Application of SIRUS in Credit Card Fraud Detection

  • Yuwei Zhang
  • Guanjun LiuEmail author
  • Wenjing Luan
  • Chungang Yan
  • Changjun Jiang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11280)


Credit card fraud problem is very common in recent years. It not only causes economic loss to people, but also causes trust crisis to enterprises. Due to the imbalance of data, fraud detection has always been tricky. In our previous work, we proposed a method of dealing with the class imbalance problem based on stacking ensemble learning and inverse random undersampling method (SIRUS). First, the inverse random undersampling method is used to generate multiple data subsets from the original data set. Then we use the stacking ensemble learning method for each data subset to train several different learners (also called first-level learners), and then the results generated by each first-level learner are taken as features to train a meta learner. We apply SIRUS to detect the credit card fraud in this paper. Our dataset comes from a financial company in China. A variety of measurements such as recall, precision, accuracy, F-measure, and G-mean to illustrate the effectiveness of our method in fraud detection.


Fraud detection Stacking Inverse random undersampling Class imbalance problem 


  1. 1.
    Srivastava, A., et al.: Credit card fraud detection using Hidden Markov Model. IEEE Trans. Dependable Secur. Comput. 5(1), 37–48 (2008)CrossRefGoogle Scholar
  2. 2.
    Bahnsen, A.C., Aouada, D., Stojanovic, A.: Feature engineering strategies for credit card fraud detection. Expert Syst. Appl. Int. J. 51(C), 134–142 (2016)Google Scholar
  3. 3.
    Albrecht, W.S., Albrecht, C., Albrecht, C.C.: Current trends in fraud and its detection. Inf. Syst. Secur. 17(1), 2–12 (2008)zbMATHGoogle Scholar
  4. 4.
    Yong-Hua, X.U.: Detection of credit card fraud based on support vector machine. Comput. Simul. 28(8), 371–376 (2011)Google Scholar
  5. 5.
    Whitrow, C., et al.: Transaction aggregation as a strategy for credit card fraud detection. Data Min. Knowl. Disc. 18(1), 30–55 (2009)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Kou, Y., et al.: Survey of fraud detection techniques. In: IEEE International Conference on Networking, Sensing and Control IEEE, vol. 2, 749–754 (2004)Google Scholar
  7. 7.
    Khoshgoftaar, T.M., et al.: Learning with limited minority class data. In: International Conference on Machine Learning and Applications, pp. 348–353. IEEE (2007)Google Scholar
  8. 8.
    Tahir, M.A., Kittler, J., Yan, F.: Inverse random under sampling for class imbalance problem and its application to multi-label classification. Pattern Recogn. 45(10), pp. 3738–3750 (2012)CrossRefGoogle Scholar
  9. 9.
    Breiman, L.: Bagging predictors. Mach. Learn. 24(2), 123–140 (1996)MathSciNetzbMATHGoogle Scholar
  10. 10.
    Kittler, J., et al.: On combining classifiers. IEEE Trans. Pattern Anal. Mach. Intell. 20(3), 226–239 (1998)CrossRefGoogle Scholar
  11. 11.
    Wolpert, D.H.: Stacked generalization *. Neural Netw. 5(2), 241–259 (1992)CrossRefGoogle Scholar
  12. 12.
    Zhang, Y., Liu, G., Luan, W., Yan, C., Jiang, C.: An approach to class imbalance problem based on stacking and inverse random under sampling methods, pp. 1–6 (2018).
  13. 13.
    Bhattacharyya, S., et al.: Data mining for credit card fraud: a comparative study. Decis. Support. Syst. 50(3), 602–613 (2011)CrossRefGoogle Scholar
  14. 14.
    Abbasi, A., et al.: Metafraud: a meta-learning framework for detecting financial fraud. MIS Q. 36(4), 1293–1327 (2012)CrossRefGoogle Scholar
  15. 15.
    He, H., Garcia, E.A.: Learning from imbalanced data. IEEE Trans. Knowl. Data Eng. 21(9), 1263–1284 (2009)CrossRefGoogle Scholar
  16. 16.
    Tomek, I.: Two modifications of CNN. IEEE Trans. Syst. Man Cybern. SMC 6(11), 769–772 (1976)Google Scholar
  17. 17.
    Chawla, N.V., et al.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16(1), 321–357 (2002)CrossRefGoogle Scholar
  18. 18.
    Han, H., Wang, W.-Y., Mao, B.-H.: Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning. In: Huang, D.-S., Zhang, X.-P., Huang, G.-B. (eds.) ICIC 2005. LNCS, vol. 3644, pp. 878–887. Springer, Heidelberg (2005). Scholar
  19. 19.
    Weiss, G.M.: Mining with rarity: a unifying framework. ACM SIGKDD Explor. Newslett. 6(1), 7–19 (2004)CrossRefGoogle Scholar
  20. 20.
    Freund, Y., Schapire, R.E.: A desicion-theoretic generalization of on-line learning and an application to boosting. In: Vitányi, P. (ed.) EuroCOLT 1995. LNCS, vol. 904, pp. 23–37. Springer, Heidelberg (1995). Scholar
  21. 21.
    Nanni, L., Lumini, A.: FuzzyBagging: a novel ensemble of classifiers. Pattern Recogn. 39(3), 488–490 (2006)CrossRefGoogle Scholar
  22. 22.
    Zhang, P.B., Yang, Z.X.: A Novel AdaBoost framework with robust threshold and structural optimization. IEEE Trans. Cybern. PP(99), 1–13 (2016)Google Scholar
  23. 23.
    Zhou, Z.H.: Ensemble Methods: Foundations and Algorithms. Taylor & Francis (2012)Google Scholar
  24. 24.
    Hall, M., et al.: The WEKA data mining software: an update. ACM SIGKDD Explor. Newslett. 11(1), 10–18 (2009)CrossRefGoogle Scholar
  25. 25.
    Chan, P.K., Stolfo, S.J.: Toward scalable learning with non-uniform class and cost distributions: a case study in credit card fraud detection. In: International Conference on Knowledge Discovery and Data Mining AAAI Press, pp. 164–168 (1998)Google Scholar
  26. 26.
    Wang, B.X., Japkowicz, N.: Imbalanced Data Set Learning with Synthetic Examples. IRIS Machine Learning Workshop, N.p. (2004). PrintGoogle Scholar
  27. 27.
    Galar, M., et al.: A review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid-based approaches. IEEE Trans. Syst. Man Cybern. Part C Appl. Rev. 42(4), 463–484 (2012)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Yuwei Zhang
    • 1
    • 2
  • Guanjun Liu
    • 1
    • 2
    Email author
  • Wenjing Luan
    • 1
    • 2
  • Chungang Yan
    • 1
    • 2
  • Changjun Jiang
    • 1
    • 2
  1. 1.Department of Computer Science and TechnologyTongji UniversityShanghaiChina
  2. 2.Key Laboratory of Embedded System and Service ComputingMinistry of EducationShanghaiChina

Personalised recommendations