SOURCE: Sift Science

Sift Science

October 20, 2015 09:00 ET

New Research Reveals Alaska and Delaware Have Highest Fraud Rates, While 3 A.M. Is Fraudiest Time of Day

Sift Science's "United States of Fraud" Report Shows Purchases Made by Individuals Claiming to Be 85-90 Years Old Are 2 Times More Fraudulent

SAN FRANCISCO, CA--(Marketwired - Oct 20, 2015) - Sift Science, the leading provider of machine learning fraud detection, today released a new fraud report titled, "The United States of Fraud," which examines data of online transactions and profiles in various industries from August 2014 to August 2015. The study reveals and identifies fraud patterns, regions, purchase ranges and profiles the "Fraudiest Person in America."

To see more, download a full copy of the report here:

"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 for our customers. This not only helps our customers understand the risk of each transaction made on their websites, but also automate business decisions based on that risk. As a result, this data not only showcases typical fraudulent behavior, but allows some of today's premier online retailers to deliver a better customer experience to good users."

For this report, Sift Science examined a subset of customer data from August 2014 through August 2015, collecting information from 1.3M transactions that included shipping or billing addresses in the United States. 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.

In addition, Jason Tan will be presenting at this year's Money20/20 event in Las Vegas, NV, joined by security and data analytics experts from companies such as Bank of America and Microsoft, discussing "Using Artificial Intelligence & Data Analytics for Managing Fraud Risk & Data Security". The event will be held Oct. 25-28 at the Venetian hotel. To register, visit:

Tweet This: @SiftScience finds 3 am is the fraudiest time of day. See more in new "United States of Fraud" report: #USOF

About Sift Science
Sift Science provides real-time fraud protection through large-scale machine learning and risk scoring that allows online businesses to easily identify all types of fraud and protect their core assets. Sift Science not only provides businesses with the most comprehensive fraud detection platform, it can also be customized for any online business. By utilizing Sift Science's beautiful Console to effectively visualize site activity in real time, online business and marketplaces can balance the needs of fraud protection and great customer experience. Sift Science is headquartered in San Francisco, California. Visit us at and follow us on Twitter @SiftScience.

Contact Information

  • Media Contact:
    Jim Dvorak
    Kulesa Faul for Sift Science
    Email Contact