Fraud Detection in Transaction Based on ‎Artificial Intelligence

Authors

  • Harem Mahdi Hadi

    Duhok Polytechnic University, Technical College of Informatics, Department of Information Technology, ‎ Duhok, Kurdistan Region, Iraq

  • Omar Sedqi Kareem

    Duhok Polytechnic University, College of Health and Medical Technology, Shekhan, Public health ‎Department

How to Cite

Hadi, H. M. ., & Kareem, O. S. . (2025). Fraud Detection in Transaction Based on ‎Artificial Intelligence. International Journal of Scientific World, 11(2), 15-25. https://doi.org/10.14419/wr932k70

Received date: May 21, 2025

Accepted date: July 5, 2025

Published date: July 9, 2025

DOI:

https://doi.org/10.14419/wr932k70

Keywords:

Fraud Detection in transaction; Anomaly Detection; Unsupervised Learning; K-Means Clustering; ‎DBSCAN; Isolation Forest

Abstract

Fraud detection has become a top priority for banks and other financial institutions in a time when digital ‎transactions rule the financial ecosystem. To identify anomalies in real-world transaction datasets, this paper ‎presents a strong hybrid unsupervised learning framework that combines K-Means, DBSCAN, and ‎Isolation Forest. The method circumvents the drawbacks of conventional supervised models, specifically ‎their sensitivity to class imbalance and requirement for labeled data. The suggested approach improves the ‎accuracy of fraud detection by including contextual and behavioral variables like ‎TimeSinceLastTransaction, DeviceUsage, and MerchantPreference. High accuracy 99.20% for K-Means ‎and Isolation Forest, and 99.16% for DBSCAN is demonstrated by experimental results on a dataset with ‎‎2,512 transactions. The models' consensus-based validation strengthens the dependability of the fraud that is ‎identified. This study offers an efficient and scalable anomaly detection method that works well for real-time fraud analytics in settings with a small number of labeled datasets‎.

References

  1. Association of Certified Fraud Examiners, Report to the Nations: 2022 Global Study on Occupational Fraud and Abuse, ACFE, 2022.
  2. R. J. Bolton and D. J. Hand, “Statistical fraud detection: A review,” Statistical Science, vol. 17, no. 3, pp. 235–255, 2002. https://doi.org/10.1214/ss/1042727940.
  3. C. Phua, V. Lee, K. Smith, and R. Gayler, “A comprehensive survey of data mining-based fraud detection research,” arXiv preprint arXiv:1009.6119, 2010.
  4. E. W. T. Ngai, Y. Hu, Y. H. Wong, Y. Chen, and X. Sun, “The application of data mining techniques in financial fraud detection: A classification framework and an academic review of literature,” Decision Support Systems, vol. 50, no. 3, pp. 559–569, 2011. https://doi.org/10.1016/j.dss.2010.08.006.
  5. A. C. Bahnsen, D. Aouada, and B. Ottersten, “Feature engineering strategies for credit card fraud detection,” Expert Systems with Applications, vol. 51, pp. 134–142, 2016. https://doi.org/10.1016/j.eswa.2015.12.030.
  6. J. Jurgovsky et al., “Sequence classification for credit-card fraud detection,” Expert Systems with Applications, vol. 100, pp. 234–245, 2018. https://doi.org/10.1016/j.eswa.2018.01.037.
  7. Y. Zhang, Y. Yuan, and Q. Liu, “Fraud detection with graph neural networks,” arXiv preprint arXiv:2003.06902, 2020.
  8. U. Fiore, A. De Santis, F. Perla, P. Zanetti, and F. Palmieri, “Using generative adversarial networks for improving classification effectiveness in credit card fraud detection,” Information Sciences, vol. 479, pp. 448–455, 2019. https://doi.org/10.1016/j.ins.2017.12.030.
  9. A. Roy, J. Sun, W. Mahoney, N. Alsharif, and A. K. Dey, “Deep learning detecting fraud in credit card transactions,” in Proc. IEEE IEMCON, 2018, pp. 405–410. https://doi.org/10.1109/SIEDS.2018.8374722.
  10. H. Sahin, D. Bulus, and T. Tunali, “Detecting concept drift in nonstationary environments using ensemble classifiers,” IEEE Access, vol. 7, pp. 110907–110917, 2019. https://doi.org/10.1109/ACCESS.2020.2970614.
  11. T. Zhang, D. Song, H. Chen, and G. Wang, “Behavior-based fraud detection in mobile payment: A survey,” IEEE Access, vol. 8, pp. 166678–166692, 2020.
  12. S. Chowdhury, A. Das, S. Chatterjee, and T. Roy, "Unsupervised Detection of Fraudulent Transactions in E-commerce Using Contrastive Learn-ing," arXiv preprint arXiv:2503.18841, 2024. [Online]. Available: https://arxiv.org/abs/2503.18841
  13. R. Parveen and A. A. Parvez, "Credit Card Fraud Detection Using Unsupervised Machine Learning Algorithms," in Proc. Int. Conf. on Computing, Communication, and Intelligent Systems (ICCCIS), 2021. [Online]. Available: https://www.researchgate.net/publication/354065310
  14. C. Liu, M. Zhang, and Y. Zhang, "Credit Card Fraud Detection Based on Unsupervised Attentional Anomaly Detection Network," Systems, vol. 11, no. 6, p. 305, 2023. [Online]. Available: https://www.mdpi.com/2079-8954/11/6/305. https://doi.org/10.3390/systems11060305.
  15. B. Hu, H. Zhao, and Y. Wang, "Unsupervised Fraud Transaction Detection on Dynamic Attributed Networks," in Proc. Int. Conf. on Database Systems for Advanced Applications (DASFAA), 2023. [Online]. Available: https://librahu.github.io/data/dasfaa2023_ufdt_paper.pdf
  16. S. J. Yan, X. Zhang, and M. Wang, "Real-Time Online Banking Fraud Detection Model by Unsupervised Learning Fusion," 2024. [Online]. Avail-able: https://www.researchgate.net/publication/380080105.

Downloads

How to Cite

Hadi, H. M. ., & Kareem, O. S. . (2025). Fraud Detection in Transaction Based on ‎Artificial Intelligence. International Journal of Scientific World, 11(2), 15-25. https://doi.org/10.14419/wr932k70

Received date: May 21, 2025

Accepted date: July 5, 2025

Published date: July 9, 2025