Mining Online Shopping Frauds—A Non-Data Mining Approach

 Abstract—With the growth of e-commerce, various schemes have emerged to defraud suppliers who offer services and sell goods over the Internet. The deferred payment system, which is a traditional Japanese business practice whereby customers do not pay until goods are received, facilitates online fraud. After receiving goods, fraudulent clients simply disappear and the supplier does not receive the payment. However, since the traditional deferred payment system is expected by honest customers, online shopping sites cannot eliminate this payment system, and consequently are vulnerable to this type of fraud. The conventional approach to detect online shopping fraud is the use of various data mining methods based on statistical analysis. However, outbreaks of new fraudulent clients create new samples that change the distribution of data and decrease the performance of data-mining-based fraud detection. In this study, we propose a new approach that does not rely primarily on data mining. The main characteristic of the proposed approach is the use of the nature of economic crimes. In addition, specific implementations to detect online shopping fraud are proposed. The application of the proposed approach in other areas, such as spam filtering and Internet virus detection, is also discussed. outlier detection, and visualization are techniques typically used to detect fraud. Based on the statistical attributes of transaction data, these methods attempt to distinguish normal transactions from fraudulent transactions. However, fraudsters attempt to steal goods without triggering identification of a fraudulent transaction. They pose as new customers and change their address frequently. Since fraudulent clients change identity and essentially disappear before data mining methods acquire sufficient information to detect their fraudulent activities, the use of data mining methods to expose such clients cannot achieve effective outcomes.