How SEOClerks created an excellent experience for trusted users while deterring fraudsters
70%
Fewer orders reviewed
Significant decline in fraud rate
OVERVIEW
Connecting buyers and sellers of SEO services
SEOClerks provides a unique marketplace where people and companies seeking SEO and other web-related services can connect with trusted providers. Founded in 2011, SEOClerks currently boasts hundreds of thousands of registered users. With buyers and sellers hailing from across the globe, SEOClerks is constantly exploring fresh ways to expand their marketplace, such as offering a lifetime affiliate program and other incentives. They’ve also broadened the services offered on the marketplace beyond SEO, inviting the community to ask for or offer any type of service.
CHALLENGE
Fraud rings and repeat scammers threaten the marketplace
Before Sift, SEOClerks’ approach to fraud prevention was largely reactionary. They would receive a chargeback from a fraudulent account, then ban that user from the site. However, more often than not, that user would come straight back to the site and create another account for committing fraud. Not only was SEOClerks feeling the pain of chargeback fees, but they were concerned about bad users threatening good users’ trust in the community.
Despite having a legacy IP-based fraud-detection tool in place, the SEOClerks marketplace was hit with multiple types of fraudulent activity, including money laundering, referral fraud, account abuse, and friendly fraud. The main problem that didn’t seem to have an easy solution was money laundering using stolen credit card or PayPal, since they could see no clear relationship between multiple bad users—and their existing fraud tool didn’t give them any intelligence for spotting fraud rings or repeat abusers.
SOLUTION
Connecting the dots between fraudsters
Battling a 4% chargeback rate, SEOClerks met with PayPal (their credit card merchant) to discuss their options. From a list of fraud detection vendors suggested by PayPal, SEOClerks chose Sift and successfully integrated within two days. They saw results immediately, identifying previously undetected fraud rings that their previous tool had missed. By the end of their trial, Sift had become an integral part of SEOClerks’ daily workflow.
Now fraud management at SEOClerks—which was previously a “hit or miss” activity shared across all members of the support staff—has turned into a more strategic endeavor. Armed with machine learning-based intelligence from the Sift Console, the SEOClerks team easily uncovers hidden links between fraudulent buyers and sellers. The team uses Lists based on custom criteria to quickly analyze high-risk users and decide whether they should be approved or blocked.
Not only does SEOClerks regularly discover and ban large fraud networks from the site, but their previous problem of banned users returning and creating new accounts has disappeared. Sift’s machine learning detects those repeat offenders immediately, so SEOClerks can automatically ban them, preventing them from placing orders or messaging other users.
SEOClerks also uses Sift to dispute chargebacks involving friendly fraud—cases where a legitimate customer makes a purchase and then claims it wasn’t them—by presenting evidence from Sift to show that the purchase was made by the rightful owner of the account.
RESULTS
Sales are up, fraud is down
Since implementing Sift, SEOClerks has seen sales on their platform rise, buoyed by enhanced trust that users have in the marketplace. With fraudsters and scammers prohibited from creating accounts, good users are having an even better experience with the SEOClerks community. Plus, by labeling users as “not bad,” SEOClerks has been able to train their machine learning model to recognize good, loyal customers.
Meanwhile, SEOClerks’ fraud rate—previously at 4%—has declined significantly. Because Sift’s predictions are so accurate, the amount of time the SEOClerks team dedicates to fraud management has also shrunk significantly, “minimized to minutes versus hours.” On average, they’re manually reviewing 70% fewer orders than before they used Sift.
And SEOClerks has been able to tailor a fraudster’s user experience based on their Sift Score—for example, not allowing a high-risk user to pay with a credit card, send messages, or create new content.
