University of Rhode Island researchers have created algorithms they say can detect subtle manipulations of online rating systems such as those used by eBay and Amazon. in a statement. “Our algorithm is designed to improve the quality of the information in the rating systems to make them more reliable.”
“These reputation rating systems are used every day and they are highly valuable,” said Yan Sun, assistant professor of computer engineering at URI,
Sun points out that rating systems are important in that customers have been shown to pay more for offerings with high ratings. Not surprisingly, obvious fraudulent attempts to game the systems have been made, such as by publishers (or rival publishers) voting up or down books online.
Sun and collaborators Steven Kay, Qing Yang andYafei Yang say their patent-pending technology targets more subtle attempts to manipulate the rating systems and can reduce rating bias by two-thirds. They tested the algorithms in part by challenging computer scientists and hackers to attack a rating system protected by the technology.
Those interested in licensing the technology should contact Sun at yansun@ele.uri.edu for technical questions and David Sadowski at dsadowski@mail.uri.edu for licensing information.
Related: 10 Wicked Cool Algorithms
