Credit Fraud Prediction Using Machine Learning Algorithms

Yuan Huang ； Ya-Chi Lee ； Zongmian Huang ； Zongxi Huang ； Zixi Zhong ； Zihao Jiang

《World Scientific Research Journal》 7卷1期 (2021/01) Pp. 233-249

https://doi.org/10.6911/WSRJ.202101_7(1).0033

摘要

While the use of credit card payment is becoming more and more popular, the rise of credit card frauds also becomes a highly notable issue and causes serious problems in many financial industries. This paper presents a complete process of a fraud model building project that includes the discussion of data preparation, data cleaning, feature selection, model building, and corresponding results. The fraud models built in this project are supervised models with given labels on data to indicate whether it is fraud or non-fraud. In more specifically, for feature selection, starting with 308 expert variables, the univariate filter methods KS and FDR are applied to cut off the majority of variables and to keep 80 of them, and the wrapper is applied to reduce the number of variables to 30 using backward selection with the logistic regression model. Also, in the model algorithms section, the performance and result of logistic regression, neural network, boosted tree, and random forest is compared and illustrated. In this paper, neural net is determined to be the best predictive model with out-of-time FDR of 53.7091%.

關鍵字

Credit Fraud Prediction ； Machine learning ； Data preparation ； Data cleaning ； Feature selection ； Model building

參考文獻

Albashrawi, M. (2016) Detecting Financial Fraud Using Data Mining Techniques: A Decade Review from 2004 to 2015. Journal of Data Science, 14, 553-569.

Hastie, T., Tibshirani, R. and Friedman, J. (2009) Boosting and Additive Trees. In: The Elements of Statistical Learning, Springer, New York, 337-387.

Randhawa, K., Loo, C.K., Seera, M., Lim, C.P. and Nandi, A.K. (2018) Credit Card Fraud Detection Using AdaBoost and Majority Voting. IEEE Access, 6, 14277-14284. https://doi.org/10.1109/ACCESS.2018.2806420

Gao, J.X., Zhou, Z.R., Ai, J.S., Xia, B.X. and Coggeshall, S. (2019) Predicting Credit Card Transaction Fraud Using Machine Learning Algorithms. Journal of Intelligent Learning Systems and Applications, 11, 33-63. https://doi.org/10.4236/jilsa.2019.113003

Dal Pozzolo, A., Caelen, O., Le Borgne, Y.-A., Waterschoot, S. and Bontempi, G. (2014) Learned Lessons in Credit Card Fraud Detection from a Practitioner Perspective. Expert Systems with Applications, 41, 4915-4928. https://doi.org/10.1016/j.eswa.2014.02.026