8 key online fraud behaviors and patterns

Sift Science examined data from 1.3 million online transactions and profiles in various industries from August 2014 to August 2015. Data was cross-referenced with third-party data from FullContact to identify age and gender, computing fraud rate with the number of fraud users as a fraction of the entire sample size.


Key findings:

  • 3 a.m. is the fraudiest time of day, regardless of time zone. Also, fraudsters are more likely to transact during the weekdays
  • Alaska has the highest fraud rate based on billing address while Delaware has the highest fraud rate based on shipping address.
  • The Midwest has the lowest rate of fraud based on both shipping and billing addresses. However, Massachusetts has the overall lowest rate of fraud.
  • Men are slightly more likely to be fraudsters than women.
  • Users identifying themselves in the 85-90 age range are two and-a-half times more likely to be fraudsters than the average user.
  • A user with two to four accounts linked to one device is eight times more likely to be fraudulent.
  • Purchases worth $0-25 are twice as likely to be fraudulent, suggesting criminals test stolen credits cards for validity, trying low-value orders.
  • Accounts less than three days old are three times more likely to be fraudulent, while accounts that are two months old are two times more likely to be fraudulent.



“Fraudsters are enjoying success in the ever-changing online playground as the ecommerce marketplace ecosystem grows,” said Jason Tan, CEO and co-founder of Sift Science. “We continue to see fraud behavior consistent across various industries, and reveal identifying factors that help us track and score today’s most advanced fraudsters.”

More about

Don't miss