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
Contactless Turns Ten: The Shift to Contactless Universal Payments is Now Well Established
In September 2007, Barclaycard first introduced contactless payments to the UK. Ten years on, and many Brits would no longer want to live without a contactless card in their wallet. In fact, six out of ten Brits now pay with "touch and go," and according to the UK Cards Association 108 million contactless cards are in circulation in the UK, with volumes of transactions currently reaching £400 million per month.
Vanilla Payments Don't Always Cut the Mustard
Five years ago, there was a clear trend among major brick-and-mortar retailers to bring in their own payments software. Except for very small retailers that used bank-owned stand-alone POS terminals, retailers wanted to own and operate their own systems – usually licensed products from a small number of specialist payments software vendors. This approach gave retailers flexibility, control and cost savings through centralization. Other than the bank-owned terminal approach, there were few viable alternatives.
How Connected Consumer Lifestyles Will Drive Forward Mobile Payments
Merchants are striving to respond to the ever-changing behaviors and expectations of consumers by creating seamless purchasing experiences that engage customers and keep them returning for more. In turn, payment service providers (PSPs) and technology vendors are endeavoring to meet the needs of those merchants by providing appropriate supporting technology and services.
Amazon & Whole Foods: A Game-Changer for Customer Experience
The estimated $700-billion-dollar grocery business recently got a jolt when Amazon announced its intended purchase of Whole Foods Market. With more than 450 stores in the U.S. and UK, Amazon will be plunging head first into the physical world of commerce.
Stop Fraud… Or Increase Conversion Rates? With a Fine-Tuned Fraud Engine, Merchants Can Do Both
Preventing fraud and driving high conversion rates are universally important objectives for merchants – but many struggle to adequately balance these two demands. They either employ aggressive fraud prevention strategies to minimize fraud losses, or conversely, reduce checks in order to prevent false positives, improve customer experience and ensure sales targets are met. Neither exclusive approach works in the long run; focusing on only one will prove costly on multiple fronts.
ETA TRANSACT: Time To Break Out… And Cross Borders To Reach New Customers
It’s before lunch on day one of ETA Transact17 in Las Vegas; exhibitors are still putting the finishing touches on their stands in the main hall, so it’s the perfect opportunity to sit in on some of the breakout sessions, part of the educational program put on by the Electronic Transactions Association. And ‘breakout session’ seems particularly apt in this case, as panelists from ACI Worldwide, Planet Payment, and arvato launch into a discussion on how merchants and payment providers can ‘break out’ of their domestic markets and take advantage of the huge opportunity in cross-border eCommerce.
Why Omnichannel Shoppers Are Worth It
Today’s consumers are tech savvy and highly connected, demanding convenience, speed and choice across channels, payment methods and fulfilment options. And, with a growing proportion of shoppers readily switching between online, mobile and physical touchpoints at various points in the purchasing journey, merchants are now dealing with a constantly evolving and unpredictable retail landscape. This requires fresh strategies and technologies that allow them to adapt to the expectations of omni-channel customers.
Are Millennials’ Shopping Behaviors Today, Everyone’s Shopping Behaviors Tomorrow?
Much has been made of the impact that the so-called ‘Millennial generation’ (aka Generation Y) will have – or is already having – on the way financial services are developed and delivered. And plenty of (digital) column space has been dedicated to discussing how the first digital native generation is transforming commerce – and payments – with different expectations, preferences, and shopping behaviors than their older cohorts.
The Middle East Presents Retailers A Growing Opportunity But Faces Two Challenges
36% of Middle East residents are digital shoppers1 and are expected to spend $19B2 online in 2017; with this spend figure rapidly growing to $34B in 2021. Although cash is the preferred method of transacting, the region is edging toward a digital society. In the UAE and Saudi Arabia, nearly two thirds of the population has smartphones—fueling shopping online growth.3 This prevents retailers new growth opportunities.
Are Card Payments Getting Simpler... Or More Complex?
2017 is now well underway, and the trends that will shape the year ahead in payments are taking shape. There has already been plenty of discussion around frictionless payments, and reducing complexity for both consumers and for merchants. So, are card payments getting simpler, or more complex? The answer seems to be… both.