Your credit card been declined at checkout? Credit card fraud detection systems mistakenly decline billions in store sales, an especially frustrating problem during holiday shopping days. According to the following article, the credit card networks are among companies turning to tech solutions to improve the approve/decline process for in-store payment transactions.
It’s an experience many shoppers have had: You’re queued in line at the store prepared to make a purchase only to have your credit card declined for no apparent reason. A perfectly legitimate charge has been flagged as fraudulent, and the result is an agitated customer and a retailer with unsold merchandise. MasterCard has now turned to artificial intelligence to better differentiate between real and mistaken fraud, hoping to tamp down on the former while allowing the latter to go through. It’s the latest financial services company to see the potential for the burgeoning field of machine learning to improve security on its network and enhance the customer experience.
Financial institutions have for years collected data on customers’ habits and routines, and used the information to pinpoint cards that may have been compromised. That’s the reason your card may be declined if you make an unusually large purchase, shop at a store for the first time, or buy gas in a place far from home. The system is essentially deciding whether that behavior seems normal according to predetermined questions, then accepting or declining the purchase based on its decision.
Machine learning can help fraud-detection systems become smarter about what fraud actually looks like, both across the network and on an individual level. For example, the system might detect that you haven’t shopped at a particular merchant in the past, but still accept the purchase because customers with a similar spending history shop there often. Or perhaps you travel to a certain state or country often enough that the system learns purchases there are likely to be legitimate.
The tech solutions now being used for in-store transaction approval are standard operating procedure for e-commerce merchants. An emerging industry of fraud management tech vendors have developed highly sophisticated, machine learning systems to pass judgement on online sales. Machine learning fraud detection for e-commerce is highly successful. Watch for these solutions to become more widely used at checkout counters, and save merchants from incorrectly declining legitimate sales.
Overview by Raymond Pucci, Associate Director, Research Service at Mercator Advisory Group
Read the full story here