Despite the Hype, Machine Learning, Models, Behavioral Profiling and the Customer Experience are Still Fundamental
Think about the last time you got a fraud decline. Where were you? In the grocery store? Buying airline tickets? On holiday? Shopping in the same place you’ve been a dozen times, but across the border? How frustrating was that, what did it do to your perspective, your mood, your confidence in your financial institution? This can be embarrassing and inconvenient, stressful and alarming for the consumer. There are few things that can be more disruptive in our day-to-day lives then the lack of access to your funds, or the care taken by your financial institution after a fraud occurs. According to ACI’s Global Consumer Fraud Survey, 20% of people may decide this is too much and move along to another financial institution.
How can we harness payments data and manipulate it to determine if a transaction is legitimate (or more accurately, if it is not) and reduce customer churn? Here’s a guide to some of the advanced analytics that can underpin a successful approach to fraud detection. This should allow you to start separating the hype around artificial intelligence, from the machine learning, neural and regression models and the rule-based logic we have all come to embrace in the practice of making sausage in a fraud shop.
The role of behavioral profiling and adaptive machine learning
Enter behavioral profiling, the capacity for one’s own behavior to influence fraud detection strategy. The merchants we typically visit, the fuel pumps where we get gas, common travel destinations, these are all a part of the behavioral profiling technology that we’ve been using for years. Questions arise… How often do we buy from retailers that sell women’s ready-to-wear clothes? What’s the potential that someone will spend their holiday in Belize? Is this an unusual amount that someone is taking out at this ATM and is it the first time they are using this specific terminal on the other side of town? The technology to evaluate these scenarios has been around for a while, it’s mature and widely accepted as the “table stakes” feature functionality to reduce risk of fraud and maintain a good customer experience.
Behavioral profiling is also useful in models, whether it be a regression model (expanding on the example above at the ATM), neural scoring models, or going down the rule-based machine learning path. Adaptive machine learning will typically leverage multiple data sources, using up-to-date variables to provide the greatest possible timeliness in both legitimate and fraud transactions. This integration of many data points and risk indicators may include; recent fraud trends, legitimate spending patterns including non-monetary transaction elements like the addition of beneficiaries or changes to demographics, end-point device intelligence, resident malware indicators, authentication results and third-party or internal scoring models.
So, while all these elements are assembled together into a larger complex regression model, there is one additional element that can be integrated into the model that enhances it with statistical properties; the risk-weighting of the various signals and data elements inside of the regression model. This allows for the model to accurately assign an optimized predictive capability to these data elements, which will then accurately calculate the relative risk of the data element. This process produces reliable and repeatable decisioning logic, identifies insights into the legitimacy of the transaction and provides value relative to historical relationships and trends, aligning the model logic to inbound transactions, recognizing patterns and delivering the value of advanced analytics in fraud detection.
But is AI ready for primetime?
Pattern recognition in supervised machine learning (where the machine is provided example inputs, perhaps exemplified in the data elements described above) is not a new science; we’ve been delivering these models for years. What is new is the hype around this process and the introduction of Artificial Intelligence (AI) concepts in the fraud detection space. Here’s the deal with unsupervised AI… it’s not ready for primetime, performing under the legacy supervised machine learning analytics applications that are deployed presently in the smarter financial institutions and processors. It’s simply not fast enough, smart enough or cheap enough to be implemented at scale, so when you hear people say AI and fraud in the same sentence, you might be smelling actual fraud.
AI is suggested, expected and advertised to be the technology holy grail that will reduce human supervision and oversight, minimizing the manual analytical work load and constant strategy maintenance that is the backbone of any fraud analytics team. The end goal of AI is to get the computer to minimize the amount of work from humans and transition it to the machine, ultimately to realize a lift in efficiency and accuracy in fraud detection. The computer can indeed do things faster than humans, but the human will always know better about the reasons behind the signals… and for this reason, while the goal is admirable, its unlikely to be fully realized.
Utilizing the existing supervised machine learning strategies is presently delivering the best probability of aligning the stars of a high detection rate AND a positive customer experience. This is again, table stakes for financial institutions as the culture of fraud detection moves further toward the best customer experience metrics. Because I shouldn’t get a decline when I am going back to Arizona for Christmas again or having my favorite meal at that one Poutinerie in Montreal with the best smoked meats. But if you’re my bank and you fail to detect more than a transaction in a country I’ve never been to, I’ll be upset over it.
Do you want to learn how to leverage machine learning in your payments fraud prevention strategy? Learn from ACI experts in our webinar on Machine Learning for Fraud Prevention.
Every new payment type brings new fraud challenges – download our whitepaper 'The Fraud Trap: Optimizing Digital Payment Controls from Day One' [PDF] to find out more.
Related Blog Posts
No Margin for Error: Acquirers Must Now Master the Art of Reinvention [Q&A]
The digital transformation of banking and growing competition within the industry is rapidly changing the world of global acquirers. Long gone are the days when an acquirer’s primary role was simply to facilitate an acceptance ecosystem for credit card payments. As part of its new “Prime Time for Real-Time” report, ACI recently published No Margin for Error, an eBook looking at the changes — and challenges — facing acquirers. I spoke to Ruth Fornell, our executive vice president – consumer payments, about the key insights, why acquirers are being forced to rethink their business models and what the future may hold.
Digital Payments: A Creature Comfort in the Era of COVID-19
Humans have an impressive ability to adapt – and have quickly done so in terms of their spending behaviors and choice of payment methods in response to the COVID-19 pandemic. Lockdowns forced many to consider cash alternatives to make payments, driving a huge surge in demand for digital payment services. And in some European countries, demand has risen as much as 81 percent.
Why Human Nature Presents a Challenge for Acquirers
It’s one of the great paradoxes of human behavior: people are predictably unpredictable. We work in irrational ways, hearts win out over heads and the unexpected can rapidly become the norm. Try as we might, predicting the emergence of any new trend is difficult – particularly in unpredictable times – and this is just as true in the world of payments as it is elsewhere.
How ISO 20022 Represents Both a Challenge and an Opportunity for Southeast Asia’s Payments Landscape
Governments across Southeast Asia (SEA) are increasingly recognizing the vital role that payments play in the engines of their economies, which has resulted in a number of payments modernization initiatives such as those in Vietnam and Malaysia (PayNet). Yet there is one particular area in which SEA’s financial institutions might still be lagging behind their global counterparts: the adoption of ISO 20022, which has become the global standard for high-value payments and immediate payments (IP) when it comes to cross-border payments.
Ready or Not, The Time Is Now for Real-Time Payments
Research from ACI and GlobalData confirms that demand for real-time payments is only going in one direction: up. The root cause of this increasing demand is rising customer expectations and behaviors; clunky and opaque payment experiences are becoming less tolerable in a world where customers can buy, watch and listen to almost anything with a swipe, tap or click.
When It Comes to Payments, COVID-19 Crisis Could Lead to Long-Term Shifts in Consumer Behavior [Q&A]
ACI Worldwide and GlobalData recently launched Prime Time for Real-Time, a new global report tracking and analyzing real-time payments volumes, growth and dynamics across 30 global markets. According to the global research, an industry first, more than half a trillion real-time payments transactions will be processed over the next five years. I discussed what the findings mean, and how the COVID-19 pandemic might be a further catalyst for behavioral change, with ACI’s global head of real-time payments, Craig Ramsey.
TCH RTP and FedNow: What’s Next for U.S. Immediate Payments?
It has taken some time, but immediate payments (IP) are on the move in the United States. Although the speed of adoption has been slightly behind the curve of regions like India, the Nordics and the U.K., the U.S. has seen significant year-on-year IP growth of 69 percent.
Social, Mobile and Instant Payments: How Digital Payment Overlay Services Will Power Up P27
For some years now, the Nordics region has been a global-standard bearer for payments and financial services innovation. Sweden has for many years been a leader in the progressive move towards cashlessness, championing the range of efficiencies that it brings. Major payments innovators like Klarna, FundedByMe and iZettle are based in the region, rubber-stamping Stockholm as a genuine fintech hub. Analysts and insight leaders also regularly single the Nordics out as a genuine leader, in particular praising the collaboration between governments, regulators, financial institutions and businesses that has led to such fertile ground for financial modernization initiatives.
How to Meet ISO 20022 Migration Deadlines for Fedwire and SWIFT
Over the next decade, we will undoubtedly see huge shifts in how financial institutions throughout North America transact, whether domestically or across international borders. This will be driven not just by changing technologies, but also by regulatory events – such as the widespread adoption of financial messaging standards like ISO 20022.
How Can European Banks Meet the ISO 20022 Migration Deadlines for TARGET2 and SWIFT?
First published in 2004 – and already broadly used in some quarters – ISO 20022 is rapidly set to become the de facto standard for financial messaging around the world, replacing MT messages.