Machine Learning in the detection of e-commerce fraud applied to banking services
Abstract
One of the main risks to which financial institutions are subject are electronic fraud attacks. Billions of dollars in losses are absorbed each year by financial institutions due to fraudulent transactions.
This article presents a model that considers the main challenges to design a fraud detection system: a) highly unbalanced classes, b) stationary distribution of data and c) incorporation of online feedback from fraud investigators on transactions labeled suspicious. The implementation of the model in a test dataset allowed to successfully predicting the majority of cases of fraudulent transactions with a minimum percentage of false negatives.
Downloads
References
Aite. (2014). Financial Institutions, Merchants, and the Race Against Cyberthreats.
Bhattacharyya, S., Jha, S., Tharakunnel, K., & Westland, J. (2011). Data mining for credit card fraud: A comparative study. Decision Support Systems.
Breiman, L. (2001). Universidad de California. Obtenido de Random Forest: https://www.stat.berkeley.edu/~breiman/randomforest2001.pdf
Correa Bahnsen, A., Stojanovic, A., Aouada, D., & Ottersten, B. (2013). Cost sensitive credit card fraud detection using bayes minimum risk. Machine Learning and Applications (ICMLA). 2013 12th International Conference.
Dal Pozzolo, A. (2015). Adaptive Machine Learning for Credit Card Fraud Detection.
Donaldson, S. E., Williams, C. K., & Siegel, S. (2019). Undertanding Security Issues.
Group, A.-P. W. (2019). Phishing Activity Trends Report - 2nd Quarter 2019.
Juszczak, P., Adams, N., Hand, D., Whitrow, C., & Weston, D. (2008). Off-the-peg and bespoke classifiers for fraud detection. En Computational Statistics & Data Analysis - Volume 52 (págs. 4521-4532). Elsevier.
Koshrow-Pour, M. (s.f.). Encyclopedia of Criminal Activities and the Deep Web. IGI Global.
Mendez, J., Fdez-Riverola, F., Díaz, F., & Corchado, J. (2007). Sistemas inteligentes para la detección y filtrado de correo spam: una revisión. Inteligencia Artificial. Revista Iberoamericana.
Merino, M. (01 de 2019). Conceptos de inteligencia artificial: qué es el aprendizaje por refuerzo . Obtenido de https://www.xataka.com/inteligencia-artificial/conceptos-inteligencia-artificial-que-aprendizaje-refuerzo
Mohri, M., Rostamizadeh, A., & Talwalkar, A. (2018). Foundations of machine learning . Second edition. Cambridge, MA : The MIT Press.
Morales, L. (2018). BIGDATA: 5 MÉTODOS PARA DETECTAR POSIBLES FRAUDES. Obtenido de https://www.grupo-novatech.com/bigdata-5-metodos-para-detectar-posibles-fraudes/
Murphy, K. (2012). Machine learning. A probabilistic perspective. London: The MIT Press.
Pathak, N., Pawar, A., & Patil, B. (2015). A Survey on Keylogger: A malicious Attack. International Journal of Advanced Research in Computer Engineering & Technology.
Security Standards Counsil. (2018). Requisitos y procedimientos de evaluación de seguridad. Version 3.2.1. Obtenido de https://es.pcisecuritystandards.org/minisite/env2/
Seguridad en Sistemas y Técnicas de Hacking. (2011). ¿Qué es el Hacking? Obtenido de https://thehackerway.com/about/
Téllez, J. (2004). Derecho Informático. México: McGraw-Hill, 3ra edición.
Viola, P., & Jones, M. (2001). Fast and robust classification using asymmetric adaboost and a detector cascade. Advances in Neural Information Processing System.
Whitrow, C., Hand, D., Juszczak, P., Weston, D., & Adams, M. (2009). Transaction aggregation as a strategy for credit card fraud detection. Data Mining and Knowledge Discovery.
The articles published in the journal Ciencia y Tecnología are the exclusive property of their authors. Their opinions and content belong to their authors, and the Universidad de Palermo declines all responsibility for the rights that may arise from reading and/or interpreting the content of the published articles.
The reproduction, use or exploitation by any third party of the published articles is not authorized. Its use is only authorized for exclusively academic and/or research purposes.
