Fraud management has been known to be a very painful problem for banking and finance firms. Card-related frauds have proven to be especially difficult for firms to combat. Technologies such as chip and PIN are available and are already used by most credit card system vendors, such as Visa and MasterCard. However, the available technology is unable to curtail 100% of credit card fraud. Unfortunately, scammers come up with newer ways of phishing to obtain passwords from credit card users. Also, devices such as skimmers make stealing credit card data a cake walk!
Despite the availability of some technical abilities to combat credit card fraud, The Nilson Report, a leading publication covering payment systems worldwide, estimated that credit card fraud is going to soar to $32 billion in 2020 (https://nilsonreport.com/upload/content_promo/The_Nilson_Report_10-17-2017.pdf). To get a perspective on the estimated loss, it is more than the recent profits posted by companies such as Coca-Cola ($2 billion), Warren Buffet’s Berkshire Hathaway ($24 billion), and JP Morgan Chase ($23.5 billion)!
While credit card chip technology-providing companies have been investing hugely to advance the technology to counter credit card fraud, in this chapter, we are going to examine whether and how far machine learning can help deal with the credit card fraud problem. We will cover the following topics as we progress through this chapter:
- Machine learning in credit card fraud detection
- Autoencoders and the various types
- The credit card fraud dataset
- Building AEs with the H2O library in R
- Implementation of auto encoder for credit card fraud detection