Using Stereotypes to Identify Risky Transactions in Internet Auctions

Encountering unknown sellers is very common in online auction sites. In such a scenario, a buyer can not estimate trustworthiness of the unknown seller based on the seller´s past behavior. The buyer is thus exposed to the risks of being cheated. In this paper we describe a stereotypes based mechanism to determine the risk of a potential transaction even if the seller is personally unknown to not only the buyer but also to the rest of the system. Specifically, our approach first identifies discriminating attributes which are capable of distinguishing successful transactions from unsuccessful ones. A buyer can use its own past transactions (with other sellers) to form such stereotypes. Alternatively, the community´s collective knowledge can also be used to build such stereotypes. When posed to a potential transaction with an unknown seller, buyers can estimate trustworthiness (and thus the risk) by combining the corresponding stereotypes. We report experiments over real auction data collected from Allegro, a leading auction site in Eastern Europe. Data driven simulation results show that by setting suitable thresholds our approach can effectively detect (predict) frauds, i.e., has low false positive, with flagging very few successful transactions, that is, it has very low false negative. We also observe from these experiments that local knowledge derived stereotypes are the most accurate, since it is personalized for individual buyers. However, community knowledge derived stereotypes are particularly useful for inexperienced buyers that dominate online auction sites, though there is slight decrease in accuracy. We leverage such analytics to provide a browser (Firefox) based tool to guide buyers during live auctions.