Shilling Recommender Systems for Fun and Profit

Recommender systems have emerged in the past several years as an effective way to help people cope with the problem of information overload. One application in which they have become particularly common is in e-commerce, where recommendation of items can often help a customer find what she is interested in and, therefore, can help drive sales. Unscrupulous producers may find it profitable to *shill* recommender systems by lying to the systems so that their products are recommended more often than those of their competitors. This talk will explore four aspects that may affect the effectiveness of such shilling attacks: (i) which recommender algorithms is begin used; (ii) whether the application is producing recommendations or predictions;
(iii) how detectable the attacks are by the operator of the system; and (iv) what are the properties of the items being attacked. The questions are explored experimentally on a dataset of a million movie ratings.

Article related to the above talk:

Lam, S.K. & Riedl, J. (2004) Shilling recommender systems for fun and profit. In Proceedings of the 13th international conference on World Wide Web (WWW2004), New York, NY, 2004, pp. 393-402.) See the publication page.

*John Riedl* has been a member of the faculty of the computer science department of the University of Minnesota since March 1990. In 1992 he co-founded the GroupLens Research project on collaborative information filtering, and has been co-directing it since. In 1996 he co-founded Net Perceptions to commercialize GroupLens. Net Perceptions was the leading recommender systems company during the Internet boom. In 1999, John and other Net Perceptions' co-founders shared the MIT Sloan School's award for E-Commerce Technology. They also shared the World Technology Award for being judged among the individual leaders worldwide who most contributed to the advance of emerging technologies for the benefit of business and society.

John received a bachelor's degree in mathematics from the University of Notre Dame in 1983. He earned a master's degree in computer science in 1985 and a doctorate in computer science in 1990 from Purdue University.
He is presently Professor at the University of Minnesota.