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 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.
Dedicated Followers of Fintech: Why Transaction Banking Never Goes Out of Fashion
Taking part in a panel at a recent corporate treasury conference, I was introduced as a ‘consumer payments expert’ – not an obvious qualification for sharing stage-time with serious corporate liquidity and cash management folk, but as the talk track was on mobile wallets and Open Banking, I had some reasonably safe and relevant content on which to fall back.
Sibos Preview: The Five Trends Transforming Real-Time Payments
Real-time is now a reality, with more than 30 schemes live around the world. And real-time is in the spotlight as banks and financial service providers make their way to Sydney for Sibos 2018. What better time to look ahead at the key trends that are going to shape the ongoing development of real-time payments.
API Management: The Reason Digital Open Banking Can Fly
When it comes to thinking about the different roles that an API Manager can play for an organization, I personally think that an airport provides the perfect analogy. The customer is the passenger, the third-party organizations using a bank’s APIs are the airlines and the airport itself is the bank. I also think this analogy helps to visualize the variety of API management capabilities – including the role of an API gateway.
Can Corporate Banking be as Easy as Ordering Pizza?
ACI recently hosted Greenwich Associates on a webinar to discuss corporate banking. While not a topic that would usually make attendees salivate, the discussion turned toward ordering pizza (maybe, because it was close to lunchtime) and Greenwich highlighted how corporate banking should be as easy as ordering pizza.
Modernizing Cross-Border Transfers with SWIFT gpi
The customer experience for domestic payments – retail and corporate – has recently undergone a complete transformation. There’s still plenty more that could be achieved, but the advent of real-time payments in combination with open APIs has seen the launch of Request for Payment services and direct eCommerce instant payments in the UK and Europe. And it’s not just the PSD2 push in Europe that’s driving change – in the U.S., Zelle is moving beyond standalone P2P payments to become an integrated part of the retail banking app experience, as well as being included in new kinds of corporate disbursements.
Instant + Open Payments = A Winning Combination
I recently joined a panel discussion at EBAday 2018, alongside representatives from across the payments ecosystem, and the clear consensus was that real-time payments will be the new normal. This was evidenced by some of the interactive polls carried out.
Maintain Vs. Invest: What the Digital Era Ushers in for Banks
Taking place this week in Brussels, the European Credit Research Institute (ECRI) will host a high-level debate on how policymakers can build on the process of digitalisation of banks to raise competitiveness in light of increased competition from fintech start-ups and tech giants.
How the Merchant Payment Ecosystem Can Create Value in Instant Payments
Recently, ACI conducted some research into the appetite to make use of instant payments among corporates. The results were overwhelmingly favorable, but when we think about the benefits of immediate payments for corporates, it does seem obvious that they would want to leverage this new payment type.
Real-Time Payments Will be Europe’s Most Dominant Payments System – Are You Ready to Realize the Full Value?
Since the launch of the SCT Inst rulebook in November 2017, many more banks are live and offering real-time payments to their customers, with most of the rest committed to 2018. The buzzword at the recent ECB #TIPSapp Event in Frankfurt was ‘Interoperability,’ or as my friend José Beltrán from STET would say, ‘Reachability.’ No-one expressed this more clearly on February 6th than Javier Santamaria, President of the European Payments Council, when he reiterated his message from Il Salone Dei Pagamenti, the day after the SEPA launch; "We have launched the Pan-EU scheme, now it is up to you in the audience and beyond to take advantage of it and make it work."