Aplicação de Técnicas de Inteligência Computacional para Detecção de Fraude em Comércio Eletrônico
Resumo
O volume de transações eletrônicas cresceu significativamente nos últimos anos, devido principalmente à popularização dos serviços de comercio eletrônico. Com essa popularização aumentou consideravelmente os casos de fraudes, resultando assim em um prejuízo de bilhões de dólares em todo o mundo. Assim, é necessário prover mecanismos capazes de auxiliar na detecção de fraude, foco principal deste projeto de pesquisa. Este trabalho de iniciação científica visa a modelagem e aplicação de técnicas de inteligência computacional para detectar fraudes em transações eletrônicas, mais especificamente em operações envolvendo cartão de crédito, utilizando as técnicas de Regressão Logística e Redes Bayesianas. Para avaliar a eficácia das técnicas, definimos o conceito de Eficiência Econômica e o aplicamos a um cenário real do serviço de pagamento eletrônico mais popular do Brasil. Nossos resultados apresentaram bom desempenho para detecção de fraude, com um ganho de 35,61% em relação ao cenário real da empresa.Referências
Amiratti, S. (2007). Google’s udi manbersearch is a hard problem. In ReadWriteWeb Blog.
Barse, E. L., Kvarnström, H., and Jonsson, E. (2003). Synthesizing test data for fraud detection systems. In Proceedings of the 19th Annual Computer Security Applications Conference, ACSAC ’03, pages 384–, Washington, DC, USA. IEEE Computer Society.
Bolton, R. J. and Hand, D. J. (2002). Unsupervised Profiling Methods for Fraud Detection. Statistical Science, 17(3):235–255.
Casella, G. and Berger, R. (2002). Statistical Inference. Pacific Grove, 2nd edition.
Chen, C., Liaw, A., and Breiman, L. (2004). Using random forest to learn imbalanced data. Discovery, (1999):1–12.
Cooper, G. and Herskovits, E. (1992). A bayesian method for the induction of probabilistic networks from data. Machine Learning, 9(4):309–347.
Fawcett, T. and Provost, F. (1997). Adaptive fraud detection. data mining and knowledge discovery.
Hosmer, D. W. (2000). Applied Logistic Regression. Wiley, New York, 2nd edition.
J. Hendler, N. Shadbolt, W. H. T. B.-L. and Weitzner, D. (2008). Web science: an interdisciplinary approach to understanding the web. Communications of the ACM, 51:60–69.
Lima, R. and Pereira, A. (2011). Applying logistic regression to rank credibility in web applications. In 7th Intl Conference on Web Information Systems and Technologies.
Lundin, E., Kvarnström, H., and Jonsson, E. (2002). A synthetic fraud data generation methodology. In Proceedings of the 4th International Conference on Information and Communications Security, ICICS ’02, pages 265–277, London, UK. Springer-Verlag.
Maes, S., karl Tuyls, Vanschoenwinkel, B., and Manderick, B. (2001). Credit card fraud detection using bayesian and neural networks. Vrije Universiteir Brussel.
Maes, S., Tuyls, K., Vanschoenwinkel, B., and Manderick, B. (1993). Credit card fraud detection using bayesian and neural networks. In Maciunas RJ, editor. Interactive image-guided neurosurgery. American Assoc. Neurological Surgeons, pages 261–270.
Maranzato, R., Pereira, A., Neubert, M., and do Lago, A. P. (2010). Fraud detection in reputation systems in e-markets using logistic regression and stepwise optimization. SIGAPP Appl. Comput. Rev., 11:14–26.
Netmap (2004). Fraud and crime example brochure.
Phua, C., Lee, V., Smith-Miles, K., and Gayler, R. (2005). A comprehensive survey of data mining-based fraud detection research.
Team, R. (2009). R: A language and environment for statistical computing. [link]. The R Development Core Team.
Tseng, S. and Fogg, B. J. (1999). Credibility and computing technology. ACM?42, 429:39–44.
Venables, W. N., Smith, D. M., and the R Development Core Team (2009). An introduction to r. [link].
Version, T. R. D. C. T. (2006). The r project for statistical computing. [link].
Witten, I. H. and Franku, E. (2005). Data Mining: Practical Machine Learning Tools and Techniques. Elsevier.
Barse, E. L., Kvarnström, H., and Jonsson, E. (2003). Synthesizing test data for fraud detection systems. In Proceedings of the 19th Annual Computer Security Applications Conference, ACSAC ’03, pages 384–, Washington, DC, USA. IEEE Computer Society.
Bolton, R. J. and Hand, D. J. (2002). Unsupervised Profiling Methods for Fraud Detection. Statistical Science, 17(3):235–255.
Casella, G. and Berger, R. (2002). Statistical Inference. Pacific Grove, 2nd edition.
Chen, C., Liaw, A., and Breiman, L. (2004). Using random forest to learn imbalanced data. Discovery, (1999):1–12.
Cooper, G. and Herskovits, E. (1992). A bayesian method for the induction of probabilistic networks from data. Machine Learning, 9(4):309–347.
Fawcett, T. and Provost, F. (1997). Adaptive fraud detection. data mining and knowledge discovery.
Hosmer, D. W. (2000). Applied Logistic Regression. Wiley, New York, 2nd edition.
J. Hendler, N. Shadbolt, W. H. T. B.-L. and Weitzner, D. (2008). Web science: an interdisciplinary approach to understanding the web. Communications of the ACM, 51:60–69.
Lima, R. and Pereira, A. (2011). Applying logistic regression to rank credibility in web applications. In 7th Intl Conference on Web Information Systems and Technologies.
Lundin, E., Kvarnström, H., and Jonsson, E. (2002). A synthetic fraud data generation methodology. In Proceedings of the 4th International Conference on Information and Communications Security, ICICS ’02, pages 265–277, London, UK. Springer-Verlag.
Maes, S., karl Tuyls, Vanschoenwinkel, B., and Manderick, B. (2001). Credit card fraud detection using bayesian and neural networks. Vrije Universiteir Brussel.
Maes, S., Tuyls, K., Vanschoenwinkel, B., and Manderick, B. (1993). Credit card fraud detection using bayesian and neural networks. In Maciunas RJ, editor. Interactive image-guided neurosurgery. American Assoc. Neurological Surgeons, pages 261–270.
Maranzato, R., Pereira, A., Neubert, M., and do Lago, A. P. (2010). Fraud detection in reputation systems in e-markets using logistic regression and stepwise optimization. SIGAPP Appl. Comput. Rev., 11:14–26.
Netmap (2004). Fraud and crime example brochure.
Phua, C., Lee, V., Smith-Miles, K., and Gayler, R. (2005). A comprehensive survey of data mining-based fraud detection research.
Team, R. (2009). R: A language and environment for statistical computing. [link]. The R Development Core Team.
Tseng, S. and Fogg, B. J. (1999). Credibility and computing technology. ACM?42, 429:39–44.
Venables, W. N., Smith, D. M., and the R Development Core Team (2009). An introduction to r. [link].
Version, T. R. D. C. T. (2006). The r project for statistical computing. [link].
Witten, I. H. and Franku, E. (2005). Data Mining: Practical Machine Learning Tools and Techniques. Elsevier.
Publicado
16/07/2012
Como Citar
LIMA, Rafael A. F.; PEREIRA, Adriano C. M..
Aplicação de Técnicas de Inteligência Computacional para Detecção de Fraude em Comércio Eletrônico. In: CONCURSO DE TRABALHOS DE INICIAÇÃO CIENTÍFICA DA SBC (CTIC-SBC), 31. , 2012, Curitiba/PR.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2012
.
p. 11-20.
