以模型融合為基礎之線上拍賣詐騙偵測

Online Auction Fraud Detection based on Model Fusion

張昭憲(Jau-Shien Chang)；陳世軒(Shih-Hsuan Chen)

詐騙偵測 ； 模型融合 ； 分類 ； 線上拍賣 ； 電子商務 ； Fraud detection ； model fusion ； classification ； online auctions ； e-commerce

資訊管理學報

28卷4期（2021 / 10 / 31）

419 - 444

繁體中文

隨著金流與物流等基礎建設的成熟，電子商務的蓬勃發展有目共睹，而線上拍賣更是其中重要的一環。面對日益龐大交易金額，也引起不肖人士的覬覦，在拍賣平台中進行詐騙。有關線上拍賣詐騙偵測，已有許多方法已被提出，但對於日新月異的詐騙手法，其準確率仍有待提升。有鑑於此，本研究將運用模型融合（Model Fusion）概念，發展更有效的詐騙偵測方法。首先，我們分析單一模型應用在不同測試集之效能，發現當詐騙者與正常者比例未知時，單一模型的效能將受到限制。其次，本研究利用不同類型配比之訓練資料，探討如何產生有利於詐騙者與正常者之偵測模型。最後，運用多種不同特質之模型，分別以多階連續過濾及平衡過濾方式加以整合，以提升總體偵測效能。為驗證提出方法之有效性，我們採用Yahoo!拍賣實際交易資料進行實驗。與各種單一偵測模型相較，本研究提出之連續過濾與平衡過濾法確能提升準確率，並提供更穩定的偵測結果。當使用連續過濾時，除獲得較高準確率外，也能對各階段之偵測精度進行分析，提升結果之實用性。此外，雖然模型融合時嘗試使用各種不同特質的單一模型可影響準確性，但我們發現在多階段過濾的流程下，對偵測效能之影響有限。由上述結果可知，本研究提出方法確有助於改善詐騙偵測之準確率，提供消費者更周全的交易防護。

With the maturity of infrastructure such as cash flow and logistics, the booming development of e-commerce is obvious to all. However, facing such a large transaction amount, it also attracts many fraudsters to join e-commerce. Among the reported cases, online auction fraud undoubtedly forms a large proportion. Although a lot of detection methods have been proposed, the detection accuracy for the ever-changing fraud scheme still needs to be improved. To solve this problem, this study adopts the model fusion concept to develop more effective fraud detection methods. First, we analyzed the effectiveness of a single model in different test sets, and found that when the ratio of fraudsters to non-fraudsters is unknown, it is difficult for a single model to be effective. Secondly, this study uses different types of training data to explore how to generate a detection model that is beneficial to fraudsters and normal traders. Finally, a variety of models with different characteristics are used to integrate multi-stage successive filtering and balanced filtering to improve the overall performance. To verify the effectiveness of the proposed method, we use Yahoo! auction transaction data to conduct experiments. Compared with single detection models, the successive filtering and balanced filtering can improve the detection accuracy and provide more stable results. When using successive filtering, the precision of each stage can also be analyzed to enhance the practicability of the results. In addition, we found that changing the characteristics of each single model has a limited impact on the performance of the multi-stage filtering process. In summary, the proposed method can actually help improve the accuracy of fraud detection and provide a safer trading environment.

1. Ahmed, M.,Mahmood, A. N.,Islam, M. R.(2016).A survey of anomaly detection techniques in financial domain.Future Generation Computer Systems,55,278-288.
2. Alford M.(2013).Intelligent fraud detection: a comparison of neural and Bayesian methods.Computer Fraud & Security,14-16.
3. Amrehn, M.,Mualla, F.,Angelopoulou, E.,Steidl, S.,Maier, A.(2018).,未出版
4. Chang, J. S.,Chang, W. H.(2009).An early fraud detection mechanism for online auctions based on phased modeling.Proceedings of the 2009 International Workshop on Mobile Systems E-Commerce and Agent Technology,Taipei, Taiwan:
5. Chang, J. S.,Liu, Y. H.,Lee, C. F.(2020).Developing Effective Fraud Detection Methods for Online Auction.TANET 2020 臺灣網際網路研討會
6. Chang, W. H.,Chang, J. S.(2011).A novel two-stage phased modeling framework for early fraud detection in online auctions.Expert Systems with Applications,38,11244-11260.
7. Chang, W. H.,Chang, J. S.(2012).An effective early fraud detection method for online auctions.Electronic Commerce Research and Applications,11(4),346-360.
8. Chau, D. H.,Faloutsos, C.(2005).Fraud detection in electronic auction.Proceedings of European Web Mining Forum at ECML/PKDD 2005
9. Chau, D. H.,Pandit, S.,Faloutsos, C.(2006).Detecting fraudulent personalities in networks of online auctioneers.Proceedings of PKDD 2006
10. Chen, C.,Zhu, Q.,Lin, L.,Shyu M. L.(2013).Web Media Semantic Concept Retrieval via Tag Removal and Model Fusion.ACM Transactions on Intelligent Systems and Technology,4(4),1-22.
11. Chen, J.,Tao, Y.,Wang, H.,Chen, T.(2015).Big Data based fraud risk management at Alibaba.The Journal of Finance and Data Science,1(1),1-10.
12. Darudi, A.,Bashari, M.,Javidi, H.(2015).Electricity price forecasting using a new data fusion algorithm.IET Generation, Transmission & Distribution,2015(9),1382-1390.
13. eMarketer (2020). Retail & Ecommerce report. Retrieved on Mar. 1, 2020, https://www.emarketer.com/topics/topic/retail-ecommerce.
14. Gavish, B.,Tucci, C.(2008).Reducing Internet Auction Fraud.Communications of the ACM,51(5),89-97.
15. Goes, P. B.,Tu, Y.,Tung, A.(2009).Online Auctions Hidden Metrics.Communications of the ACM,52(4),147-149.
16. Huang, S.,Ma, J.,Cheng, P.,Wang, S.(2015).A Hybrid Multigroup Co-clustering Recommendation Framework Based on Information Fusion.ACM Transactions on Intelligent Systems and Technology,6(2),1-22.
17. Kim, K.,Choi, Y.,Park, J.(2013).Price fraud detection in online shopping malls using a finite mixture model.Electronic Commerce Research and Applications,12,195-207.
18. Kumar, M. S.,Soundarya, V.,Kavitha, S.,Keerthika, E.S.,Aswini, E.(2019).Credit Card Fraud Detection Using Random Forest Algorithm.Proceedings of IEEE 3rd International Conference on Computing and Communication Technologies (ICCCT)
19. Li, S. H.,Yen, D. C.,Lu, W. H.,Wang, C.(2012).Identifying the signs of fraudulent accounts using data mining techniques.Computers in Human Behavior,28,1002-1013.
20. Makki, S.,Assaghir, Z.,Taher, Y.,Haque, R.,Hacid, M.-S.,Makki H. Z.(2019).An Experimental Study with Imbalanced Classification Approaches for Credit Card Fraud Detection.IEEE Access,7,93010-93022.
21. National White Collar Crime Center (NW3C) (2019, March 1). 2019 Internet Crime Report. https://pdf.ic3.gov/2019_IC3Report.pdf
22. Pandit, S.,Chau, D.H.,Wang, S.,Faloutsos, C.(2007).Netprobe: a fast and scalable system for fraud detection in online auction networks.Proceedings of the 16th international conference on World Wide Web
23. Tsang, S.,Koh, Y.-S.,Dobbie, G.,Alam, S.(2014).SPAN: Finding collaborative frauds in online auctions.Knowledge-based systems,71,389-408.
24. West, J.,Bhattacharya, M.(2016).Intelligent financial fraud detection: A comprehensive review.Computer & Security,57,47-66.
25. Xuan, S.,Liu, G.,Li, Z.,Zheng, L.(2018).Random Forest for Credit Card Fraud Detection.Proceedings of IEEE 15th International Conference on Networking, Sensing and Control (ICNSC)
26. 鄭孝儒(2010)。新北市，淡江大學資訊管理研究所。