DETECTING FINANCIAL FRAUD IN UZBEKISTAN’S DIGITAL ECOSYSTEM: A COMPARATIVE ANALYSIS OF MACHINE LEARNING AND DATA BALANCING TECHNIQUES
Received: 2026-07-15 15:50:49
Published: 2026-04-18
Abstract
The report discusses the growing risk of financial fraud within Uzbekistan’s digital banking ecosystem, focusing on unauthorized loans obtained through stolen personal information. Conventional rule-based detection frameworks fail to deliver reliable results, generating excessive false alarms and struggling to adapt to evolving scam tactics. By deploying machine learning models such as Random Forest, XGBoost, neural networks, and anomaly detection algorithms that paired with data balancing techniques like SMOTE, the research achieves significant improvements in fraud identification accuracy.
Keywords
List of references
-
Doe, J. [et al.] (2024), “Performance evaluation of data balancing techniques in financial fraud detection using machine learning”, Procedia Computer Science, Vol. 235, pp. 124-133, doi: 10.1016/j.procs.2024.03.1028.
-
Akhilomen, M. A. [et al.] (2018), “A comparative study of machine learning techniques for credit card fraud detection”, Expert Systems with Applications, Vol. 110, pp. 350-362, doi: 10.1016/j.eswa.2018.05.032.
-
Fawcett, T. (2006), “An introduction to ROC analysis”, Pattern Recognition Letters, Vol. 27 No. 8, pp. 861-874, doi: 10.1016/j.patrec.2005.10.010.
-
Ngai, E. W. T., Hu, Y. and Wong, Y. H. (2011), “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, doi: 10.1016/j.dss.2010.08.006.
-
Prasad, S. S. P. [et al.] (2017), “Deep learning for financial fraud detection”, 2017 IEEE International Conference on Computing, Communication and Automation (ICCCA), pp. 1297-1302, doi: 10.1109/CCAA.2017.8229994.
About the Authors
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
