Share this post:
With new payments products surfacing regularly, unpredictable threats also continue to increase with these new platforms and services. Balancing the need for adequate antifraud measures without impacting the customer experience has never been more important. In the emerging world of real-time person-to-person (P2P) payments, establishing a frictionless (and “fraudless”) experience is even more critical since a bad experience early on will lead consumers to the many competitive alternatives in the market, or scare them away from P2P payments entirely.
P2P payments go mainstream
When Fidelity National Information Services (FIS), one of the world’s leading payment technology providers, required an effective offering to help its customers detect and prevent fraudulent P2P transactions in real time it chose IBM Safer Payments.
Real-time P2P payment services enable users to, among other things, split the bill for dinner, or reimburse a friend for buying tickets, by sending cash to another user via the recipient’s email address or mobile phone number. P2P payments’ popularity continues to grow exponentially where nearly 60% of people in the U.S. use these services, including 80% of young adults ages 18 to 34 according to Mercator Advisory Group. The total dollar volume is expected to triple by 2021, topping $336 billion, according to the American Banker.
Faster payments mean faster response to fraud
Real-time P2P fraud solutions need to be even more effective to identify and prevent suspicious activity as quickly as possible.
Norm Marraccini, FIS General Manager, explains:
“There’s nothing inherently unique about P2P fraud. But the funds move faster than other channels, so bad actors are content with lower dollar amounts. Up against this challenge – in which a fraudulent transaction can hide in plain sight – along with the pressing needs for real-time decisioning and increased flexibility for our team, we’ve found IBM Safer Payments has exceeded our expectations.”
New payment threats require new solutions
FIS initially tried an approach that many financial institutions take to address their fraud issues today; using industry-standard, channel-specific, out-of-the-box “productized statistical models.” These models are based on the assumption that a generic model or rule was originally designed for a certain payment channel is superior to an optimized, custom, machine-learning model tailored to a specific institution. A similar analogy would be to assume that an off-the-rack department store suit fits better than one tailored just for you.
The ineffectiveness of the more “generic” model approach for P2P payments was likely exacerbated due to the novelty of this payment channel and its wide variety of governing business rules and customer behavioral patterns or more simply, no accurate model could anticipate the unique needs of a channel with no transaction history within that institution. After unsuccessful attempts with a leading fraud prevention vendor, FIS decided to take a fundamentally different approach. Using IBM Safer Payments to create custom models tailored to the institution’s data proved to be much more effective at detecting fraudulent activities than a model built on an average of the financial industry. FIS implemented the IBM Safer Payments solution within weeks allowing its customers to achieve significant reductions in fraud and false positives across their P2P network. More importantly, this was achieved without compromising on the unique P2P “frictionless transactions experience” of their end user institutions.
Taking a data science approach to payment fraud
IBM Safer Payments’ advanced capabilities such as artificial intelligence and machine learning mean it can continuously improve detection over time. It can augmenting monetary and nonmonetary data to discover new patterns, while applying that learning to future transactions making it more accurate is its ability to perform rigorous authentication and profiling on each and every transaction. Furthermore, IBM Safer Payments delivers the highspeed processing capabilities and required response time to adequately protect against fraud in the real-time P2P channel, enabled by an ultra-efficient architecture and a purpose-built, in-memory NoSQL database.
To see how other institutions achieved success with IBM Safer Payments, check out our customer testimonial videos here.