Popular auction sites such as eBay have a new allies at Carnegie Mellon University. Computer science professors there have developed data mining techniques to seek out fraudsters in online auctions, reports Carnegie Mellon News.
Online auction sites are immensely popular. eBay, by far the largest online auction, reported third quarter revenues of $1.449 billion, up 31 percent from the previous year, and registered 212 million users, up 26 percent. This makes the site a magnet for unscrupulous dealers and alliances. This is where Network Detection via Propagation of Beliefs, or NetProbe, could help in revealing those who perpetrate fraud in online auctions.
"To the best of our knowledge, this is the first work that uses a systematic approach to analyze and detect electronic auction frauds," said computer science professor Christos Faloutsos.
The software looks for distinctive online behaviors that cause them to be readily purged from an online auction site. NetProbe has been tested and successfully identified 10 known perpetrators, as well as more than a dozen probable fraudsters and several dozen apparent accomplices. Though NetProbe is not yet available to the public, scientists at Carnegie Mellon said the software would not only be beneficial to combat online fraud but also could prove useful to law enforcement and security personnel of online sites.
"We want to help people detect potential fraud before the fraud occurs," said research associate Duen Horng "Polo" Chau, who developed NetProbe with Faloutsos, undergraduate student Samuel Wang and graduate student Shashank Pandit.