Detecting Fraudulent Personalities in Networks of Online Auctioneers
Online auctions have gained immense popularity by creating an accessible environment for exchanging goods at reasonable prices. Not surprisingly, malevolent auction users try to abuse them by cheating others. In this paper we propose a novel method, 2-Level Fraud Spotting (2LFS), to model the techniques that fraudsters typically use to carry out fraudulent activities, and to detect fraudsters preemptively. Our key contributions are: (a) we mine user level features (e.g., number of transactions, average price of goods exchanged, etc.) to get an initial belief for spotting fraudsters, (b) we introduce network level features which capture the interactions between different users, and (c) we show how to combine both these features using a Belief Propagation algorithm over a Markov Random Field, and use it to detect suspicious patterns (e.g., unnaturally close-nit groups of people that trade mainly among themselves). Our algorithm scales linearly with the number of graph edges. Moreover, we illustrate the effectiveness of our algorithm on a real dataset collected from a large online auction site.
Unable to display preview. Download preview PDF.
- 1.Brin, S., Page, L.: The anatomy of a large-scale hypertextual web search engine. In: Seventh international conference on World Wide Web, vol. 7, pp. 107–117 (1998)Google Scholar
- 2.Chau, D.H., Faloutsos, C.: Fraud detection in electronic auction. In: European Web Mining Forum at ECML/PKDD (2005)Google Scholar
- 4.eBbay 2006 1Q financial results (2006), http://investor.ebay.com/releases.cfm
- 5.Federal trade commission: Internet auctions: A guide for buyers and sellers (2004), http://www.ftc.gov/bcp/conline/pubs/online/auctions.htm
- 6.Gyongyi, Z., Molina, H.G., Pedersen, J.: Combating web spam with TrustRank. In: VLDB, pp. 576–587 (2004)Google Scholar
- 7.IC3 2004 internet fraud - crime report (2005), http://www.ifccfbi.gov/strategy/statistics.asp
- 10.Msnbc: Man arrested in huge ebay fraud (2003), http://msnbc.msn.com/id/3078461/
- 11.Neville, J., Jensen, D.: Collective classification with relational dependency networks. In: 2nd Multi-Relational Data Mining Workshop, 9th ACM SIGKDD, pp. 77–91 (2003)Google Scholar
- 12.Neville, J., Simsek, Jensen, D., Komoroske, J., Palmer, K., Goldberg, H.: Using relational knowledge discovery to prevent securities fraud. In: 11th ACM SIGKDD, pp. 449–458 (2005)Google Scholar
- 14.Resnick, P., Zeckhauser, R., Swanson, J., Lockwood, K.: The value of reputation on eBay: A controlled experiment (2003)Google Scholar
- 15.USA Today: How to avoid online auction fraud (2002), http://www.usatoday.com/tech/columnist/2002/05/07/yaukey.htm
- 16.Yedidia, J.S., Freeman, W.T., Weiss, Y.: Understanding belief propagation and its generalizations. Exploring artificial intelligence in the new millennium, 239–269 (2003)Google Scholar