Session-Based Fraud Detection in Online E-Commerce Transactions Using Recurrent Neural Networks

  • Shuhao WangEmail author
  • Cancheng Liu
  • Xiang Gao
  • Hongtao Qu
  • Wei Xu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10536)


Transaction frauds impose serious threats onto e-commerce. We present CLUE, a novel deep-learning-based transaction fraud detection system we design and deploy at, one of the largest e-commerce platforms in China with over 220 million active users. CLUE captures detailed information on users’ click actions using neural-network based embedding, and models sequences of such clicks using the recurrent neural network. Furthermore, CLUE provides application-specific design optimizations including imbalanced learning, real-time detection, and incremental model update. Using real production data for over eight months, we show that CLUE achieves over 3x improvement over the existing fraud detection approaches.


Fraud detection Web mining Recurrent neural network 



We would like to thank our colleagues at JD for their help during this research. This research is supported in part by the National Natural Science Foundation of China (NSFC) grant 61532001, Tsinghua Initiative Research Program Grant 20151080475, MOE Online Education Research Center (Quantong Fund) grant 2017ZD203, and gift funds from Huawei.


  1. 1.
    Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., et al.: TensorFlow: large-scale machine learning on heterogeneous distributed systems. arXiv:1603.04467 (2016)
  2. 2.
    Abdallah, A., Maarof, M.A., Zainal, A.: Fraud detection system: a survey. J. Netw. Comput. Appl. 68, 90–113 (2016)CrossRefGoogle Scholar
  3. 3.
    Barkan, O., Koenigstein, N.: Item2Vec: neural item embedding for collaborative filtering. In: IEEE 26th International Workshop on Machine Learning for Signal Processing, pp. 1–6. IEEE (2016)Google Scholar
  4. 4.
    Bellinger, C., Drummond, C., Japkowicz, N.: Beyond the boundaries of SMOTE. In: Frasconi, P., Landwehr, N., Manco, G., Vreeken, J. (eds.) ECML PKDD 2016. LNCS (LNAI), vol. 9851, pp. 248–263. Springer, Cham (2016). CrossRefGoogle Scholar
  5. 5.
    Bianchi, C., Andrews, L.: Risk, trust, and consumer online purchasing behaviour: a chilean perspective. Int. Mark. Rev. 29(3), 253–275 (2012)CrossRefGoogle Scholar
  6. 6.
    Carminati, M., Caron, R., Maggi, F., Zanero, S., Epifani, I.: BankSealer: a decision support system for online banking fraud analysis and investigation. Comput. Secur. 53, 175–186 (2015)CrossRefGoogle Scholar
  7. 7.
    Cheng, H.T., Koc, L., Harmsen, J., Shaked, T., Chandra, T., Aradhye, H., Anderson, G., Corrado, G., Chai, W., Ispir, M., et al.: Wide & deep learning for recommender systems. In: Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, pp. 7–10. ACM (2016)Google Scholar
  8. 8.
    Fu, K., Cheng, D., Tu, Y., Zhang, L.: Credit card fraud detection using convolutional neural networks. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds.) ICONIP 2016. LNCS, vol. 9949, pp. 483–490. Springer, Cham (2016). CrossRefGoogle Scholar
  9. 9.
    Glover, S., Benbasat, I.: A comprehensive model of perceived risk of e-commerce transactions. Int. J. Electron. Commer. 15(2), 47–78 (2010)CrossRefGoogle Scholar
  10. 10.
    He, H., Garcia, E.A.: Learning from imbalanced data. IEEE Trans. Knowl. Data Eng. 21(9), 1263–1284 (2009)CrossRefGoogle Scholar
  11. 11.
    Hidasi, B., Quadrana, M., Karatzoglou, A., Tikk, D.: Parallel recurrent neural network architectures for feature-rich session-based recommendations. In: Proceedings of the 10th ACM Conference on Recommender Systems, pp. 241–248 (2016)Google Scholar
  12. 12.
    Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv:1412.6980 (2014)
  13. 13.
    Lim, W.Y., Sachan, A., Thing, V.: Conditional weighted transaction aggregation for credit card fraud detection. Adv. Inf. Commun. Technol. 433, 3–16 (2014)Google Scholar
  14. 14.
    Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)Google Scholar
  15. 15.
    Phua, C., Alahakoon, D., Lee, V.: Minority report in fraud detection: classification of skewed data. ACM SIGKDD Explor. Newslett. 6(1), 50–59 (2004)CrossRefGoogle Scholar
  16. 16.
    Sheng, V.S., Ling, C.X.: Thresholding for making classifiers cost-sensitive. In: National Conference on Artificial Intelligence, pp. 476–481 (2006)Google Scholar
  17. 17.
    Shi, Y., Sun, C., Li, Q., Cui, L., Yu, H., Miao, C.: A fraud resilient medical insurance claim system. In: Thirtieth AAAI Conference, pp. 4393–4394 (2016)Google Scholar
  18. 18.
    Tan, Y.K., Xu, X., Liu, Y.: Improved recurrent neural networks for session-based recommendations. In: Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, pp. 17–22. ACM (2016)Google Scholar
  19. 19.
    Tian, T., Zhu, J., Xia, F., Zhuang, X., Zhang, T.: Crowd fraud detection in internet advertising. In: International Conference on World Wide Web, pp. 1100–1110 (2015)Google Scholar
  20. 20.
    Tseng, V.S., Ying, J.C., Huang, C.W., Kao, Y., Chen, K.T.: FrauDetector: a graph-mining-based framework for fraudulent phone call detection. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 2157–2166 (2015)Google Scholar
  21. 21.
    Wu, S., Ren, W., Yu, C., Chen, G., Zhang, D., Zhu, J.: Personal recommendation using deep recurrent neural networks in NetEase. In: International Conference on Data Engineering, pp. 1218–1229 (2016)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Shuhao Wang
    • 1
    Email author
  • Cancheng Liu
    • 2
  • Xiang Gao
    • 2
  • Hongtao Qu
    • 2
  • Wei Xu
    • 1
  1. 1.Tsinghua UniversityBeijingChina
  2. 2.JD FinanceBeijingChina

Personalised recommendations