Analysis of Machine Learning Methods Performance for Fraud Recognition in Payroll ERP Systems

  • Authors

    • Rashmika Jalagam Matilda Cloud - Cloud Engineer/Python Developer, USA. Author
    • Sridevi Allu American Airlines, AI/ML Engineer, USA. Author
    • Venkata Phaneendra Reddi Atlantic Health systems - Oracle Integrations Developer, USA. Author
    • Pradeep Rao Vennamaneni Medtronic - Senior Software Engineer, USA. Author
    • Sri Prudhvi Adusumilli Charter Communications, Sr Software Developer, USA. Author
    • Khaja Moiezuddin Mohammed Iqvia - Sr Data Engineer, USA. Author

    DOI:

    https://doi.org/10.67228/30715628/IJMIET-2022PII9K4M

    Published 09-07-2022

  • Fraud Detection, Payroll ERP Systems, Machine Learning, Financial Fraud, Random Forest, XGBoost, PaySim Data

    Issue

    Vol. 5 No. 2 (2022)

    Section

    Articles

  • Abstract

    Financial institutions are increasingly worried about online payment fraud, which has increased the need for efficient and effective detection systems. In response, this work focuses on an innovative method for detecting online payment fraud by leveraging Random Forest (RF) and XGBoost (XGB) classifiers on the PaySim synthetic dataset. The methodology comprises the preprocessing of data, outlier identification, feature extraction, z-score normalization, and class balancing as a solution to severe imbalance between classes using the approach of Random Over-Sampling. Training of the models was done with the best hyperparameters and the evaluation was done in terms of accuracy, precision, recall, F1-score and ROC-AUC. The experimental findings prove that RF has almost perfect performance with 99.99% accuracy, 99.87% precision, 99.98% recall and 0.9998 ROC whereas XGB performs well too. The high effectiveness of proposed models is proved by the comparative analysis with traditional and DL models, such as Decision Tree (DT), Logistic Regression (LR), CNN, LSTM, BERT, etc. The analysis of feature importance and SHAP indicates that the account balance discrepancies and transaction amounts are the most prominent indicators of fraud. The main features such as balance gap and transaction volumes are the focus of detecting fraud, and hence the models are very precise, dependable, and can work on unbalanced time-sensitive financial data.

  • References

    [1] Roy, A., Sun, J., Mahoney, R., Alonzi, L. P., Adams, S., & Beling, P. (2018). Deep learning detecting fraud in credit card transactions. In 2018 Systems and Information Engineering Design Symposium (SIEDS) (pp. 129–134). IEEE. https://doi.org/10.1109/SIEDS.2018.8374722

    [2] Sinanc, D., Demirezen, U., & Sağıroğlu, Ş. (2021). Explainable credit card fraud detection with image conversion. ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal, 10(1), 63–76. https://doi.org/10.14201/ADCAIJ20211016376

    [3] Tan, R., Tan, Q., Zhang, P., & Li, Z. (2021). Graph neural network for Ethereum fraud detection. In 2021 IEEE International Conference on Big Knowledge (ICBK) (pp. 78–83). IEEE. https://doi.org/10.1109/ICKG52313.2021.00020

    [4] Jullum, M., Løland, A., Huseby, R. B., Ånonsen, K. H., & Lorentzen, J. (2020). Detecting money laundering transactions with machine learning. Journal of Money Laundering Control, 23(1), 173–186. https://doi.org/10.1108/JMLC-07-2019-0055

    [5] A hybrid deep learning model for online fraud detection. (2021). In 2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE) (pp. 1–5). IEEE. https://doi.org/10.1109/ICCECE51280.2021.9342110

    [6] Dhieb, N., Ghazzai, H., Besbes, H., & Massoud, Y. (2020). A secure AI-driven architecture for automated insurance systems: Fraud detection and risk measurement. IEEE Access, 8, 58546–58558. https://doi.org/10.1109/ACCESS.2020.2983300

    [7] Gee, S. (2015). Payroll fraud. In Fraud and fraud detection. Wiley. https://doi.org/10.1002/9781118936764.ch10

    [8] Nguyen, G., Dlugolinsky, S., Bobák, M., Tran, V., López García, Á., Heredia, I., Malík, P., & Hluchý, L. (2019). Machine learning and deep learning frameworks and libraries for large-scale data mining: A survey. Artificial Intelligence Review, 52, 77–124. https://doi.org/10.1007/s10462-018-09679-z

    [9] Goes, A. S. de O., & de Oliveira, R. C. L. (2020). A process for human resource performance evaluation using computational intelligence: An approach using a combination of rule-based classifiers and supervised learning algorithms. IEEE Access, 8, 39403–39419. https://doi.org/10.1109/ACCESS.2020.2975485

    [10] Lucas, Y., & Jurgovsky, J. (2020). Credit card fraud detection using machine learning: A survey. arXiv. https://arxiv.org/abs/2010.06479

    [11] West, J., & Bhattacharya, M. (2019). Performance of machine learning techniques in the detection of financial frauds. Procedia Computer Science, 148, 45–54. https://doi.org/10.1016/j.procs.2019.01.007

    [12] Li, C., Ding, N., Zhai, Y., & Dong, H. (2021). Comparative study on credit card fraud detection based on different support vector machines. Intelligent Data Analysis, 25(1), 105–119. https://doi.org/10.3233/IDA-195011

    [13] Al-Hashedi, K. G., & Magalingam, P. (2021). Financial fraud detection applying data mining techniques: A comprehensive review from 2009 to 2019. Computer Science Review, 40, Article 100402. https://doi.org/10.1016/j.cosrev.2021.100402

    [14] Liu, G., Tang, J., Tian, Y., & Wang, J. (2021). Graph neural network for credit card fraud detection. In 2021 IEEE International Conference on Big Data (Big Data). IEEE.

    [15] Liu, X., & Chen, J. (2021). Anomaly detection of JavaScript codes using one-class support vector machine and convolutional neural networks. Journal of Information Security and Applications, 61, Article 102857.

    [16] Nawrocki, P., & Osypanka, P. (2021). Cloud resource demand prediction using machine learning in the context of QoS parameters. Journal of Grid Computing, 19, Article 20. https://doi.org/10.1007/s10723-021-09561-3

    [17] Lucas, Y., & Jurgovsky, J. (2020). Credit card fraud detection using machine learning: A survey. arXiv. https://doi.org/10.48550/arXiv.2010.06479

    [18] Rajora, S., Li, D. L., Jha, C., Bharill, N., Patel, O. P., Joshi, S., Puthal, D., & Prasad, M. (2019). A comparative study of machine learning techniques for credit card fraud detection based on time variance. In S. Sundaram (Ed.), Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence (SSCI) (pp. 1958–1963). IEEE. https://doi.org/10.1109/SSCI.2018.8628930

    [19] A. H. Almuteer, A. A. Aloufi, W. O. Alrashidi, J. F. Alshobaili, and D. M. Ibrahim, “Detecting Credit Card Fraud using Machine Learning,” Int. J. Interact. Mob. Technol., vol. 15, no. 24, pp. 108–122, Dec. 2021, doi: 10.3991/ijim.v15i24.27355.

    [20] Psychoula, I., Gutmann, A., Mainali, P., Lee, S. H., Dunphy, P., & Petitcolas, F. A. P. (2021). Explainable machine learning for fraud detection. arXiv. https://arxiv.org/abs/2105.06314

    [21] Carminati, B., Ferrari, E., & Viviani, M. (2018). A fraud detection decision support system via human on-line behavior characterization and machine learning. In Proceedings of the 2018 IEEE International Conference on Big Data (Big Data). IEEE.

    [22] Owolabi, O. O., & Olatunji, S. O. (2020). A framework for detecting credit card fraud with cost-sensitive meta-learning ensemble approach. Scientific African, 8, Article e00464. https://doi.org/10.1016/j.sciaf.2020.e00464.

    [23] Taluri, R. (2021). Cloud-Native Architectures for Enterprise Financial Data Management, Analytics, and Regulatory Reporting Compliance. International Journal of Emerging Trends in Computer Science and Information Technology, 2(2), 101-111. https://doi.org/10.63282/3050-9246.IJETCSIT-V2I2P112

  • Downloads

Similar Articles

21-30 of 111

You may also start an advanced similarity search for this article.