Rise Of The Machine (Learning) and Fraud Prevention
Machine learning, as a sub-discipline within computer science, is primarily concerned with the discovery of patterns in data through algorithms that can learn from and make predictions on that data. These algorithms operate by building a model based on example inputs, which can then make data-driven predictions or decisions. So what, exactly, does this have to do with beating fraud in the real world?
From big data to actionable insights
Machine learning algorithms can be used to build predictive models, which assess the probability of a transaction being fraudulent. This is achieved by combining historical transaction data from fraudulent activity, together with information from genuine customer transactions, delivering very tangible results in fraud detection.
The ability of machine learning algorithms to extract meaning from complicated data means that they can be used to identify patterns and highlight trends that are simply too complex – or require too much data to be crunched - to be noticed either by human fraud analysts or through other automated techniques. By running specific algorithms, and using them to make automated decisions or generate alerts for suspicious activity, it is possible to save manual review time, reduce the number of false positives, and quickly stop fraud attempts.
Even models need rules
Models learn by example – so the more valuable, complete, and relevant data they are fed and trained on, the more accurate they will be. Access to merchant, payment provider and FI data across sector and geographies helps to enhance and train machine learning models. From the perspective of retail fraud, there are two primary models that need to be considered.
Sector models are developed based on data from multiple merchants within a given sector. Fraudsters operate across retailers and geographies, so a global view helps to ensure higher predictive performance.
Tactical models can be developed for a specific segment, data strata, or merchant. The customized nature of the modelling process means that implementing tactical models comes with a higher cost, but they can enable merchants to achieve higher fraud detection rates at lower false positive rates.
Combining either of these machine learning models with a sophisticated rules engine allows fraud strategies to be fine-tuned to the needs of individual merchants. A rules engine needs to be flexible, so that merchants can quickly adapt to emerging fraud trends, as well as respond to business changes such as entry into new markets or channels. Ideally, this is done in such a way that it is not necessary to ‘retrain’ the machine learning model.
Who’s in the driver’s seat?
The successful use of machine learning within the payments and fraud space requires dedicated data scientists, who can develop the models, and also apply the use of algorithms in detecting fraud. Data scientists, however, cannot develop these capabilities in isolation, and work closely alongside risk analysts and software engineering teams. Most importantly, such cross-functional teams must strive to constantly enhance the relevance and performance of machine learning models, to ensure they remain effective as the payments landscape changes. And the ability to navigate this evolving landscape – despite the increasing power of machine learning – still requires a distinctly human touch.
ACI Worldwide will participate in a panel discussion on Machine Learning at MRC London, April 25th at 4:15pm, as well as showcasing online fraud management and payments capabilities.
Related Blog Posts
Instant Payments Are at the Heart of the New Global Payments Landscape: 10 Trends to Watch in 2018
2017 was a big year for immediate payments: European Banking Association, Real-Time 1 (EBA RT1) SEPA Credit Transfer Instant, The Clearing House (TCH) Real-Time Payments in the U.S., and the Australian New Payments Platform (NPP) schemes, all either going live, or in the case of Australia, about to go live. These schemes enable real-time payment transfers across the United States, 34 European countries and Australia, with the potential to reach nearly another 1 billion people. This comes on top of the existing live schemes in the UK, China and India, so that over half of the global population now can access real-time payments solutions.
The Complexities of Cannabis: Banks, Merchants, Consumers and More
Cannabis—it’s no longer the verboten 800-pound pink elephant (though I think that might be a new strand). It’s about as mainstream as well…mainstream. And as we begin our latest Rantings Rant, it seems like the last time we (well, not you or I) experienced something like this, Al Capone and Elliot Ness were facing off during the time of Prohibition (if you’ve never seen the film The Untouchables, I highly recommend it!).
KodakCoin and Six Ways That Blockchain Could Really Be Leveraged
The newest cry in the cryptocurrency clamour? That of heritage-photography-giant-cum-new-kid-on-the-payments-block, Kodak. Unbelievably, they have managed to out-blockchain the long-island-iced-tea company in their audacity, and (more than) double their share price to boot.
Why User Engagement Matters, Even for Enterprise Applications
As a User Experience Designer at ACI, I spend a lot of time watching users interact with my designs. I need to make sure our solutions work properly, but lately I’m more interested in how they make my users feel. Engagement is a dominant concept in user interface design right now. It’s important because positive emotional experiences often lead to increased use and loyalty.
Five Payments Trends to Watch in 2018 [Part 1]
2018 is set to be a year of rapid change and new challenges for payments players. The floodgates are opening with PSD2 and UK Open Banking coming into force, bringing an onslaught of new competitors and potential partners. Whether evolution is mandated or market-driven, banks and processors are facing a critical year in their long-term success.
Five Payments Trends to Watch in 2018 [Part 2]
The New Payments Ecosystem Is Here. The floodgates are opening with PSD2 and UK Open Banking coming into force, bringing an onslaught of new competitors and potential partners. Whether evolution is mandated or market-driven, banks and processors are facing a critical year in their long-term success.
When Is Processing Payments in The Cloud More Secure?
Back when I started my career, “Jessie’s Girl” by Australian rocker Rick Springfield topped the charts, the federal funds rate was 20 percent and most organizations were reliant upon one or more mainframe computers that were hosted in an internal “computer room.”
Oh, the Different Ways to Pay Today (Not by Doctor Seuss)
Mark, Mega Millions tickets cost 2 dollars now?!? I don’t have 2 dollars in my wallet... I don’t have any dollars in my wallet!
And due to my lack of paper currency, if I’m not in it, I can’t win it. And I wanna win it, which has got me to thinking (again) about the new(er) ways to pay. When we last tackled the topic, I think we were ranting about wearable rings, speedos, the Rio Games and maybe Ryan Lochte’s hair. We’re now approaching a saturation point when it comes to places (on the body) to put payment mechanisms (especially if you’re in Rio!).
Payments' Big Five: what We Will be Hearing about in 2018
The new year is here… so while resolutions are enacted, and almost inevitably broken before the month is out, it is also the time to look ahead at what the next year may bring. One thing that is clear is that payments will become an even more important ingredient in the business strategy of every merchant. From my perspective, these are the five trends that will have the biggest impact in 2018.
The Eba's Regulatory Technical Standards Provide the “How” to Psd2's “What”
February 2017 saw the release of the long-awaited draft regulatory technical standards (RTS) for strong customer authentication (SCA) from the European Banking Authority (EBA). The RTS defines the technical framework for the implementation of PSD2 with primary focus on SCA, and common and secure connection (CSC). In short, we could say that PSD2 covers the “what” aspect of the regulation whereas the RTS defines the “how” this is to be done.