According to the Internet Crime Complaint Center (IC3) reports from 2006 to 2014, we can find the online fraud cases are increasing rapidly year by year. Although the online auction web site is the biggest platform for online transaction, it brings the huge chances to do the online auction frauds. To prevent the online auction frauds, this research will propose a fuzzy genetic approach to learn the detection rules for detect the fraudster accounts. The goal of this research is to help the users to identify which seller is more dangerous. The seller behavior features will transform into fuzzy rules which can represent the detection rules. Then optimize the fuzzy rules by genetic algorithms to build the auction fraud detection model. For implementation, we collect the real auction data from "Ruten Auction" which is the most popular auction site in Taiwan. Then we use the proposed detection model to analyze the fraudster accounts and find out the optimal detection rules of them. We hope the result of this research can help the website administrators to detect the possible seller fraudsters easier in online auction.
展开▼
