Online Detection of Shill Bidding Fraud Based on Machine Learning Techniques

Ganguly, Swati; Sadaoui, Samira

doi:10.1007/978-3-319-92058-0_29

Cited by 16 publications

(17 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To facilitate the labeling of our SB dataset, we first utilized hierarchical clustering to group participants with similar bidding behavior, as well as direct and statistical testing methods to find out about the optimal number of clusters. After grouping the bidders, we applied the labeling strategy introduced in [14] to determine whether the bidders in a given cluster were behaving normally or suspiciously. However, the labeled SB training dataset is imbalanced, which poses a challenge because the classifiers have difficulty learning from such datasets.…”

Section: Contributionsmentioning

confidence: 99%

“…Recently, an SVM-based SB detection model has been developed in [14] that overcome the issues of ANN and HMM.…”

Section: Related Workmentioning

confidence: 99%

“…Since the class imbalance is a serious fact in fraud detection problems, the authors applied three data sampling methods (SMOTE, SpreadSubSample, and hybrid of both). Our ultimate goal is to greatly increase the predictive performance results of [14] by using a more advanced and robust preprocessing and classification process. The differences between [14] and the present study are in terms of the training datasets, clustering, sampling and classification approaches, and classification results.…”

Section: Related Workmentioning

confidence: 99%

“…Our ultimate goal is to greatly increase the predictive performance results of [14] by using a more advanced and robust preprocessing and classification process. The differences between [14] and the present study are in terms of the training datasets, clustering, sampling and classification approaches, and classification results. In [14], the authors used an available dataset containing 149 PDA auctions.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Detection of Auction Fraud in Commercial Sites

Anowar

Sadaoui

2020

J. theor. appl. electron. commer. res.

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Contributionsmentioning

confidence: 99%

“…Recently, an SVM-based SB detection model has been developed in [14] that overcome the issues of ANN and HMM.…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Detection of Auction Fraud in Commercial Sites

Anowar

Sadaoui

2020

J. theor. appl. electron. commer. res.

Self Cite

View full text Add to dashboard Cite

show abstract

“…CURE [3] has been proved over the years to be a very efficient clustering method for large-scale training datasets in terms of the cluster quality and outlier elimination. Hierarchical clustering has been practiced successfully in numerous fraud studies [4], [5]. The resulting labeled SB dataset can be employed by the state-of-the-art classification methods.…”

Section: Introductionmentioning

confidence: 99%

Clustering and Labeling Auction Fraud Data

Alzahrani

Sadaoui

2019

Data Management, Analytics and Innovation

Self Cite

View full text Add to dashboard Cite

Although shill bidding is a common auction fraud, it is however very tough to detect. Due to the unavailability and lack of training data, in this study, we build a high-quality labeled shill bidding dataset based on recently collected auctions from eBay. Labeling shill biding instances with multidimensional features is a critical phase for the fraud classification task. For this purpose, we introduce a new approach to systematically label the fraud data with the help of the hierarchical clustering CURE that returns remarkable results as illustrated in the experiments.

show abstract

Multi-class Ensemble Learning of Imbalanced Bidding Fraud Data

Anowar

Sadaoui

2019

Advances in Artificial Intelligence

View full text Add to dashboard Cite

Online Detection of Shill Bidding Fraud Based on Machine Learning Techniques

Cited by 16 publications

References 18 publications

Detection of Auction Fraud in Commercial Sites

Detection of Auction Fraud in Commercial Sites

Clustering and Labeling Auction Fraud Data

Multi-class Ensemble Learning of Imbalanced Bidding Fraud Data

Contact Info

Product

Resources

About