Voice of the Industry

Why understanding your fraud false-positive rate is key to growing your business

Thursday 12 March 2020 15:53 CET | Author Mirela Ciobanu | Voice of the industry

Ecommerce businesses have a problem - one that causes lost customer revenue, yet has been historically nearly impossible to solveGeoff Huang, VP of Product at Sift

The problem stems from the inability to know their false-positive rate, which is the percentage of orders from legitimate customers that are mistakenly blocked as fraud.

According to a survey conducted by CNP, 42% of ecommerce merchants don’t know their false-positive rate (also known as customer insult rate). That is a startling statistic—nearly half of online sellers have no visibility into the number of good orders they inadvertently block or the subsequent revenue lost from those orders.

And the news, unfortunately, doesn’t get much better.

Insulted customers head to your competitors

Sift polled 1,000 adult consumers and found roughly 25% of insulted online shoppers—those who were falsely declined—will take their business to a competitor. That rate of brand abandonment jumps to 36% for consumers between 18-24 years old, and 31% for those between 25-34 years old. And businesses aren’t just missing out on the revenue from the declined orders and abandoned carts but the revenue from every subsequent order those customers would have placed. In a world where people expect frictionless, delightful experiences, one incorrect fraud decision can send valuable customers into the arms of competitors, hindering top-line growth.

The problem with determining your true false-positive rate

In the past, there hasn’t been an easy way to determine a true false-positive rate. In fact, it was next to impossible, leading 30% of businesses to not even attempt to measure it, according to CNP. Merchants could try to determine their rate by relying on legitimate customers who were inadvertently blocked—and insulted—to complain. But that put the onus on people who have just had a bad buying experience to alert businesses to the mistake. That type of data is anecdotal at best and hardly actionable.

Another option is to employ a team of reviewers who analyse each transaction that was deemed fraudulent, figure out why those transactions were declined, and determine whether that was the right call. But that approach requires a dedicated team focused on tedious, time-consuming analysis. It's also relying on analysts for the ‘ground truth’. It's tough to be sure that there would be consistency across different analysts. Hardly the ideal way to tackle the problem.

Meanwhile, as an industry, fraud prevention has benefited from automation, including real-time machine learning. With the right fraud prevention technology in place, businesses can spend less time on manual review, accept more orders, and drive revenue growth. So how can technology be applied to understanding and reducing false positives?

An unbiased way to reveal your true false-positive rate

To understand your false-positive rate and, subsequently, reduce the number of customers you insult, you need insight into the source of the false declines. The best way to do that is to run experiments on your blocking logic by creating holdout groups. Take a sample size of transactions that normally would be automatically blocked and instead automatically accept them or send them to manual review. You’ll know—either from a chargeback or a manual review decision—whether that purchase should have gone through, and can optimise your logic based on your findings.

This type of experimentation takes time and engineering resources to build—two things that are hard to come by for fraud teams. We’ve made it easy to run multiple experiments concurrently, quickly analyse the results, and turn those insights into action.

At Sift, we recognised how daunting the task of determining your true false-positive rate is, and how crucial doing so was to growth. Every business we work with knows customer insults are a problem but, unfortunately, many of them were resigned to just live with it since there hasn’t been a simple and effective way to measure false positives.

That is, until now.

Simply and effectively measure false positives with Insult Monitor

We wanted to create an easy way to accurately measure customer insult, ensure more good orders get through and build long-term customer loyalty. We created Insult Monitor to do just that.

Insult Monitor is the first and only feature offered by a fraud prevention solution that is dedicated to helping businesses understand their false-positive rates and take action to drive more revenue. It allows Sift customers to set up false-positive experiments with ease right within the Sift Console—no developers required. From there, you can visualise your results in real time and monitor the experiments you are running. And finally, we have made it easy to turn insight into action and ensure seamless order experiences—with one simple click.

To learn more about how Insult Monitor and why reducing customer insult is crucial to growing your business, visit our website >> www.sift.com/insult-monitor

About Geoff Huang

Geoff has led product marketing at companies like RingCentral and VMware, with a focus on go-to-market execution. He is a strong believer in simplifying the complexity of disruptive technology.

 

 

About Sift

Sift, formerly Sift Science, is the leader in Digital Trust & Safety, empowering companies of all sizes to unlock revenue without risk. Sift prevents fraud with industry-leading technology and expertise, an unrivalled global data network, and a commitment to building long-term partnerships with our customers. Twitter, Airbnb, and Twilio rely on Sift to stay competitive and secure. Visit us at Sift.com and follow us on Twitter @GetSift.


Free Headlines in your E-mail

Every day we send out a free e-mail with the most important headlines of the last 24 hours.

Subscribe now

Keywords: Geoff Huang, Insult Monitor, Sift, customer, customer experience, fraud prevention, risk, ecommerce, false positives
Categories: Securing Transactions | Digital Identity, Security & Online Fraud
Countries: World
This article is part of category

Securing Transactions