When it comes to fighting fraud, it’s not really what you know – not exactly, at least. It’s what you don’t know, and how you go about finding those gaps and putting up defenses via better data and new technology.
That sounds like some cheap philosophical riddle, perhaps, but it serves as wisdom from the front lines of the fight against digital and financial services fraud – at least according to the story told in a new PYMNTS discussion involving Karen Webster and Yinglian Xie, CEO and co-founder of DataVisor, a company that uses artificial intelligence (AI) to help other businesses fight off fraudsters.
Fraud is big business, with online losses topping some $14.7 billion, according to the most recent research. As fraudsters become increasingly aggressive, new global regulations and solutions are being deployed to keep consumers, merchants and banks safe. As Xie discussed with Webster, the best general practice is to take a proactive approach to fighting fraud – but that’s much easier said than done. Fraudsters, after all, often work at an industrial-level scale (and with state backing), and are constantly finding loopholes to exploit and new techniques to try. Even the most aggressive fraud prevention efforts are often behind the times, so to speak – and that creates another vulnerability in the form of blind spots from which fraudsters can attack.
“The mindset has truly not been proactive, so we are not there yet,” Xie said.
But that also provides more opportunity to construct, deploy and use fraud defenses based on machine learning and AI. The models and algorithms at the heart of such systems are designed to spot patterns that can escape the human eye – patterns that might not appear as such now, but may signal future fraud attempts, tactics and attacks.
Fraud is a massive global problem, and you can bet that right now, fraudsters are thinking up new ways to defraud consumers and businesses. And fraudsters keep moving on to different scams, seeing what works as digital and mobile commerce continues to progress and consumer habits shift.
Download the latest edition of the @pymnts Digital Fraud Tracker today, to learn how @offerup is using #machinelearning to keep their #ecommerce marketplace secure and the fraudsters away: https://t.co/FBFfYCOo9a
— DataVisor (@DataVisor) November 4, 2019
New vs. Old Fraud
Take one recent example.
According to PYMNTS research, federal regulators in the U.S. are urging consumers to be cautious of a particular type of social scam. The Federal Trade Commission (FTC) reports that U.S. consumers lose more to romance-based fraud than any other type of scheme. The agency reported that more than 21,000 individuals were tricked into sending $143 million in romance scams in 2018 – triple the rate reported in 2015. The FTC also warned that these scammers are active on dating and romance platforms, and urged users to watch for warning signs like someone who asks for money at an in-person meeting or who claims to have no money on hand due to a business deal gone sour.
Account takeovers are also a hotspot for fraudsters, to the tune of some $4 billion per year. It can require a dizzying amount of activity to keep up with the latest fraud attempts without losing sight of the traditional methods that still bring in a decent amount of scratch to fraudsters’ coffers.
“Some fraud is newer, and some we see over and over again,” Xie said. And that’s part of the proactive fraud defense process: “You have to figure out the problem you want to solve,” she told Webster, “and in which areas you want to be more proactive.”
And doing so, in turn, will involve data – pinpointing what type of data to collect, order and feed into those machine learning and AI algorithms. After all, bad data will produce bad, misleading results.
“We are all collecting a lot of data,” Xie said. “We encourage [users] to think about particular use cases (for that data) and make sure they are leveraging the right amount of innovation.”
When it comes down to adopting a real, proactive stance on fraud prevention – one that will make a dent in fraud losses – Xie urged businesses to take an aggressive look at the new technology while also making sure to keep blind spots covered. After all, an incremental, step-by-step approach is unlikely to be enough when fraudsters are working at scale.