Title :
Characterizing and preventing chargebacks in next generation web payments services
Author :
Caldeira, Evandro ; Brandao, Gabriel ; Pereira, Adriano C. M.
Author_Institution :
Comput. Dept. (DECOM), Fed. Center for Tech. Educ. of Minas Gerais (CEFET-MG), Belo Horizonte, Brazil
Abstract :
The volume of electronic transactions has raised a lot in last years, mainly due to the popularization of ecommerce, such as online retailers. We also observe a significant increase in the number of fraud cases, resulting in billions of dollars losses each year worldwide. Therefore it is important and necessary to developed and apply techniques that can assist in fraud detection, which motivates our research. This work aims to apply and evaluate some computational intelligence techniques to identify fraud in electronic transactions, more specifically in credit card operations. In order to evaluate the techniques, we define a concept of economic efficiency and apply them in an actual dataset of the most popular Brazilian electronic payment service. Our results show good performance in fraud detection, presenting significant gains in comparison to the actual scenario of the company.
Keywords :
Web services; belief networks; data mining; electronic commerce; financial data processing; fraud; neural nets; regression analysis; retail data processing; security of data; Bayesian networks; Brazilian electronic payment service; chargeback characterization; chargeback prevention; computational intelligence techniques; credit card operations; data mining; e-Business; ecommerce; economic efficiency; electronic transactions; fraud cases; fraud detection; fraud identification; logistic regression; neural networks; next generation Web payments services; online retailers; random forest; Artificial neural networks; Companies; Credit cards; Data mining; Economics; Radio frequency; Support vector machines; Bayesian Networks; Computational Intelligence; Data Mining; Fraud Detection; Logistic Regression; Neural Networks; Random Forest; e-Business;
Conference_Titel :
Computational Aspects of Social Networks (CASoN), 2012 Fourth International Conference on
Conference_Location :
Sao Carlos
Print_ISBN :
978-1-4673-4793-8
DOI :
10.1109/CASoN.2012.6412424
