Adaptive Credit Card Fraud Detection Techniques Based on Feature Selection Method
Credit card fraud is a crucial issue that has been faced by cardholder and card issuing companies for decades. Credit card frauds are performed at two levels, application-level frauds and transaction-level frauds. This paper focus on credit cards fraud detection at application level using features selection methods. In this paper, J48 decision tree, AdaBoost, Random Forest, Naive Bayes, and PART machine learning techniques have been used for detection of financial frauds of a credit card and the performance of these techniques are compared on the basis of the five parameters namely sensitivity, specificity, precision, recall, MCC, and accuracy. A German credit dataset is used to evaluate these machines learning techniques efficiency based on filter and wrapper features selection method. The experiment outcomes show that the prediction accuracy of J48 and PART has been increased after applying filter and wrapper methods. Finally, precision and sensitivity of J48, AdaBoost, and the random forest have been enhanced.
KeywordsCredit card fraud Fraud detection Feature selection Machine learning technique
Sincere thanks to the University Grants Commission (UGC), Delhi, India for providing fellowship to work on a research problem. We also thank USICT, Guru Gobind Singh Indraprastha University, Delhi, India to research ambiance for carrying out research.
- 1.Phua, C., Gayler, R., Lee, V., Smith-Miles, K.: A comprehensive survey of data mining based fraud detection research (2005)Google Scholar
- 2.Jans, M., Lybaert, N., Vanhoof, K.: A framework for internal fraud risk reduction at IT integrating business processes: the IFR framework (2010)Google Scholar
- 3.Department of Justice, Office of Public Affairs. Bank of America to pay $16.65 Billion in Historic Justice Department Settlement for Financial Fraud Leading up to and During the Financial Crisis. August 21, 2014. Last accessed 10 Mar 2018Google Scholar
- 4.Singh, A., Jain A.: Study of cyber attacks on cyber-physical system. In: 3rd International Conference on Advances in Internet of Things and Connected Technologies (ICIoTCT), Springer 26, 27 Mar 2018Google Scholar
- 6.Seeja, KR., Zareapoor, M.: FraudMiner: a novel credit card fraud detection model based on frequent itemset mining. Sci. World J. (2014)Google Scholar
- 8.Panday, P.: Analysis of machine learning techniques (J48 and AdaBoost) for classification. In: 2016 1st India International Conference on Information Processing (IICIP), 12–14 Aug 2016Google Scholar
- 11.Awoyemi, J.O., Adetunmbi, A.O., Oluwadare, S.A.: Credit card fraud detection using machine learning techniques: a comparative analysis. In: 2017 International Conference on Computing Networking and Informatics (ICCNI), pp. 1–9. IEEE (2017)Google Scholar
- 12.Mishra, M. K., Dash, R.: A comparative study of chebyshev functional link artificial neural network, multi-layer perceptron and decision tree for credit card fraud detection. In: 2014 International Conference on Information Technology (ICIT), pp. 228–233. IEEE (2014)Google Scholar
- 13.UCI Repository. https://archive.ics.uci.edu/ml/. Last accessed 3 Mar 2018
- 14.Fadaei Noghani, F., Moattar, M.H.: Ensemble classification and extended feature selection for credit card fraud detection. J. AI Data Min. 5(2), 235–243 (2017)Google Scholar
- 15.Xuan, S., Liu, G., Li, Z.: Random forest for credit card fraud detection. In: 2018 IEEE 15th International Conference on Networking, Sensing, and Control, 27–29 Mar 2018Google Scholar
- 16.Stolfo, S.J., Fan, D.W., Lee, W., Prodromidis, A.L.: Credit card fraud detection using meta-learning: issues and initial results (1999)Google Scholar