Putting Speed Bumps In The Path Of Real-Time Payments Fraud

No one ever said that developing real-time payments would be easy. While more businesses are realizing the need for the velocity and data that comes with real-time payments, they’re also realizing that it’s challenging to safeguard such systems. “These struggles are leading many to examine cutting-edge tools that can help them better protect these transactions from fraud,” according to PYMNTS January 2021 Real-Time Payments Tracker® done in collaboration with The Clearing House.

Faster payments, it might be said, lead to faster fraud. It’s an issue that’s high on the agenda at enterprise financial crime management platform Featurespace. In an interview with PYMNTS, Dena Hamilton, senior vice president of global product management, said financial institutions (FIs) must confront the instant and irreversible nature of real-time payments — and new fraud prevention challenges.

“With the introduction of faster payments, we’ve seen an abbreviated window in which customers are able to dispute or retract a payment,” she said. That makes proactive monitoring and detection for fraud and financial crime — rather than a reactive approach — critical.

As has been the case with wire transfer fraud, noted Hamilton, these fraud attempts — when successful — result in large thefts, as measured in dollars. And the reputational damage to those firms can be significant, too.

“For our counterparts in the U.K. and across Europe as well, what we’ve seen with the faster payments initiative is that it’s reduced the recourse window as a financial institution from days to two hours,” Hamilton said. “So what that means to us here in the United States, as we move to real-time payments, is that we need to look at how we’re going to address the shorter timeframe in which we can actually identify those items that may be potentially fraudulent or suspect.”

To put it bluntly, fraud detection needs to get faster, too. In anti-money laundering (AML) efforts, she said, traditional programs often run in a batch environment. That means FIs usually wait until the end of the day, the end of the week or even the end of the month to examine transactions and pinpoint suspect activity — with a historical “look back” all the way to a consumer’s point of onboarding.

As real-time payments take root, firms can add a line of defense by understanding the nuances of what “good” consumer behavior looks like. Hamilton pointed to Featurespace’s development and debut of Adaptive Behavioral Analytics, which integrates into FIs’ AML transaction monitoring programs that teach machines to understand, in real time, how consumers are conducting themselves.

Reducing False Positives 

“You are able to stop those ‘known‘ fraud types, as well as the new ones that are emerging,” she said. “It allows you to stop more fraud and it allows you to reduce friction by allowing more genuine transactions to come through.” She pointed, too, to Featurespace’s Automated Deep Behavioral Networks, which further reduces points of friction.

“We have been able to utilize our knowledge and experience and deploy our software and our machine learning to understand the good behavior of the customer so that the bad behavior ‘rises’ more rapidly to us,” Hamilton said.

In the end, FIs’ fraud prevention teams can do their jobs with greater effectiveness and efficiency. Hamilton said “dynamic, peer profiling” through Adaptive Behavioral Analytics can uncover how individuals interact with peers, or groups of peers, which allows FIs to move beyond the traditional approach of segmenting products and consumers. FIs gain insight into how consumers’ behaviors change as they move through their financial lives.

When peer profiling, Adaptive Behavioral Analytics and advanced technologies are all working in tandem, she told PYMNTS, “it delivers the pinnacle performance that exceeds all standards in the fraud prevention and detection space.”