI, S. M.; LEWIS, A. Grey Wolf Optimizer. Advances in Engineering Software, 2014. Elsevier.
[33] KENNEDY, J.; EBERHART, R. Particle Swarm Optimization. Proceedings of the IEEE International Conference on Neural Networks (ICNN), 1995. IEEE.
[34] AKIBA, T.; SANO, S.; YANASE, T.; OHTA, T.; KOHN, K. Optuna: A Next-Generation Hyperparameter Optimization Framework. Proceedings of the 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2019. ACM.
[35] GARCÍA, V.; SÁEZ, J. A.; HERRERA, F. An Updated Review on Imbalanced Data Learning: Taxonomy, Challenges, and Solutions. ACM Computing Surveys, v. 54, n. 2, p. 1–36, 2021.
[36] SOKOLOVA, M.; LAPLANTE, F. On the Use of ROC Analysis for Binary Classification under Class Imbalance. Information Processing & Management, v. 58, n. 3, p. 102–152, 2021.
[37] KRAWIEC, K. et al. Handling Imbalanced Data in Classification: A Review. Expert Systems with Applications, v. 206, p. 117–240, 2022.
[38] BENAVOLI, A.; CORANI, G.; MANGILI, F. A New Look at Statistical Comparison of Machine Learning Algorithms: Bayesian Perspective. Machine Learning, v. 109, p. 199–223, 2020.
[39] DERRAC, J.; GARCÍA, S.; MOLINA, D.; HERRERA, F. A practical tutorial on the use of nonparametric statistical tests for evaluating machine learning algorithms. Information Sciences, v. 512, p. 248-284, 2020.
[40] GARCÍA, S.; FERNÁNDEZ, A.; LUENGO, J.; HERRERA, F. A tutorial on the use and a
ssessment of statistical tests in machine learning. Journal of Systems and Software, v. 162, p. 110516, 2019.
[41] BRASCHKA, S. Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning. arXiv preprint arXiv:1811.12808, 2020.
[42] ZHANG, Y.; YANG, Q.; LI, X. Cross-validation and statistical testing in machine learning experiments. ACM Computing Surveys, v. 54, n. 6, p. 1-36, 2021.
[43] GARCÍA, V.; SÁNCHEZ, J. S.; MARTÍN-FÉLEZ, R.; MOLLINEDA, R. A. Surrounding neighborhood-based SMOTE for learning from imbalanced data sets. Progress in Artificial Intelligence, Springer, 2012.