Sift

SEOClerks, a marketplace for SEO and other web-related services, was facing a significant challenge with fraud. Their approach to fraud prevention was largely reactionary, with fraudulent accounts being banned after a chargeback was received. However, these users would often return and create new accounts to continue their fraudulent activities. Despite having an IP-based fraud-detection tool, SEOClerks was still experiencing various types of fraudulent activity, including money laundering, referral fraud, account abuse, and friendly fraud. The main issue was money laundering using stolen credit card or PayPal information. They were unable to identify clear relationships between multiple bad users, and their existing fraud tool didn't provide any intelligence for spotting fraud rings or repeat abusers.

As Carousell began to scale, they started to see fraudsters posting fake and spammy product listings for products that either arrived to the buyer not as described or never got delivered to the buyer at all. Carousell didn’t have a way of proactively preventing these listings and relied on user flags to spot and remove them. This meant that these listings not only posed a threat to good users until they were eventually removed but threatened to sully the reputation of the platform, as well. Repeat fraudsters were also finding ways to get back onto the platform even after Carousell deleted their accounts, and continued to post abusive, fake listings with their new accounts. Carousell limits the number of accounts a user may have to a maximum of two, but fraudsters were creating multiple accounts and Carousell was finding it difficult to keep track of them all. Carousell was using a rules-based fraud solution, but it was time-consuming to have to jump in and change rules every time fraudsters changed their tactics.

Zirtue, a mobile relationship-based lending application, was facing a growing issue of friendly fraud where users were disputing their loan payments falsely claiming they had not authorized the transactions. This was compounded by the fact that Zirtue had access to a very limited amount of user data, preventing them from proactively recognizing suspicious behaviors and stopping the fraud before it happened. Additionally, the vetting process for taking out a loan was lengthy and required tedious and time-consuming email exchanges between Zirtue and the borrower, to ensure the borrower could confirm their identity. This manual work frequently delayed loans, creating headaches for the Data Analytics team and borrowers alike, and it was looking as though another team member would need to be hired to help handle the workload.