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
The Race to Real-Time Payments in Europe
Instant payments have quickly morphed into the new norm, and as individual European nations forge a real-time, digital-first payments environment, they raise the bar for all financial institutions conducting business in the Eurozone. It’s no longer a question of “what’s the business case?” but a matter of how instant payments players can take advantage of the opportunities now being created.
Local Perspectives: Real-Time Realities Across Asia-Pacific in 2019
Money20/20 Asia returns to Singapore this week, attracting payments professionals from around the vast APAC region – and beyond. The real-time and open imperative is one of the reasons why all eyes are on Asia-Pacific when it comes to payments, so I caught up with ACI payments experts representing three of the key countries within the region, to take the pulse of real-time schemes that are in varying stages of maturity.
Instant and Open Payments for Consumer Purchases – Lessons Learned From India and Beyond
Did you know that 65% of merchants want to accept instant payments? That’s because they know the customer experience (CX) benefits will drive growth for their business, and they recognize that this payment type will save their business money.
What it Means for a Bank to be Real-Time Ready – It’s More Than Just Payments
Banks are quickly learning that real-time enablement of the business is more than just a technological upgrade – there is a wider challenge of transforming services and customer experience. Although the banking world faces this challenge with some trepidation, there are success stories from other industries that have overcome legacy technologies and transformed frustrating and opaque customer experiences.
Putting Malaysia on the Path to Payments Innovation
The public launch of the DuitNow instant credit transfer service, in December 2018, provides just a taste of what lies ahead as Malaysia’s Real-time Retail Payments Platform (RPP) is progressively rolled out. Fueled by Bank Negara’s (BNM) increasing support for e-payment platform development, there has been a steady increase in mobile wallet and digital payment usage, setting the stage for 2019 to be a year of transformation for the payments industry in Malaysia.
The Potential of 'Request to Pay' to Revolutionize Payments
How often have you been in a situation where you realize in the middle of the month that you’re late paying an important bill? And then hit with a wave of dread as you check your bank account with trepidation to see if you can pay? Many of us are lucky to not be in that situation regularly, but most of us have been there at some point, and likely know others who are regularly confronted by this situation.
Monetizing Real Time and Open Payments A Global View from Leading Banks
Payments experts from Bank of Montreal, Lloyds Bank and Rabobank lead a discussion on #NewPayments use cases.
During Sibos 2018, I was lucky enough to moderate a panel of payments experts from around the globe, including banking leaders representing three key phases of the real-time evolution; early adoption, go-live and ‘wave 2.’ Here, I’d like to share insights from these experts, outlining the challenges and rewards for banks in the new real-time and open payments ecosystem.
All I Want For Christmas (Or Any Holiday) Is… Instant Payments Gratification
Mark, some of us are fast approaching the end of the holiday shopping season, some of us are fast approaching that time of year when we consume too much egg nog, and some of us are fast approaching too many viewings of Die Hard or It’s a Wonderful Life or Love Actually or Christmas in Connecticut (I’ve disclosed too much about myself). To segue slightly more than slightly, I was at Target over the weekend, braving the holiday shopping crowds, to buy toilet paper, paper towels and tissues… and I took advantage of the 5% off that I get from using my Red Card. I surveyed the throngs of other consumers in the nearby checkout lines and not once did I see another store card. During this, the biggest shopping season of the year, why wouldn’t consumers use loyalty/rewards cards when making purchases?
Instant Payments in Italy – And Beyond: Lessons from Il Salone dei Pagamenti
ACI was invited back to Il Salone dei Pagamenti – Italy’s premier payments event organized by the Italian Banking Association (ABI) – to participate in a panel, “SEPA Inst – the Future.” As expected, the session was packed with stats and advice for a more efficient roll out of instant payments – in Italy and beyond.
Request for Pay – What Does It Mean For Financial Institutions?
What do banks – one with $60B+ in assets, one a mid-size regional bank, and one, a small innovative credit union – have in common with payment networks and the ‘Big 4’ consulting firms? They were all part of the first ACI #PaymentsForBreakfast event in North America! The theme was real-time payments, but the focus was more specifically on Request for Pay.