Detection of Auction Fraud in Commercial Sites

Abstract

Online auctions have become one of the most convenient ways to commit fraud due to a large amount of money being traded every day. Shill bidding is the predominant form of auction fraud, and it is also the most difficult to detect because it so closely resembles normal bidding behavior. Furthermore, shill bidding does not leave behind any apparent evidence, and it is relatively easy to use to cheat innocent buyers. Our goal is to develop a classification model that is capable of efficiently differentiating between legitimate bidders and shill bidders. For our study, we employ an actual training dataset, but the data are unlabeled. First, we properly label the shill bidding samples by combining a robust hierarchical clustering technique and a semi-automated labeling approach. Since shill bidding datasets are imbalanced, we assess advanced over-sampling, under-sampling and hybrid-sampling methods and compare their performances based on several classification algorithms. The optimal shill bidding classifier displays high detection and low misclassification rates of fraudulent activities.

Incremental learning framework for real‐world fraud detection environment

“…So, regarding the bidder verification model, in the experiments, we extract the actual labels from the original labeled Shill Bidding dataset. 9 Besides, the bidder verification model can be fully automated, as explained in the future work section.…”

“…9 SMOTE increases the size of the fraud class with new data strongly related to the original data, and ENN removes TomekLinks/noisy data that threat the model performance. 9 • Incremental memory model: The challenge when implementing an incremental learning algorithm is the stability and plasticity problem. An incremental model requires being adequately stable to hold the training data a bit longer, that is, the recent chunk has more impact on the model training than the previous chunk.…”

“…3,5,7,8 Shill Bidding is a critical problem, as it can result in substantial financial losses for genuine consumers, as seen in several lawsuits. 9 For instance, in 2012, the auction company "Trade Me" made payments of $70,000 to each victim of Shill Bidding committed by an autodealer. 9 The fraud, which went undetected for a year, resulted in important losses for the victims.…”

“…9 For instance, in 2012, the auction company "Trade Me" made payments of $70,000 to each victim of Shill Bidding committed by an autodealer. 9 The fraud, which went undetected for a year, resulted in important losses for the victims. Trade Me banned the accused trader and referred it to the Commerce Commission for a thorough investigation.…”

“…In addition, imbalanced data often lowers the classification algorithm performance. 9 • Offline learning: Existing fraud classification solutions were designed for offline use and cannot function in real-life scenarios. To benefit consumers, we need to devise a Shill Bidding detection service to be operational in the real-world auction environment.…”