Building High-Quality Auction Fraud Dataset

Proceedings of the 51st Hawaii International Conference on System Sciences, 2018

Online auctions are highly susceptible to fraud. Shill bidding is where a seller introduces fake bids into an auction to drive up the final price. If the shill bidders are not detected in run-time, innocent bidders will have already been cheated by the time the auction ends. Therefore, it is necessary to detect shill bidders in real-time and take appropriate actions according to the fraud activities. This paper presents a real-time shill bidding detection algorithm to identify the presence of shill bidding in multiple online auctions. The algorithm provides each bidder a Live Shill Score (LSS) indicating the likelihood of their potential involvement in price inflating behavior. The LSS is calculated based on the bidding patterns over a live auction and past bidding history. We have tested our algorithm on data obtained from a series of realistic simulated auctions and also commercial online auctions. Experimental results show that the real-time detection algorithm is able to prune the search space required to detect which bidders are likely to be potential shill bidders.

Journal of theoretical and applied electronic commerce research

Online auctions are a popular and convenient way to engage in ecommerce. However, the amount of auction fraud has increased with the rapid surge of users participating in online auctions. Shill bidding is the most prominent type of auction fraud where a seller submits bids to inflate the price of the item without the intention of winning. Mechanisms have been proposed to detect shill bidding once an auction has finished. However, if the shill bidder is not detected during the auction, an innocent bidder can potentially be cheated by the end of the auction. Therefore, it is essential to detect and verify shill bidding in a running auction and take necessary intervention steps accordingly. This paper proposes a run-time statistical algorithm, referred to as the Live Shill Score, for detecting shill bidding in online auctions and takes appropriate actions towards the suspected shill bidders (e.g., issue a warning message, suspend the auction, etc.). The Live Shill Score algorithm also uses a Post-Filtering Process to avoid misclassification of innocent bidders. Experimental results using both simulated and commercial auction data show that our proposed algorithm can potentially detect shill bidding attempts before an auction ends.

Applied Artificial Intelligence, 2019

Given the magnitude of monetary transactions at auction sites, they are very attractive to fraudsters and scam artists. Shill bidding (SB) is a severe fraud in e-auctions, which occurs during the bidding period and is driven by modern-day technology and clever scammers. SB does not produce any obvious evidence, and it is often unnoticed by the victims. The lack of availability of training datasets for SB and the difficulty in identifying the behavior of sophisticated fraudsters hinder research on SB detection. To safeguard consumers from dishonest bidders, we were incentivized to investigate semisupervised classification (SSC) for the first time, which is the most suitable approach to solving fraud classification problems. In this study, we first introduce two new SB patterns, and then based on a total of nine SB patterns, we build an SB dataset from commercial auctions and bidder history data. SSC requires the labeling of a few SB data samples, and to this end, we propose an anomaly detection method based on data clustering. We addressed the skewed class distribution with a hybrid data sampling method. Our experiments in training several SSC models show that using primarily unlabeled SB data with a few labeled SB data improves predictive performance when compared to that of supervised models.

2016

Due to rapid growth of the use of online auctions, fraudsters have taken advantage of these platforms to participate in their own auctions in order to raise prices (a practice called shilling). Innocent bidders have been forced to pay higher prices than they were willing to offer. This has resulted in the need to design and implement a shill detection algorithm. To eliminate this shilling problem, we designed a shilling detection algorithm integrated with an online auction. The algorithm proved to be effective and it was tested on the internet, and the short time of shill detection proved that the algorithm can work real time on e-auctions with large user base. This method can be used as a technique to eliminate shilling. Key words: E-auction, bidding, shilling, shill attributes, shill score.

Entropy, 2015

Online auction websites use a simple reputation system to help their users to evaluate the trustworthiness of sellers and buyers. However, to improve their reputation in the reputation system, fraudulent users can easily deceive the reputation system by creating fake transactions. This inflated-reputation fraud poses a major problem for online auction websites because it can lead legitimate users into scams. Numerous approaches have been proposed in the literature to address this problem, most of which involve using social network analysis (SNA) to derive critical features (e.g., k-core, center weight, and neighbor diversity) for distinguishing fraudsters from legitimate users. This paper discusses the limitations of these SNA features and proposes a class of SNA features referred to as neighbor-driven attributes (NDAs). The NDAs of users are calculated from the features of their neighbors. Because fraudsters require collusive neighbors to provide them with positive ratings in the reputation system, using NDAs can be helpful for detecting fraudsters. Although the idea of NDAs is not entirely new, experimental results on a real-world dataset showed that using NDAs improves classification accuracy compared with state-of-the-art methods that use the k-core, center weight, and neighbor diversity.

Online auctioning has attracted serious fraud given the huge amount of money involved and anonymity of users. In the auction fraud detection domain, the class imbalance, which means less fraud instances are present in bidding transactions, negatively impacts the classification performance because the latter is biased towards the majority class i.e. normal bidding behavior. The best-designed approach to handle the imbalanced learning problem is data sampling that was found to improve the classification efficiency. In this study, we utilize a hybrid method of data over-sampling and under-sampling to be more effective in addressing the issue of highly imbalanced auction fraud datasets. We deploy a set of well-known binary classifiers to understand how the class imbalance affects the classification results. We choose the most relevant performance metrics to deal with both imbalanced data and fraud bidding data.

2020

Shill Bidding (SB) is a serious auction fraud committed by clever scammers. The challenge in labeling multidimensional SB training data hinders research on SB classification. To safeguard individuals from shill bidders, in this study, we explore Semi-Supervised Classification (SSC), which is the most suitable method for our fraud detection problem since SSC can learn efficiently from a few labeled data. To label a portion of SB data, we propose an anomaly detection method that we combine with hierarchical clustering. We carry out several experiments to determine statistically the minimal sufficient amount of labeled data required to achieve the highest accuracy. We also investigate the misclassified bidders to see where the misclassification occurs. The empirical analysis demonstrates that SSC reduces the laborious effort of labeling SB data.

International Conference on Agents and Artificial Intelligence, ICAART, 2019

Shill Bidding (SB) has been recognized as the predominant online auction fraud and also the most difficult to detect due to its similarity to normal bidding behavior. Previously, we produced a high-quality SB dataset based on actual auctions and effectively labeled the instances into normal or suspicious. To overcome the serious problem of imbalanced SB datasets, in this study, we investigate over-and under-sampling techniques through several instance-based classification algorithms. Thousands of auctions occur in eBay every day, and auction data may be sent continuously to the optimal fraud classifier to detect potential SB activities. Consequently , instance-based classification is appropriate for our particular fraud detection problem. According to the experimental results, incremental classification returns high performance for both over-and under-sampled SB datasets. Still, over-sampling slightly outperforms under-sampling for both normal and suspicious classes across all the classifiers.

Current Approaches in Applied Artificial Intelligence,, 2015

In spite of many advantages of online auctioning, serious frauds menace the auction users’ interests. Today, monitoring auctions for frauds is becoming very crucial. We propose here a generic framework that covers realtime monitoring of multiple live auctions. The monitoring is performed at different auction times depending on fraud types and auction duration. We divide the real-time monitoring functionality into threefold: detecting frauds, reacting to frauds, and updating bidders’ clusters. The first task examines in run-time bidding activities in ongoing auctions by applying fraud detection mechanisms. The second one determines how to react to suspicious activities by taking appropriate run-time actions against the fraudsters and infected auctions. Finally, every time an auction ends, successfully or unsuccessfully, participants’ fraud scores and their clusters are updated dynamically. Through simulated auction data, we conduct an experiment to monitor live auctions for shill bidding. The latter is considered the most severe fraud in online auctions, and the most difficult to detect. More precisely, we monitor each live auction at three time points, and for each of them, we verify the shill patterns that most likely happen.

2019

Online auctions have become one of the most popular and convenient buying and selling media in e-commerce. However, the amount of auction fraud increases with the popu- larity of online auctions. This thesis examines one of the most severe types of auction fraud, referred to as shill bidding, where fake bids are used to arti cially in ate an item's nal price. Shill bidding is strictly prohibited in online auctions because it forces honest bidders to pay more for their products. Researchers have proposed several mechanisms to detect shill bidding once an auction has nished. However, if shill bidding is not detected during an auction, an innocent bidder (i.e., the winner of the auction) can potentially be cheated by the end of the auction. Therefore, it is necessary to detect and verify potential shill bidding in real-time (i.e., while an auction is in progress). This thesis proposes and implements several novel techniques for combating shill bidding in real-time. The e ectiveness...

Electronic Commerce Research and Applications, 2019

Shill bidding is where spurious bids are introduced into an auction to drive up the final price for the seller. This causes legitimate bidders to pay more for the item in order to win the auction. Shill bidding detection becomes more difficult when a seller involves two or more bidders and forms a collusive group to commit price-inflating behaviour. Colluding shill bidders can distribute the work evenly among each other to collectively reduce their chances of being detected. This paper presents a Collusive Shill Bidding Detection algorithm to identify the presence of colluding shill bidders. The algorithm calculates an anomaly score for each bidder and then verifies the anomaly scores to improve the detection accuracy. We use a Local Outlier Factor for calculating the anomaly score for each bidder. We then model the auction network in a Markov Random Field and apply Loopy Belief Propagation for identifying the colluding shill bidders. We implemented the proposed algorithm and applied it on both simulated and commercial auction datasets. Experimental results show that the algorithm is able to potentially detect colluding shill bidders. Comparative analysis on simulated auction datasets shows that the proposed algorithm performs better than two existing published approaches.

Given a large online network of online auction users and their histories of transactions, how can we spot anomalies and auction fraud? This paper describes the design and implementation of NetProbe, a system that we propose for solving this problem. NetProbe models auction users and transactions as a Markov Random Field tuned to detect the suspicious patterns that fraudsters create, and employs a Belief Propagation mechanism to detect likely fraudsters. Our experiments show that NetProbe is both efficient and effective for fraud detection. We report experiments on synthetic graphs with as many as 7,000 nodes and 30,000 edges, where NetProbe was able to spot fraudulent nodes with over 90% precision and recall, within a matter of seconds. We also report experiments on a real dataset crawled from eBay, with nearly 700,000 transactions between more than 66,000 users, where NetProbe was highly effective at unearthing hidden networks of fraudsters, within a realistic response time of about 6 minutes. For scenarios where the underlying data is dynamic in nature, we propose Incremental NetProbe, which is an approximate, but fast, variant of Net-Probe. Our experiments prove that Incremental NetProbe executes nearly doubly fast as compared to NetProbe, while retaining over 99% of its accuracy.

Proceedings of the 20th ACM international conference on Information and knowledge management - CIKM '11, 2011

Online auction and shopping are gaining popularity with the growth of web-based eCommerce. Criminals are also taking advantage of these opportunities to conduct fraudulent activities against honest parties with the purpose of deception and illegal profit. In practice, proactive moderation systems are deployed to detect suspicious events for further inspection by human experts. Motivated by real-world applications in commercial auction sites in Asia, we develop various advanced machine learning techniques in the proactive moderation system. Our proposed system is formulated as optimizing bounded generalized linear models in multi-instance learning problems, with intrinsic bias in selective labeling and massive unlabeled samples. In both offline evaluations and online bucket tests, the proposed system significantly outperforms the rule-based system on various metrics, including area under ROC (AUC), loss rate of labeled frauds and customer complaints. We also show that the metrics of loss rates are more effective than AUC in our cases.

Entropy, 2014

Online auctions attract not only legitimate businesses trying to sell their products but also fraudsters wishing to commit fraudulent transactions. Consequently, fraudster detection is crucial to ensure the continued success of online auctions. This paper proposes an approach to detect fraudsters based on the concept of neighbor diversity. The neighbor diversity of an auction account quantifies the diversity of all traders that have transactions with this account. Based on four different features of each trader (i.e., the number of received ratings, the number of cancelled transactions, k-core, and the joined date), four measurements of neighbor diversity are proposed to discern fraudsters from legitimate traders. An experiment is conducted using data gathered from a real world auction website. The results show that, although the use of neighbor diversity on k-core or on the joined date shows little or no improvement in detecting fraudsters, both the neighbor diversity on the number of received ratings and the neighbor diversity on the number of cancelled transactions improve classification accuracy, compared to the state-of-the-art methods that use k-core and center weight.

Trust is difficult to establish in online auctions since transactions occur among complete strangers. The Internet Fraud Complaint Center shows that auction fraud is the highest rate of crime in online activities. Nowadays, shill bidding is the most severe and persistent fraud for online auction users. Considering the strengths and weaknesses of existing works on , in this paper, we propose a reliable software architecture to secure and protect auction systems from shill bidders for both forward and reverse auctions. More precisely our auction system monitors and detects shill bidding in run-time as well as takes necessary actions against shill bidding .