Detecting online auction shilling frauds using supervised learning
Expert Systems with Applications: An International Journal
| Hi-index | 0.00 |
Online auction sites are a target for fraud. Researchers have developed fraud detection and prevention methods. However, there are difficulties when using either commercial or synthetic auction data to evaluate the effectiveness of these methods. When using commercial data, it is not possible to accurately identify cases of fraud. Using synthetic data, the conclusions drawn may not extend to the real world. The availability of realistic synthetic auction data, which models real auction data, will be invaluable for effective evaluation of fraud detection algorithms. We present an agent-based simulator that is capable of generating realistic English auction data. The agents and model are based on data collected from the Trade Me online auction site. We evaluate the generated data in two ways to show that it is similar to the Trade Me auction data we have collected. In addition, we demonstrate that the simulator can have additional agents added to simulate fraudulent behaviour, and be used to evaluate fraud detection algorithms: we implement three different fraud behaviours and three detection algorithms, and using the simulator, compare the ability of the detection algorithms to correctly identify fraudulent agents.