{"id":25839,"date":"2024-01-31T16:46:40","date_gmt":"2024-01-31T15:46:40","guid":{"rendered":"https:\/\/www.intellias.com\/?p=25839"},"modified":"2024-06-14T12:12:29","modified_gmt":"2024-06-14T10:12:29","slug":"how-to-reduce-to-the-volume-of-false-positives-in-payments-with-ml","status":"publish","type":"blog","link":"https:\/\/intellias.com\/how-to-reduce-to-the-volume-of-false-positives-in-payments-with-ml\/","title":{"rendered":"How to Reduce False Positives in Banking Payments with ML"},"content":{"rendered":"

Payment fraud is a shared locus of pressure for payment processors, merchants, and us, the regular online shoppers. Can we eradicate payment fraud? Unlikely. Can we learn how to cope with it more effectively? Absolutely.<\/p>\n

In fact, better payment fraud detection should be a top priority for FIs. Increased volume of digital sales is ‘new normal\u2019<\/a> for most retailers. But that\u2019s awesome news, right?<\/p>\n

Sure thing, but…the card not present (CNP) fraud is on the rise, too.<\/b><\/p>\n

\n\t\t\t
\n\t\t\t\t
\n\t\t\t\t<\/linearGradient><\/defs><\/svg>\n\t\t\t\t\t

By 2023, retailers will lose $130+ billion in revenue on fraudulent card-not-present transactions if they fail to keep up with digital fraud prevention measures. <\/p>\n\t\t\t\t<\/div>\n\t\t\t\t\n\t\t\t\t\n\t\t\t\t\tJuniper Research<\/span> <\/span>\n\t\t\t\t<\/small>\n\t\t\t<\/blockquote>\n\t\t<\/section>
\nOk, so should I tighten my online payment security measures, is this what you are implying?<\/p>\n

Not so fast. Running a suboptimal fraud detection engine \u2014 one that has an offensively high rate of false positives \u2014 can cause more damage to your company than payment fraud.<\/p>\n

Why false positives are a jinx for the financial industry<\/h2>\n

A standard rules-based security engine installed by an online retailer can decline up to 30% of non-fraudulent orders.<\/b><\/p>\n

After being declined, 42% of customers<\/a> will abandon their cart. What\u2019s more, 4 out of 10 shoppers will go on and place an order with another company, rather give another go to the security-tight merchant.<\/p>\n

And here\u2019s the biggest kicker:<\/p>\n

\n\t\t\t
\n\t\t\t\t
\n\t\t\t\t<\/linearGradient><\/defs><\/svg>\n\t\t\t\t\t

19% and 32% of shoppers in the $800,000-$999,999 and $1 million-plus income brackets, respectively, moved on to competing companies when their payment is declined<\/p>\n\t\t\t\t<\/div>\n\t\t\t\t\n\t\t\t\t\n\t\t\t\t\tRiskified consumer survey<\/span> <\/span>\n\t\t\t\t<\/small>\n\t\t\t<\/blockquote>\n\t\t<\/section>\n

Yikes, that\u2019s a target audience few retailers would want to lose! And even if you are not catering to the uber-rich of this world, those false declines can be cutting a major drain in your revenues. Accenture<\/a> reports that annual global e-commerce fraud losses range from $25 to $40 billion.<\/p>\n

Banks shouldn’t get all cozy either. IBM reports<\/a> that as much as 90% of notifications about potential suspicious activities do not result in the filling of a suspicious transaction report. In other words, your systems can detect all-things-that-seem-to-be-fraud, but they are not configured to investigate whether the event was actual fraud or not, resulting in a high rate of false positives in banking.<\/p>\n

Wait, but we already modernized some of our legacies back-office operations, including fraud monitoring systems. Where\u2019s the problem?<\/p>\n

\n\t\t\t
\n\t\t\t\t
\n\t\t\t\t<\/linearGradient><\/defs><\/svg>\n\t\t\t\t\t

Despite recent advancements and investments in new technology, 51% of banks still reported a high rate of false-positives, resulting from their technology solutions, decreasing efficiencies in fraud detection.<\/p>\n\t\t\t\t<\/div>\n\t\t\t\t\n\t\t\t\t\n\t\t\t\t\tGlobal Banking Fraud Survey KPMG<\/span> <\/span>\n\t\t\t\t<\/small>\n\t\t\t<\/blockquote>\n\t\t<\/section>\n

Basic financial security mechanisms such as two-factor authentication, network analysis, and even behavioral biometrics are good measures for card not present fraud prevention. But they do not help you tackle emerging fraud proactively.<\/p>\n

Also, ineffective management of incoming fraud information and lack of clear data governance can make even state-of-the-art fraud detection mechanisms inefficient. So where\u2019s the solution then? As the post title implies, it\u2019s machine learning and AI<\/a> that can make a major difference.<\/p>\n

\n\t\t\t
\"Preparing<\/div>\n\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t
PREPARING FOR THE NEW GROWTH CYCLE<\/div>\n\t\t\t\t\t
A Technical Blueprint for Banks<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t Download now <\/span>\n\t\t\t<\/div>\n\t\t<\/a><\/div>\n

Accuracy detection: Using machine learning to reduce false positives in AML screening<\/h2>\n

Traditional automated fraud detection systems can get overwhelmed pretty fast.<\/p>\n

That\u2019s because most were never meant to cope with the large volume of incoming data from multiple sources in the first place. Next, the data itself can be hosted in a siloed, fragmented, and incomplete manner across different locations, making it harder to investigate and monitor. Lastly, such detection systems rely on outdated rules and thresholds that hardly align with the current payment
\nlandscape \u2014 omnichannel commerce, mobile payments<\/a>, contactless payments<\/a>, and soon, IoT payments.<\/p>\n

\n
\n

Learn about the future of contextual commerce and IoT payments<\/p>\n

\n
<\/div>\n <\/div>\n <\/div>\n Read more<\/span>\n\t\t <\/a><\/div>\n

Machine learning (ML) relies on algorithms that can learn from an array of available data and create more accurate classifications of fraudulent and genuine payments. What\u2019s more, ML-powered systems can progressively learn over time without being reprogrammed.<\/p>\n

These qualities make ML a strong contender for augmenting the fraud investigation process and providing your analysts with the latest insights. Even better, you can set the entire process of reviewing, classifying, and flagging transactions on an intelligent auto-pilot, rather than rely on blanket rules, built upon the same logic for everybody.<\/p>\n

\n\t\t\t
\n\t\t\t\t
\n\t\t\t\t<\/linearGradient><\/defs><\/svg>\n\t\t\t\t\t

The value of real AI tech is that every single person is different. This allows FIs to know how you spend and your behavior \u2014 what is personalized and specific to you? That way, they can protect you well \u2014 and also serve you well with the kinds of products you want to see. <\/p>\n\t\t\t\t<\/div>\n\t\t\t\t\n\t\t\t\t\n\t\t\t\t\tDr. Akli Adjaoute, <\/span> CEO, Brighterion<\/span><\/span>\n\t\t\t\t<\/small>\n\t\t\t<\/blockquote>\n\t\t<\/section>\n

Picture this: you and your spouse have a joint bank account. As in all happy families, one is a spender, and another one is a saver. You decide to exchange your cards for a week to see what happens.<\/p>\n

When the spender goes on their regular shopping spree with a \u2018savers\u2019 card, a rules-based fraud detection system will likely mark this as an anomaly and decline some big-item in-store transactions. At the same time, the \u2018saver\u2019 prefers shopping online since the discounts and cashback are better. This is an untypical behavior (as per the rules-based system), so their online transactions may get falsely declined too.<\/p>\n

In both cases, the result is the same \u2014 a trusted FI got the customer in a frustrating position. Since they have plenty of other cards and payment methods available, they\u2019ll likely reach out for an alternative option the next time around.<\/p>\n

\n\t\t\t
\n\t\t\t\t
\n\t\t\t\t<\/linearGradient><\/defs><\/svg>\n\t\t\t\t\t

56% of cardholders decrease online shopping, reduce payment card usage, and close payment card accounts after facing a fraudulent event.<\/p>\n\t\t\t\t<\/div>\n\t\t\t\t\n\t\t\t\t\n\t\t\t\t\tSparks Research <\/span> <\/span>\n\t\t\t\t<\/small>\n\t\t\t<\/blockquote>\n\t\t<\/section>\n

And as we said before \u2014 superb customer experience<\/a> is key to winning and retaining financial customers. Losing loyal customers to false declines is painful to say the least.<\/p>\n

Now, unlike traditional fraud detection systems, machine learning algorithms can create rules, rather than follow them. ML solutions can capture and analyze 100+ specific features, unique to an individual transaction. For example, transaction time, location and type; amounts spent with certain vendors, a percentage of online vs offline sales, and so on.<\/p>\n

As a result, the algorithm creates an evolving ‘normcore’ profile for every cardholder and triggers alerts only if the spending behavior deviates from the set standards.<\/b><\/p>\n

But can machine learning fraud detection solutions really deliver more accurate results?<\/p>\n

You bet! Here\u2019s proof:<\/p>\n

Danske Bank<\/b> used to have a fraud detection system based on hand-crafted rules. At times, their rate of false positives reached 99.5%<\/b> transactions, skyrocketing investigation costs, and underlying customer experience. After adopting machine learning for fraud detection, the bank:<\/p>\n