A novel cardholder behavior model for detecting credit card fraud

Since credit card fraud costs the banking sector billions of dollars every year, decreasing the losses incurring from credit card fraud is an important driver for the sector and end-users. Rule-based fraud detection tools have been widely used as a part of credit card systems. Rules of such tools are determined by human fraud experts. However, experts mostly ignore cardholder-specific spending behavior. In this paper, we focus on analyzing the cardholder spending behavior and propose a novel cardholder behavior model for detecting credit card fraud. The model is named Cardholder Behavior Model (CBM).