Browse > Article
http://dx.doi.org/10.5391/JKIIS.2005.15.5.545

Cost-sensitive Learning for Credit Card Fraud Detection  

Park Lae-Jeong (Department of Electronics Engineering Kangnung National University)
Publication Information
Journal of the Korean Institute of Intelligent Systems / v.15, no.5, 2005 , pp. 545-551 More about this Journal
Abstract
The main objective of fraud detection is to minimize costs or losses that are incurred due to fraudulent transactions. Because of the problem's nature such as highly skewed, overlapping class distribution and non-uniform misclassification costs, it is, however, practically difficult to generate a classifier that is near-optimal in terms of classification costs at a desired operating range of rejection rates. This paper defines a performance measure that reflects classifier's costs at a specific operating range and offers a cost-sensitive learning approach that enables us to train classifiers suitable for real-world credit card fraud detection by directly optimizing the performance measure with evolutionary programming. The experimental results demonstrate that the proposed approach provides an effective way of training cost-sensitive classifiers for successful fraud detection, compared to other training methods.
Keywords
fraud detection; cost-sensitive learning; classifier evaluation;
Citations & Related Records
연도 인용수 순위
  • Reference
1 R. J. Bolton and D. J. Hand, 'Statistical fraud detection: A review,' Statistical Science, vol. 17, no. 3, pp. 235-255, 2002   DOI   ScienceOn
2 박래정, '신용카드 사기 검출을 위한 신경망 분류기의 진화 학습', 퍼지및지능시스템학회 논문지. vol. 11, no. 5, pp. 400-405, 2001
3 M. Weatherford, 'Mining for fraud,' IEEE Intelligence Systems, July/August Issue, pp. 4-6, 2002
4 L.-J. Park, S.-A. Kim, H.-J. Cho, T-S. Kim, and B.-H. Wang, 'A credit card fraud detection system based on hybrid of neural networks and decision tree,' Proc. of the Korea- U.S. Science and Technology Symposium, 1998
5 D. B. Fogel, Evolutionary computation: Toward a new philosophy of machine intelligence, Wiley-IEEE press, 1999
6 P. K. Chan, W. Fan, A. L. Prodromidis, and S. J. Stolfo, 'Distributed data mining in credit card fraud detection,' IEEE Intelligent Systems, vol. 14, no. 6, pp. 67-74, 1999   DOI   ScienceOn
7 F. Provost and T. Fawcett, 'Analysis and visualization of classifier performance: Comparison under imprecise class and cost distributions,' Proc. of Int'l Conf. Knowledge Discovery and Data Mining, pp. 43-48, 1997
8 C. Phua, D. Alahakoon, and V. Lee, 'Minority report in fraud detection: classification of skewed data,' Sigkdd explorations, vol. 6, no. 1, pp. 50-59, 2004   DOI
9 J. R. Dorronsoro, F. Ginel, C. Sanchez, and C. S. Cruz, 'Neural fraud detection in credit card operations,' IEEE Trans. on Neural Networks, vol. 8, no. 4, pp. 827-834, 1997   DOI   ScienceOn
10 X. Yao, 'Evolving artificial neural networks,' Proceedings of the IEEE, vol. 87, no. 9, pp. 1423-1447, 1999
11 C. Drummond and R. C. Holte, 'What ROC curves can't do (and cost curves can),' Proc. of ECAI's 2004 Workshop on ROC Analysis in AI, 2004
12 R. Brause, T. Langsdorf, and M. Hepp, 'Neural data mining for credit card fraud detection,' Proc. of 11th IEEE Int'l Conf. on Tools with Artificial Intelligence, pp. 103-106, 1999
13 A. P. Bradley, 'The use of the area under the ROC curve in the evaluation of machine learning algorithms,' vol. 30, no. 7. pp. 1145-1159, Pattern Recognition, 1997   DOI   ScienceOn
14 W. Fan, S. J. Stolfo, K. Zhang, and P. K. Chan, 'AdaCost, Misclassification cost-sensitive boosting,' Proc. of 16th Ini'l Conf. Machine Learning, pp. 97-105, 1999
15 S. Maes, K. Tuyls, B. Van schoen winkel, and B. Manderick, 'Credit card fraud detection using Bayesian and neural networks,' Proc. of the 1st Int'l NAISO Congress on Neuro Fuzzy Technologies, 2002