Sign up for The Paypers newsletter Follow The Paypers on LinkedIn Follow The Paypers on Twitter Follow The Paypers on Facebook Follow The Paypers on Google +
The Paypers, paypers, Insight in payments, News, Reports, Events
Expert opinion

Rules vs Scores: keeping fraud simple with Machine Learning

Friday 11 May 2018 | 08:42 AM CET

Aldrin Mangalabal, from Acapture, explains how Machine Learning, unlike traditional fraud prevention systems, can predict fraudulent behaviour without hindering the customer experience

What other products/services can I offer my customers? What would make their shopping experience even greater? How can we protect the business from fraud and make sure it doesn’t interfere with the shopping journey?

In an ideal world, consumer preferences would be the only concern for merchants. However, in reality, fraud takes first place in every ecommerce operator’s mind. Being too busy with protecting their business rather than offering unmatched products and customer experiences, merchants often get lost while searching for the best way to successfully manage fraud. 

And the fraud dominated ecommerce landscape does not help at all. In fact, 43% of monthly ecommerce transactions involve fraud attempts, costing more than USD 10 billion in 2017. And it gets even worse: fraud actually costs more than the value of the actual product or service being sold. On average, online merchants end up paying 2.5 times more than the actual loss itself.

This is where machine learning (ML) technology can make a big difference. Modern fraud experts use it to stay ahead of evolving fraud trends, something which has been impossible to do with traditional fraud management solutions.

Digging into the hype – worth it or not?

The technology is basically revolutionizing every industry, with fraud prevention being a particular success story. Machine learning systems are self-learning models, built using advanced mathematical algorithms to detect patterns and make predictions based on vast streams of normalized data. A fraud prevention ML model evaluates various signals and data sets, calculating the legitimacy of the transactions to precisely detect the fraudulent ones.

Why should merchants get familiar with it? Compared to the traditional rule-based fraud management approach, machine learning enables smarter and faster fraud prevention.

A smarter, more efficient way to deal with fraud 

ML solutions have a proactive nature, showing what’s happening in real-time, and identifying emerging fraud patterns. Furthermore, while traditional solutions can only calculate the outcome based on pre-programmed rules, ML is much more flexible, correlating various elements and working with past and new data features. 

The ML systems enable a more flexible and automated approach that speeds things up in terms of fraud management and conversion optimization. Fraudsters are caught on time and in a more accurate, effective way. Machine learning technology also detects patterns that are not often visible to fraud analysts, thus lifting their workload and raising the flag so that preventative action can be taken before it’s too late. Moreover, apart from differentiating fraudsters from genuine customers, ML-focused solutions can adapt the shopper experience too.

Just as people learn from experiences, machine learning collects and connects data points and paints the big picture. Dealing with fraud just got smarter and a lot easier; that’s why you should be definitely following this trend!

Empowered fraud managers

In addition to the improved speed and efficiency, machine learning also empowers fraud professionals to perform multiple reviews and analyses at the same time. Simultaneously, a machine learning model can also learn behavior patterns, integrating the outcomes and feedback provided by the analysts and using this data to continuously improve its predictive capabilities. Basically, it helps fraud professionals to easily make precise decisions, while minimizing the human effort to manually analyze data.

No matter how well-trained they are, fraud analysts wouldn’t be able to keep up with the latest scams and the current amount of fraud attempts. However, this does not mean that ML systems are on the verge of replacing fraud professionals altogether. Even the most developed systems will sometimes classify genuine activities as suspicious or overlook fraudulent behavior. That’s when the human element completes the picture by checking whether such transactions are legitimate or not, looking at the background story. Combining human expertise with this powerful technology enables a level of fraud prevention never before possible. Next to that, by using machine learning, fraud managers have more time to improve operational efficiency and focus on driving conversion to add more value to the business.

Just think of your experts as fraud fighters with superpowers: bam! You’re able to keep fraud simple with the help of Machine Intelligence.

Happy customers = increased conversion

Inflexible rule-based fraud solutions deliver too many false positives, locking out genuine buyers or causing obstacles in their shopping journey. Unsurprisingly, this makes them rethink their purchase decision. In contrast, machine learning continuously monitors buyer data based on identity and behavior, resulting in a highly accurate fraud score. By trusting this score, merchants improve authorization rates, reaching a higher conversion. At the same time, machine learning removes a lot of the hurdles and friction for legitimate consumers, ensuring that they enjoy a pleasant shopping journey and that they’re able to pay quickly and seamlessly.

Keep control over your conversion in real-time with the help of machine learning tech!

Story time: how does machine learning tech actually work?

In the end, it’s all about caring about your customers, making it as enjoyable as possible to return to your online shop and think of it as the ideal place for online purchases. To that end, machine learning is definitely shifting the way ecommerce players are designing their shopping experiences.

Acapture’s advanced fraud-screening solution, developed together with Sift Science, one of the world-leading machine learning companies, focuses on examining a great amount of payment data. The most important elements include shopping behavior, transaction amount, BIN, currency, IP and billing address, device type, payment method, email address, order history and much more. By constantly monitoring buyer behavior, the machine learning models calculate a fraud score based on a multitude of data sets and signals. The score ensures precise fraud detection to cut down chargebacks, while supporting higher authorization rates. Basically, with the help of machine learning technology, Acapture can instantly predict whether a customer is trustworthy or not so that they can approve the order, block it or perform additional screening, all while keeping genuine customers happy.

Curious about how you can keep fraud simple with machine learning? Get a live demo and check out what ML can do for your business.

About Aldrin Mangalabal

Aldrin is Acapture’s Fraud Manager, specializing in payment products and revenue optimization. He has been at the forefront of fraud innovation for his entire career, working with corporates, start-ups and SMEs from every corner of business culture to bring products and commercial strategies to new levels of accuracy and effectiveness. Companies for which Aldrin has previously worked include, Starbucks and Hawes & Curtis. 

About Acapture

Launched in 2015, Acapture is a new, modern, international payment service provider focused on maximizing the revenues of merchants around the globe. Acapture is affiliated to Payvision, one of the world’s fastest-growing global card acquiring networks. Licensed as a payment institution by the Dutch Central Bank, Acapture combines with Payvision to help merchants grow their business globally. This is done through a complete data-driven omnichannel payment solution, capable of managing a payment at every stage, from checkout to fund collection to settlement.