Challenge
Chargebacks, fake accounts, and unreliable tools
When Studypool first launched, the platform saw users who were taking advantage of tutors by posting questions and later filing chargebacks, in an attempt to get free study help. Some users also tried to game the system by creating fake student accounts so they could pay themselves and later file a chargeback, ultimately getting their money back and a payout from Studypool. At the time, their internal fraud prevention tools couldn’t keep up with the types of fraud surfacing on the platform. The tools were only able to track IP addresses and weren’t accurate or reliable, so Studypool decided to look for a better solution—Sift.
With Sift, we have more insights about all of our users. Seeing the whole picture has created a lot of value for us
Chuck Lopez, Head of Operations
Solution
Tapping into Sift for case management
To mitigate fraud on the platform, Studypool’s trust and safety priorities include both identifying fraudulent activity and accurately anticipating ill-willed schemes. This is where Sift comes in, providing the necessary tools and information Studypool relies on for its fraud-fighting processes. The Studypool team uses Sift specifically for case management to study user behavior and aid in their decision-making process. Studypool relies on Sift to identify user geolocation, which accounts are linked to each other, and see user activity including if those users have been flagged in the past under different accounts.
Results
Lowered fraud rates and boosted efficiency with Sift network visibility
Using Sift, Studypool has learned how to apply rules efficiently and lower false positives by pinpointing fraudulent behavior with reliable accuracy. After initially using Sift to lower chargebacks, their disputes are now under control at a low and steady rate, and have also seen significant improvements in operational efficiency.
Implementing Sift has also allowed Studypool to extend fraud detection across touchpoints and protect some of the features offered to users, such as their partner program. Sift helped surface users who were spoofing their IP address to cheat their way into the program and receive benefits. By leveraging Sift’s machine learning and network visibility, Studypool was able to filter out fraudulent users from joining their partner program and costing them time and money.
Our experience with Sift is very positive. We rely on Sift for 80% of our fraud prevention detection process.
Chuck Lopez, Head of Operations