Credit fraud is a broad term associated with theft or fraudulent transactions that involve the usage of a credit card. The fraud detection systems today are only capable of preventing one-twelfth of one percent of all transactions processed, which still results in huge losses. To the human eye, fraudulent transactions are indistinguishable from real ones. However, there are underlying patterns common to these transactions that can be recognized by machine learning algorithms. In this paper, we have trained supervised learning models on a dataset containing more than 280,000 transactions. We go on to evaluate the performance of each of these models on the dataset in terms of accuracy and precision and compare them with each other. With this, we show that the Random Forest model shows promising results for identifying credit fraud when trained on a labelled dataset.

Machine Learning, Supervised Learning, Fraud Detection, Random Forest, Regression, Classifier

[1] F. Misarwala, K. Mukadam, K. Bhowmick, "Applications of Data Mining in Fraud Detection", International Journal of Computer Sciences and Engineering, Vol.3, Issue.11, pp.45-53, 2015.
[2] D. Sathiya, S. V. Evangelin Sonia, “A Comparative Study of Supervised Machine Learning Algorithm”, International Journal of Computer Sciences and Engineering, Vol.6, Issue.12, pp.875-878, 2018.
[3] Shen, A., Tong, R. and Deng, Y., 2007, June. Application of classification models on credit card fraud detection. In 2007 International conference on service systems and service management (pp. 1-4). IEEE.
[4] West, J. and Bhattacharya, M., 2016. Intelligent financial fraud detection: a comprehensive review. Computers & security, 57, pp.47-66.
[5] Chaudhary, K., Yadav, J. and Mallick, B., 2012. A review of fraud detection techniques: Credit card. International Journal of Computer Applications, 45(1), pp.39-44.
[6] Şahin, Y.G. and Duman, E., 2011. Detecting credit card fraud by decision trees and support vector machines.
[7] Sahin, Y., Bulkan, S. and Duman, E., 2013. A cost-sensitive decision tree approach for fraud detection. Expert Systems with Applications, 40(15), pp.5916-5923.
[8] Gadi, M.F.A., Wang, X. and do Lago, A.P., 2008, August. Credit card fraud detection with artificial immune system. In International Conference on Artificial Immune Systems (pp. 119-131). Springer, Berlin, Heidelberg.
[9] Raj, S.B.E. and Portia, A.A., 2011, March. Analysis on credit card fraud detection methods. In 2011 International Conference on Computer, Communication and Electrical Technology (ICCCET) (pp. 152-156). IEEE.
[10] Zareapoor, M. and Shamsolmoali, P., 2015. Application of credit card fraud detection: Based on bagging ensemble classifier. Procedia computer science, 48(2015), pp.679-685.
[11] Niimi, A., 2015, October. Deep learning for credit card data analysis. In 2015 World Congress on Internet Security (WorldCIS) (pp. 73-77). IEEE.
[12] Akila, S. and Reddy, U.S., 2017, November. Risk based bagged ensemble (RBE) for credit card fraud detection. In 2017 International Conference on Inventive Computing and Informatics (ICICI) (pp. 670-674). IEEE.
[13] Adewumi, A.O. and Akinyelu, A.A., 2017. A survey of machine-learning and nature-inspired based credit card fraud detection techniques. International Journal of System Assurance Engineering and Management, 8(2), pp.937-953.
[14] Tabassum, N. and Ahmed, T., 2016, March. A theoretical study on classifier ensemble methods and its applications. In 2016 3rd Internati onal Conference on Computing for Sustainable Global Development (INDIACom) (pp. 374-378). IEEE.