Kevin Lee, Vice President of Trust and Safety at Sift, reveals three strategies for payment companies to expedite time-to-value through automated fraud prevention.
Payments and financial services merchants are a lightning rod for fraud. As companies grow, so does their appeal to fraudsters—typically at a rate that outpaces legacy risk tools and manual review. Businesses that can’t scale fraud prevention alongside growth are more likely to experience significant financial losses and struggle to recover from attacks they can’t stop.
PayMongo, a payments solution provider, suffered deep losses from payment fraud and watched its dispute rate reach an alarming 4%—a threat to its reputation and bottom line. They needed a way to scale securely while enabling their own customers’ success and found that the ideal way to do that was to balance friction with risk mitigation efforts.
‘Our goal is to help merchants focus on their business while we help them minimize risk,’ said Cha Tecson, Risk Analyst, PayMongo.
The vast majority of payments companies face common challenges just like this one: preventing payment fraud, period; and scaling fraud prevention as their user base expands, without hindering that expansion for the sake of reducing risk.
Part of the problem is that payment companies may rely on manually reviewing suspicious transactions. Banxa, a financial technology platform, built fraud rules to manually review orders using basic variables for customers, demographics, and payment methods. However, when Banxa’s volume spiked 30x, their fraud rate rose alongside it. Manual reviews could not keep up with the new level of fraud.
Another challenge that payment companies face is that verification systems and transaction limits can all create friction with legitimate users, which can negatively impact user growth. Uphold, a digital money platform, knew that it was crucial to ensure the trustworthiness of new users to prevent fraud while reducing the friction throughout the customer journey to ensure its user growth.
Automated fraud prevention is the clear solution for over-reliance on manual review. Banxa implemented an automated fraud prevention solution, allowing them to automatically accept, hold, verify, and decline orders based on routing and rules. Customised rules based on common attributes of fraud cases pinpoint when a user’s behaviour becomes suspicious. This is particularly useful for complex scams, which can often look like regular customer behaviour. Consequently, Banxa has reduced scams by 90 percent.
‘Being confident in our predicted fraud rates means we can be confident in our margins and managing costs, that value can’t be overstated,’ said Igor Sonkin, head of fraud, Banxa.
The operational efficiency of automation has enabled Banxa to grow with a 30x increase in volume while keeping their team lean—manual reviews would have cost five times more resources.
The ability to apply friction dynamically is another benefit of automation. Uphold leverages real-time risk assessments and insights from its automated fraud prevention solution to quickly build rules that secure key points in their customer journey, from account creation to the subsequent transactions on their platform. Suspicious behaviour is reviewed while trustworthy transactions are fast tracked, significantly lowering false positives and streamlining the customer experience. Consequently, Uphold has increased their new user acceptance rate to ~99 percent and lowered their credit card and ACH fraud rates to 0.01 percent.
The benefits of automated fraud prevention can be further enhanced with artificial intelligence (AI) and machine learning (ML). PayMongo discovered that certain products, such as alcoholic beverages and high-end gadgets were frequently targeted by fraudsters. These sorts of insights enable PayMongo to customise its response to stay ahead of fraud. Network visualisation enabled Banxa to see how hundreds of compromised cards were all linked together from an IP address or other signals.
It should be clear that automated fraud prevention is enabling payment companies to prevent more fraud with fewer resources as they scale with user growth, but this growth is not always predictable. When companies make the decision to invest in automated fraud solutions to mitigate rising fraud rates, they want to make sure they are realising the benefits of their investment as quickly as possible.
Hands-on guidance and pre-configured workflows can enable payment companies to start realising the benefits of automated fraud prevention in days instead of weeks, which can make a big difference in the face of rapidly growing fraud rates. Some automated fraud solution providers have fostered a community of fraud fighters, providing a hub for professionals to share their intelligence with each other.
‘Every tool has ML now, so it really comes down to how comfortable you are with the tool and how the team works with you. We really appreciate the people who work with us on this problem, that shouldn’t be overlooked,’ said Sonkin.
About Kevin Lee
Kevin Lee is VP of Digital Trust and Safety at Sift where he helps customers implement strategies that cross-functionally align risk and revenue programs. Prior to Sift, he has spent the last 15+ years leading various risk, chargeback, spam/scams, and trust and safety organizations at Facebook, Square, and Google.
About Sift
Sift is the leader in Digital Trust & Safety, empowering digital disruptors to Fortune 500 companies to unlock new revenue without risk. Sift dynamically prevents fraud and abuse through industry-leading technology and expertise, an unrivaled global data network of one trillion (1T) events per year, and a commitment to long-term customer partnerships. Global brands such as DoorDash, Twitter, and Wayfair rely on Sift to gain a competitive advantage in their markets. Visit us at sift.com, and follow us on LinkedIn.
https://www.linkedin.com/company/getsift/
https://twitter.com/GetSift
https://www.facebook.com/GetSift/
Every day we send out a free e-mail with the most important headlines of the last 24 hours.
Subscribe now