Skip to main content
SpringerLink
Log in

Applying MASI Algorithm to Improve the Classification Performance of Imbalanced Data in Fraud Detection

  • Conference paper
  • First Online:
Advanced Computational Methods for Knowledge Engineering (ICCSAMA 2019)

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 1121))

Abstract

Imbalanced data is recognized as one of the most attractive matters to many researches. It is shown by numerous publications on this which is a growing interest. The hardest challenge is the failure of generalizing inductive rules by learning algorithms. such as difficulty in forming good classification on decision boundary over more features but fewer samples and risk of overfitting of the sampling. So many solutions have been applied to deal with these problems. In our article, we propose a novel method called MASI (Moving to Adaptive Samples in Imbalanced) in term of changing majority class samples’ label into minor class samples based on data distribution. This proposed method rebalances the classes before training a model in order to improve the classification performance in imbalanced data. We tested on some unbalanced datasets from data of UCI. The empirical results showed that our method has a significant achievement in Sensitivity and G-mean values than other classification models, such as Random Over-sampling, Random Under-sampling, SMOTE, and Borderline SMOTE in using different machine learning approaches, including SVM, C5.0, and RF.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 129.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Matías, M.D., Federico, D., Juan, M.: Improving electric fraud detection using class imbalance strategies. In: International Conference on Pattern Recognition Applications and Methods (ICPRAM), pp. 135–141 (2012)

    Google Scholar 

  2. Japkowicz, N., Stephen, S.: The class imbalance problem: a systematic study. Intell. Data Anal. 6, 429–449 (2002)

    Article  Google Scholar 

  3. Nistesh, C.V.: Data mining for imbalanced datasets: an overview. In: Data Mining and Knowledge Discovery Handbook, pp. 853–868. Springer, Boston (2005)

    Google Scholar 

  4. Rafiq, M.A., Kok, W.W., Mohd, S.F., Xuequn, W.: Improving fraud prediction with incremental data balancing technique for massive data streams. CoRR, pp. 1–8 (2019)

    Google Scholar 

  5. Fei, W., Xiao-Yuan, J., Shiguang, S., Wangmeng, Z., Jing-Yu, Y.: Multiset feature learning for highly imbalanced data classification. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI), pp. 1583–1589 (2017)

    Google Scholar 

  6. Chao, C., Andy, L., Leo, B.: Using random forest to learn imbalanced data, pp. 1–12. University of California, Berkeley (2004)

    Google Scholar 

  7. Qiang, Y., Xindong, W.: 10 challenging problems in data mining research. Int. J. Inf. Technol. Decis. Mak. 5(4), 597–604 (2006)

    Article  Google Scholar 

  8. Enislay, R., Yailé, C., Rafael, B.: SMOTE-RSB∗: a hybrid preprocessing approach based on oversampling and undersampling for high imbalanced data_sets using SMOTE and rough sets theory. Knowl. Inf. Syst. 33(2), 245–265 (2011)

    Google Scholar 

  9. Dang, T.X., Tran, H.D., Osamu, H., Kenji, S.: SPY: a novel resampling method for improving classification performance in imbalanced data. In: Seventh International Conference on Knowledge and Systems Engineering (KSE), pp. 280–285 (2015)

    Google Scholar 

  10. Yanmin, S., Andrew, W.K., Mohamed, K.S.: Classification of imbalanced data: a review. Int. J. Pattern Recognit. Artif. Intell. 23(4), 687–719 (2009)

    Article  Google Scholar 

  11. Lich, N.T., Thuy, N.T., Toan, N.T.: MASI: moving to adaptive samples in imbalanced credit card dataset for classification. In: International Conference on Innovative Research and Development (ICIRD), pp. 133–137 (2018)

    Google Scholar 

  12. Alireza, P., Majid, K., Alireza, N.: Fraud detection in E-banking by using the hybrid feature selection and evolutionary algorithms. IJCSNS Int. J. Comput. Sci. Netw. Secur. 17(8), 271–279 (2017)

    Google Scholar 

  13. Aastha, B., Rajan, G.: Financial frauds: data mining based detection – a comprehensive survey. Int. J. Comput. Appl. 156(10), 20–28 (2016)

    Google Scholar 

  14. Anuj, S., Prabin, P.K.: A review of financial accounting fraud detection based on data mining techniques. Int. J. Comput. Appl. 39(1), 37–47 (2012)

    Google Scholar 

  15. Kaizhu, H., Haiqin, Y., Irwin, K., Michael, L.: Machine Learning: Modeling Data Locally and Globally. Springer (2008)

    Google Scholar 

  16. Federica, M., Marco, B., Gianfranco, B., Francesca, C.: Peculiar genes selection: a new features selection method to improve classification performances in imbalanced data sets. PLoS ONE 12, 1–18 (2017)

    Google Scholar 

  17. Alberto, F., Salvador, G., Francisco, H.: SMOTE for learning from imbalanced data: progress and challenges, marking the 15-year anniversary. J. Artif. Intell. Res. 61, 863–905 (2018)

    Article  MathSciNet  Google Scholar 

  18. Arnis, K., Sergei, P., Henrihs, G.: Entropy-based classifier enhancement to handle imbalanced class problem. Procedia Comput. Sci. 104, 586–591 (2017)

    Article  Google Scholar 

  19. Haibo, H., Yang, B., Edwardo, G.A., Shutao, L.: ADASYN: adaptive synthetic sampling approach for imbalanced learning. In: IEEE International Joint Conference on Neural Networks, pp. 1322–1328 (2008)

    Google Scholar 

  20. Nitesh, C.V., Kevin, B.W., Lawrence, H.O., Philip, K.W.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)

    Article  Google Scholar 

  21. Ivan, T.: Two modifications of CNN. Trans. Syst. Man Commun. 6(11), 769–772 (1976)

    MathSciNet  MATH  Google Scholar 

  22. Masoumeh, Z., Pourya, S.: Application of credit card fraud detection: based on bagging ensemble classifier. In: International Conference on Computer, Communication and Convergence (ICCC), vol. 48, pp. 679–685 (2015)

    Google Scholar 

  23. Sheng, G., Min, C., Hsin, Y.H., Shu, C.C., Mei, S.L., Chengde, Z.: Deep learning with MCA-based instance selection and bootstrapping for imbalanced data classification. In: IEEE Conference on Collaboration and Internet Computing (CIC), pp. 288–295 (2015)

    Google Scholar 

  24. Reshma, D.K., Banait, S.: Imbalanced time series data classification using oversampling technique. Int. J. Electron. Commun. Soft Comput. Sci. Eng. 75–80 (2015). ISSN 2277-947

    Google Scholar 

  25. Mousa, A.: Detecting financial fraud using data mining techniques: a decade review from 2004 to 2015. J. Data Sci. 14, 553–570 (2016)

    Google Scholar 

  26. Adrian, B.: Detecting and preventing fraud with data analytics. Procedia Econ. Financ. 32, 1827–1836 (2015)

    Article  Google Scholar 

  27. Yiyang, B., Min, C., Chen, Y., Yuan, Y., Qing, L., Leon, Z., Liang, L.: Financial fraud detection: a new ensemble learning approach for imbalanced data. In: Pacifc Asia Conference on Information Systems (PACIS), pp. 315–326 (2016)

    Google Scholar 

  28. Rafiq, M.A., Kok, W.W., Mohd, S.F., Xuequn, W.: Scalable machine learning techniques for highly imbalanced credit card fraud detection: a comparative study. In: Pacific Rim International Conference on Artificial Intelligence (PRICAI), pp. 237–246 (2018)

    Google Scholar 

  29. Mario, A., Firas, M., Elli, A., Stefan, S., Andreas, M.: The random forest classifier in weka: discussion and new developments for imbalanced data. Comput. Vis. Pattern Recognit. 1–6 (2019)

    Google Scholar 

  30. Ludmila, K.I., Álvar, A.-G., José-Francisco, D.-P., Iain, G.A.D.: Instance selection improves geometric mean accuracy: a study on imbalanced data classification. Prog. Artif. Intell. 8, 215–228 (2018)

    Google Scholar 

  31. Ila, D., Shantanu, D., Bijan, R.: Detecting financial restatements using data mining techniques. Expert Syst. Appl. 93, 374–393 (2017)

    Google Scholar 

  32. Leila, G., Mohammad, T.J.: Survey of detecting fraud in automobile insurance using data mining techniques. Int. J. Comput. Inf. Technol. (IJOCIT) 4(4), 111–125 (2016)

    Google Scholar 

  33. Maciej, M.A., Piotr, H.A., Jacek, Z.M., Joseph, L.Y., Jay, B.A.: Training neural network classifiers for medical decision making: the effects of imbalanced datasets on classification performance. Neural Netw. 21, 427–436 (2008)

    Article  Google Scholar 

  34. Masoumeh, Z., Pourya, S., Deepak, J.K., Haoxiang, W.: Kernelized support vector machine with deep learning: an efficient approach for extreme multiclass dataset. Pattern Recognit. Lett. 115, 4–13 (2018)

    Article  Google Scholar 

  35. Wei-Chao, L., Shih-Wen, K., Chih-Fong, T.: Top 10 data mining techniques in business applications: a brief survey. Kybernetes 46(7), 1158–1170 (2017)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Thuongmai University, 79 Ho Tung Mau, Hanoi, Vietnam

    Thi-Lich Nghiem

  2. LyNhanTong High School, Bacninh, Vietnam

    Thi-Toan Nghiem

Authors
  1. Thi-Lich Nghiem
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Thi-Toan Nghiem
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Thi-Lich Nghiem .

Editor information

Editors and Affiliations

  1. Computer Science and Applications Department LGIPM, University of Lorraine, Metz Cedex 03, France

    Hoai An Le Thi

  2. Computer Science and Applications Department LGIPM, University of Lorraine, Metz Cedex 03, France

    Hoai Minh Le

  3. Laboratory of Mathematics, National Institute for Applied Sciences, Saint-Étienne-du-Rouvray Cedex, France

    Tao Pham Dinh

  4. Department of Information Systems, Wroclaw University of Science and Technology, Wrocław, Poland

    Ngoc Thanh Nguyen

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Nghiem, TL., Nghiem, TT. (2020). Applying MASI Algorithm to Improve the Classification Performance of Imbalanced Data in Fraud Detection. In: Le Thi, H., Le, H., Pham Dinh, T., Nguyen, N. (eds) Advanced Computational Methods for Knowledge Engineering. ICCSAMA 2019. Advances in Intelligent Systems and Computing, vol 1121. Springer, Cham. https://doi.org/10.1007/978-3-030-38364-0_14

Download citation

Publish with us

Policies and ethics

Search

Navigation