Abstract
<p>While the flow of banking transactions is increasing, the risk of credit card fraud is becoming greater particularly with the technological revolution that we know, fraudulent are improve and always find new methods to deal with the preventive measures that financial systems set up. Several studies have proposed predictive models for credit card fraud detection based on different machine learning techniques. In this paper, we present an adaptive approach to credit card fraud detection that exploits the performance of the techniques that have given high level of accuracy and consider the type of transaction and the client's profile. Our proposition is a multi-level framework, which encompasses the banking security aspect, the customer profile and the profile of the transaction itself.</p>
Highlights
Customers all over the world, more inclined to abandon the use of cash, and opt for e-wallets or credit cards, this for security reasons, resource management and to enjoy the benefits of the online bank services
The aim of this paper is to propose a hybrid model for credit card fraud detection, with three level of security and it is based on profile of customer and transaction
We found that the One-Class Support Vector Machine (OCSVM) method outperform other techniques in all fields of comparison [3] with 96.6% as accuracy and low false alarm rate
Summary
Customers all over the world, more inclined to abandon the use of cash, and opt for e-wallets or credit cards, this for security reasons, resource management and to enjoy the benefits of the online bank services. The Virtual ATM, as proposed lastly [25], a new system is introduced that provides ATM service without traditional booths but two-layer authentications with a tiny OS independent device Another techniques used are the MasterCard Secure Code and Verified by VISA, which adds an additional verification factor for Internet purchases. These programs are effective at prevent only electronic card fraud and are only applied in optimal conditions. The aim of this paper is to propose a hybrid model for credit card fraud detection, with three level of security and it is based on profile of customer and transaction.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
