IBM RegTech Innovations

Removing friction and fraud from P2P payments

Share this post:

With new payment rails often come unpredictable threats, and likewise the need to help customers adopt these products easily. A balance is required between adequate reliability and security without impacting the customer experience. In the emerging world of person-to-person (P2P) payments, establishing a frictionless (and “fraud-less”) experience is even more critical, since a bad experience early in the transaction will lead consumers to the many competitive alternatives in the market.

So, when a leading payment technology solutions provider to the financial industry required a more effective offering to help its customers detect and prevent fraudulent P2P transactions, including the Zelle payment network, it chose the IBM Safer Payments solution.

The cost of convenience

P2P payment services that enable users to, among other things, split the bill for dinner or reimburse a friend for buying tickets by sending funds to another user via the recipient’s email address or mobile phone number, are gaining popularity. 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. How much are these transactions worth? American Banker recently predicted that the total dollar volume is expected to triple by 2021, topping $336 billion.

That speed, ease, and convenience may have also made P2P platforms a target for thieves who have used the fact that the system is open to anyone to rip off unsuspecting victims. Earlier this year, a well-known P2P network in the US made headlines for a spike in these types of incidents, creating the need for a more stringent approach to fraud detection for banks who participate in the network. In another case, mainstream P2P vendor Venmo saw in the first quarter of 2018 a substantial increase in their operating losses specifically due to fraudulent transactions. The PayPal-owned P2P service took a $40 million loss, an increase of 40% greater than had budgeted, because of fraud.

While all financial systems are susceptible to varying degrees of fraud, aspects of P2P’s design, like not always notifying customers when money is transferred, have contributed to the system’s vulnerability. Therefore, financial institutions participating in these networks need their enterprise fraud solutions to be even more effective as ever before to identify and prevent suspicious activity as quickly as possible. This top payment technology solution provider initially tried commonly-used, channel-specific, out-of-the-box “productized statistical models.” These models are based on the (disproven) assumption that a model or rule labeled for a payment channel is superior to the ability to build an optimized, custom, machine-learning model for that channel. A similar analogy would be to assume that an off-the-rack department store suit fits better than one tailored just for you, which of course, defies logic. The ineffectiveness of the more “generic” model approach for P2P payments was exacerbated due to the novelty of this payment channel and its wide variety of governing business rules and customer behavioral patterns.

Fraud prevention: The first line of defense

After unsuccessful attempts using a leading fraud prevention vendor’s generic model approach, this payments technology solution provider abandoned it and decided to take a fundamentally different approach. Using IBM Safer Payments’ mechanism for creating custom models tailored to the institution’s data, rather than a model build on an average of the financial industry, proved to be much more effective at detecting fraudulent activities. IBM Safer Payments’ advanced capabilities such as artificial intelligence (AI) and machine learning mean the solution learns as it goes, augmenting monetary and non-monetary data to discover new patterns and applying that learning to future transactions. This makes it more accurate is its ability to perform rigorous authentication and profiling on each and every transaction. With this additional context, fraudulent or highly suspicious transactions are quickly identified – allowing them to be stopped or put on hold pending further validation.

Within weeks, this leading payment technology solution provider implemented IBM Safer Payments as part of its portfolio of both transaction processing and fraud protection services, helping its financial institution customers achieve significant reductions in fraud and false positives across their P2P network. More importantly, this successful outcome was achieved without compromising on the essential P2P “frictionless payments experience” of their end-user institutions.

Investing in security a necessity

The key takeaway of this story is, whether supporting the rollout of a new channel or the managing the changing needs of existing channels, financial institutions and payment providers of all kinds must adapt quickly or risk suffering unacceptable losses in terms of both fraud and consumer confidence. The pace of payment innovation and emerging fraud threats has moved beyond the one-size-fits-all approach, and if you don’t move fast enough to meet them, consumers’ preferences surely will.

WW Sales Leader, IBM Safer Payments, Watson Financial Services

More IBM RegTech Innovations stories

The challenge of managing hundreds of daily GRC alerts

Today we are inundated with alerts, breaking news, celebrity scandals and what their neighbor had for lunch.  The feeds are not limited to one medium; your computer, your television, your phone, your tablet and now even the watch you wear on your wrist. The flood of data that comes in can bury a person. How […]

Continue reading

GRC is everyone’s business

In my May 2019 blog, “Has GRC Reached Its Tipping Point? Observations From The Front Lines”, I described a set of common patterns that are driving business initiatives in Governance, Risk & Compliance. These highlighted that: Organizations are transforming their GRC frameworks, They are driving to realize greater benefits from already significant GRC investments, and […]

Continue reading

Ask the expert: 20 questions fraud fighters want to know

In our webinar yesterday, the first in the series AI Fraud Detection — Beyond the Textbooks, we ran out of time and weren’t able to address some great questions we had from the audience. Instead of waiting until the next episode, I hope these brief answers will be of help and interest to both those […]

Continue reading