The popularity of online auction sites has made them a target for crooks. Computer scientists at Carnegie Mellon are using data mining techniques to identify the perpetrators and their accomplices.
"To the best of our knowledge, this is the first work that uses a systematic approach to analyze and detect electronic auction frauds," said Professor Christos Faloutsos, who teaches computer science at Carnegie Mellon.
NetProbe, the software developed by his research team, analyzes publicly available histories of transactions posted by online auction sites — such as eBay — and identifies suspicious online behaviors, as well as associations among users.
In a test analysis of about one million transactions between nearly 66,000 eBay users, NetProbe correctly detected 10 previously identified perpetrators. It also identified more than a dozen probable fraudulent users and several dozen of their apparent accomplices.
"We want to help people detect potential fraud before the fraud occurs," said Duen Horng "Polo" Chau — a research associate who developed NetProbe with Faloutsos, undergraduate student Samuel Wang and graduate student Shashank Pandit.
Internet auction fraud accounted for almost two-thirds of the 97,000 complaints received in 2005 by law enforcement agencies from the federal Internet Crime Complaint Center.