Volume 11 - Summer Supplementary
Ann Appl Sport Sci 2023, 11 - Summer Supplementary: 0-0 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Arslan E, Güneş A. Fraud Detection in Enterprise Resource Planning Systems Using One-Class Support Vector Machine Combined with Convolutional Neural Network: The Case of Spor Istanbul. Ann Appl Sport Sci 2023; 11 (S1)
URL: http://aassjournal.com/article-1-1222-en.html
URL: http://aassjournal.com/article-1-1222-en.html
1- Department of Computer Engineering, Faculty of Engineering, Istanbul Aydın University, Istanbul, Turkey , emraha@stu.aydin.edu.tr
2- Department of Computer Engineering, Faculty of Engineering, Istanbul Aydın University, Istanbul, Turkey
2- Department of Computer Engineering, Faculty of Engineering, Istanbul Aydın University, Istanbul, Turkey
Abstract: (1052 Views)
Background. Combining a One-Class Support Vector Machine (OCSVM) with a Convolutional Neural Network (CNN) is presented as a novel technique for detecting fraud in Enterprise Resource Planning (ERP) systems.
Objectives. The objective of this research is to develop a technique for detecting fraud in Enterprise Resource Planning (ERP) systems by combining a One-Class Support Vector Machine (OCSVM) with a Convolutional Neural Network (CNN), suitable for the Spor Istanbul ERP system.
Methods. This study examines the ERP system utilized by Spor Istanbul, the largest sports enterprise in Turkey, as a case study. The study utilizes a custom database of web-based program files to create a dataset of benign and malicious JavaScript applications. Firstly, the text and control flow graph of the program is analyzed. Secondly, the OCSVM method is applied as an outlier detection technique, and CNN is used as a classifier.
Results. The experimental results indicate that the proposed OCSVM-CNN approach achieves higher accuracy (96.78%) in detecting malicious scripts compared to using only CNN (94.8%).
Conclusion. The research contributes to the development of multi-layered ERP software architecture with AI decision support, improving fraud detection in ERP systems.
Objectives. The objective of this research is to develop a technique for detecting fraud in Enterprise Resource Planning (ERP) systems by combining a One-Class Support Vector Machine (OCSVM) with a Convolutional Neural Network (CNN), suitable for the Spor Istanbul ERP system.
Methods. This study examines the ERP system utilized by Spor Istanbul, the largest sports enterprise in Turkey, as a case study. The study utilizes a custom database of web-based program files to create a dataset of benign and malicious JavaScript applications. Firstly, the text and control flow graph of the program is analyzed. Secondly, the OCSVM method is applied as an outlier detection technique, and CNN is used as a classifier.
Results. The experimental results indicate that the proposed OCSVM-CNN approach achieves higher accuracy (96.78%) in detecting malicious scripts compared to using only CNN (94.8%).
Conclusion. The research contributes to the development of multi-layered ERP software architecture with AI decision support, improving fraud detection in ERP systems.
Keywords: Enterprise Resource Planning, Intelligent ERP, Forecasting, Demand Prediction, Decision Support System, Artificial Neural Networks, Cellular Neural Networks, Multi-Layered Software Architecture
Full-Text [PDF 889 kb]
(535 Downloads)
APPLICABLE REMARKS
APPLICABLE REMARKS
• This combined technique can effectively detect malicious scripts in Enterprise Resource Planning systems.
• The research proposes a new approach for feature extraction in ERP systems using machine learning algorithms.
• Future work could involve incorporating additional data sources, such as network traffic logs, to enhance the accuracy of anomaly detection in ERP systems.
• Real-time monitoring systems, integration with existing security systems, and the use of explainable AI techniques are potential directions to further improve the system's effectiveness and usability in detecting and responding to security threats and system errors.
• Overall, the research contributes to the development of multi-layered ERP software architecture with AI decision support, improving fraud detection and enhancing the success of ERP system implementations.
• The research proposes a new approach for feature extraction in ERP systems using machine learning algorithms.
• Future work could involve incorporating additional data sources, such as network traffic logs, to enhance the accuracy of anomaly detection in ERP systems.
• Real-time monitoring systems, integration with existing security systems, and the use of explainable AI techniques are potential directions to further improve the system's effectiveness and usability in detecting and responding to security threats and system errors.
• Overall, the research contributes to the development of multi-layered ERP software architecture with AI decision support, improving fraud detection and enhancing the success of ERP system implementations.
Type of Study: Original Article |
Subject:
Sport Management and its related branches
Received: 2023/05/1 | Accepted: 2023/06/24
Received: 2023/05/1 | Accepted: 2023/06/24
References
1. Liu X, Chen, J. Anomaly detection of JavaScript codes using one-class support vector machine and convolutional neural networks. Journal of Information Security and Applications, 2021;61, 102857.
2. Wang J, Li, D., Zhang, D. Li, W. A review of anomaly detection techniques in ERP systems. Journal of Systems and Software, 141, 2018;190-204.
3. Yang, S, Liu, Z, Huang, X, Wang, X. An improved fraud detection method for ERP systems based on one-class SVM and convolutional neural networks. Neural Computing and Applications, 2020; 32(17), 13797-13809.
4. Zhang Z., Li Y., Li X., Li G. Li B. The application of deep learning in ERP risk forecasting. Journal of Intelligent Manufacturing, 2021;32(3), 569-578.
5. Chen, Y., Ren, L., & Zhang, L. (2020). Anomaly detection of network traffic based on deep learning in ERP sys-tems. IEEE Access, 8, 100923-100934.
6. Zhang L., Chen X., Chen C. Fraud Detection in ERP Systems using One-Class SVM. IEEE Access, 2019;7, 108051-108059.
7. Zhang H., Jiang Y., Shi Y., Liu X. A Convolutional Neural Network Approach for Fraud Detection in ERP Systems. Future Generation Computer Systems, 2020;102, 778-786. [DOI:10.1016/j.future.2019.09.012]
8. Zhang H., Jiang Y., Shi, Y. An Improved Fraud Detection Model in ERP Systems Based on One-Class SVM and Convolutional Neural Network. IEEE Access, 2021;9, 55870-55878. [DOI:10.1109/ACCESS.2021.3063803]
9. Sun J, Zhang Y., Wang Z., Shen L. Fraud Detection in ERP Systems Based on Deep Belief Network. Journal of Computational Science, 2020;41, 101115.
10. Gupta, A. Singh, P. The role of ERP in financial accounting: A systematic review. Journal of Enterprise Information Management,2020; 33(3), 531-554.
11. Krishnan G., Yu, A.S. A comprehensive analysis of ERP adoption drivers, implications, and challenges. Journal of Information Systems, 2018;32(1), 101-121.
12. Damodaran L. Olafsson, S. Enterprise resource planning systems and financial reporting quality: The role of inter-nal controls. Journal of Information Systems, 2018;32(1), 55-75.
13. Cao M., Zhang Q. Duan Y. Big data analytics for fraud detection in accounting information systems. Journal of In-telligent & Fuzzy Systems, 2018;35(4), 4613-4625.
14. Ashar H. Hasan H. Understanding the challenges and opportunities in ERP data analytics for financial reporting. Journal of Accounting & Organizational Change, 2019;15(4), 606-625.
15. Ahmed T.A., Islam M.R., Hossain M.A. Hossain M.S. Malicious script detection in ERP using CNN and anomaly detection," IEEE Access, 2020;8,140682-140692.
16. Kumar P.V.P., Kumar P.R., Thangaraj R.C. Demand forecasting and anomaly detection in enterprise resource plan-ning systems using artificial neural network and cellular neural network," Journal of Intelligent Manufacturing, 2020, 31(3),-743-757.
17. Kumar V., Hillegersberg J.V. Enterprise resource planning systems and its implications for operations function. In-ternational Journal of Production Research, 2000;38(17), 4119-4135.
18. Gunasekaran A., Ngai E.W.T. Information systems in supply chain integration and management. European Journal of Operational Research, 2004;159(2), 269-295. [DOI:10.1016/j.ejor.2003.08.016]
19. Yao X., Liu Y. A survey of artificial neural networks for ERP systems: Applications and challenges. Applied Soft Computing, 2015;26, 325-334.
20. Münstermann B., Eckstein J., Kabst R. The use of corporate talent management for succession planning in German medium-sized enterprises. Journal of Small Business Management, 2013;51(3), 443-465.
21. Zhang Y. Wu C. The effect of intelligent ERP systems on supply chain performance: An empirical study. Journal of Enterprise Information Management, 2018;31(5), 782-800.
22. LeCun Y., Bengio Y., Hinton G. Deep learning. Nature, 2015;521(7553), 436-444. [DOI:10.1038/nature14539] [PMID]
23. Goodfellow I., Bengio Y., Courville A. Deep learning. MIT Press; 2016.
24. Guo Y., Wang H. Convolutional neural networks for image processing: A deep learning approach. Journal of Visual Communication and Image Representation, 2017; 48, 436-449.
25. Simonyan K., Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:2014; 1409.1556.
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
