Benefiting Machine Learning Methods to Detect Fraud in the Validation of Bank Customers' Cards

Document Type : Original Article


1 Department of Computer, Faculty of Engineering, Aghigh University, Shahin shahr, Isfahan, Iran.

2 Department of Computer, Naein Branch, Islamic Azad University, Naein, Isfahan, Iran



The existence of money laundering and banking fraud is one of the major challenges of the banking system in any country. Crediting customers based on their track record and performance is a method to address the banking challenges. Classification methods can be used to validate customers, but these methods own high error. In this paper, machine learning methods are applied on banking data set to classify them and to reduce the error in customer validation. To this end, first the machine learning methods are trained and then tested using the banking data set. Experiments on the banking data set show that the accuracy of the proposed method for validating customers is less than 81.6%. So, the accuracy index of the random forest, decision tree, support vector machine, and multilayer artificial neural network are 80.50\%, 80.05\%, 80.93\%, and 81.58\%, respectively. The best performance is related to multilayer artificial neural network and, accordingly, the multilayer artificial neural network method can be used in detection of the validation of bank customers' cards.

Graphical Abstract

Benefiting Machine Learning Methods to Detect Fraud in the Validation of Bank Customers' Cards


[1]    Maitlo, G.M., Kazi, Z.H., Khaskheley, A. and Shaikh, F.M., “Factors that influence the adoption of online banking services in Hyderabad”, International Journal of Economics & Management Sciences, 2015, 4(1), pp.1-10.
[2]    Mousavian, S.J. and Ghasbeh, M.J.,”Investigation of Relationship between E-Banking Industry Risks and Electronic Customer Relationship Management (E-CRM)”. MAYFEB Journal of Business and Management, 2017, 2.
[3]    Sardana, S. and Bajpai, V.N., “E-banking service quality and customer satisfaction: an exploratory study on India”. International Journal of Services and Operations Management, 2020, 35,(2), pp.223-247.
[4]    Khedmatgozar, H.R. and Shahnazi, A., “ The role of dimensions of perceived risk in adoption of corporate internet banking by customers in Iran”, Electronic Commerce Research, 2018, 18(2), pp.389-412.
[5]    Ojukwu-Ogba, N.E. and Osode, P.C., “A Critical Assessment of the Enforcement Regime for Combatting Money Laundering in Nigeria”, African Journal of International and Comparative Law, 2020, 28(1), pp.85-105.
[6]    González-Carrasco I, Jiménez-Márquez JL, López-Cuadrado JL, Ruiz-Mezcua B. “Automatic detection of relationships between banking operations using machine learning”. Information Sciences, 2019, 485, pp.319-346.
[7]    Sanz-Barbero B, Gómez AR, Ayala A, Recio P, Sarriá E, Díaz-Olalla M, Zunzunegui MV., “Impact of self-reported bank fraud on self-rated health, comorbidity and pain” International journal of public health, 2020, 65(2), pp.165-174.
[8]    Teichmann, F., “Recent trends in money laundering”, Crime, Law and Social Change, 2020, 73(2), pp.237-247.
[9]    Wang, Y., Wang, L. and Yang, J., “ Egonet based anomaly detection in E-bank transaction networks. In IOP Conference Series”, Materials Science and Engineering, IOP Publishing, 2020, Vol. 715, No. 1, p. 012038).
[10] Didimo, W., Grilli, L., Liotta, G., Menconi, L., Montecchiani, F. and Pagliuca, D., “Combining network visualization and data mining for tax risk assessment”, IEEE Access, 2020, 8, pp.16073-16086.
[11] Sariannidis, N., Papadakis, S., Garefalakis, A., Lemonakis, C. and Kyriaki-Argyro, T., “Default avoidance on credit card portfolios using accounting, demographical and exploratory factors: decision making based on machine learning (ML) techniques”, Annals of Operations Research, 2020, 294(1), pp.715-739.
[12] El-Banna, M.M., Khafagy, M.H. and El Kadi, H.M., “Smurf Detector: a Detection technique of criminal entities involved in Money Laundering”, In 2020 International Conference on Innovative Trends in Communication and Computer Engineering (ITCE), 2020, (pp. 64-71). IEEE.
[13] Han, J., Huang, Y., Liu, S. and Towey, K., “Artificial intelligence for anti-money laundering: a review and extension”, Digital Finance, 2020, 2(3), pp.211-239.
[14] Tadapaneni, N.R., “Artificial Intelligence in Finance and Investments”.
[15] Chandradeva, L.S., Amarasinghe, T.M., De Silva, M., Aponso, A.C. and Krishnarajah, N.,” Monetary Transaction Fraud Detection System Based on Machine Learning Strategies”, In Fourth International Congress on Information and Communication Technology, Springer, Singapore, 2020, pp. 385-396.
[16] Fathi, M., Nemati, M., Mohammadi, S.M. and Abbasi-Kesbi, R.,” A machine learning approach based on SVM for classification of liver diseases”, Biomedical Engineering: Applications, Basis and Communications, 2020, 32(03), p.2050018.
[17] Khine, A.A. and Khin, H.W.,” Credit Card Fraud Detection Using Online Boosting with Extremely Fast Decision Tree”. In 2020 IEEE Conference on Computer Applications (ICCA), IEEE., 2020, pp. 1-4.
[18] Dong, M., Yao, L., Wang, X., Benatallah, B., Huang, C. and Ning, X., “Opinion fraud detection via neural autoencoder decision forest”. Pattern Recognition Letters, 2020, 132, pp.21-29.
[19] Yan, C., Li, Y., Liu, W., Li, M., Chen, J. and Wang, L.,”An artificial bee colony-based kernel ridge regression for automobile insurance fraud identification”. Neurocomputing, 2020, 393, pp.115-125.
[20] Abbasi-Kesbi, R., Memarzadeh-Tehran, H. and Deen, M.Jamal : “Technique to Estimate the Human Reaction Time Based on Visual Perception”, Healthcare Technology Letters, 4, (2), 2017, pp. 73-77
[21] Abbasi-Kesbi, R., Asadi, Z. and Nikfarjam, A., “Developing a wireless sensor network based on a proposed algorithm for healthcare purposes”, Biomedical engineering letters, 2020, 10(1), pp.163-170.
[22] Abbasi‐Kesbi, R., Valipour, A. and Imani, K., “Cardiorespiratory system monitoring using a developed acoustic sensor”, Healthcare technology letters, 2018, 5(1), pp.7-12.
[23] Abbasi-Kesbi, R. and Nikfarjam, A., “A miniature sensor system for precise hand position monitoring”, IEEE Sensors Journal, 2018, 18(6), pp.2577-2584.
[24] Abbasi-Kesbi, R., Nikfarjam, A. and Memarzadeh-Tehran, H.: “A Patient-Centric Sensory System for In-Home Rehabilitation”, IEEE Sensors Journal, 2017, 17, (2), p. 524-533.
[25] Onwubiko, C., “Fraud matrix: A morphological and analysis-based classification and taxonomy of fraud”. Computers and Security, 2020, 96, p.101900.
[27] Chai, T. and Draxler, R.R., “Root mean square error (RMSE) or mean absolute error (MAE)”, Geoscientific Model Development Discussions, 2014, 7(1), pp.1525-1534.
[28] Wang, C., Yuan, H., Duan, Z. and Xiao, D., “Integrated multi-ISE arrays with improved sensitivity, accuracy and precision”, Scientific reports, 2017, 7(1), pp.1-10.