Abstract :

Real-time Fraud Detection Has Become A Crucial Challenge For Contemporary Financial Systems Due To The Exponential Rise Of Digital Financial Transactions And The Growing Sophistication Of Cyber Fraud Schemes. Conventional Fraud Detection Methods Frequently Find It Difficult To Adjust To Dynamic And Changing Fraud Trends Because They Are Mostly Dependent On Rulebased Frameworks And Manual Monitoring. These Traditional Methods Are Usually Unable To Detect Complicated Fraudulent Actions Due To High False-positive Rates, Restricted Scalability, And Slow Reaction Times. The Combination Of Machine Learning And Artificial Intelligence Has Become A Viable Approach To Intelligent Fraud Detection In Order To Overcome These Constraints. Large Amounts Of Historical Transaction Data Can Be Used By AI-driven Algorithms To Learn Complex Patterns And Spot Minute Irregularities That Might Point To Fraud. In Order To Examine Real-time Transaction Data, This Paper Suggests An AI-based Fraud Detection System That Makes Use Of Machine Learning Methods, Such As Support Vector Machines (SVM) And Decision Tree Classifiers. The Suggested Solution Employs Predictive Modeling And Automated Data Analysis To Identify Unusual Transaction Trends. The Framework Greatly Increases Detection Accuracy While Lowering False Positives And Operating Delays By Facilitating Real-time Monitoring And Quick Decision-making. In Addition, The Technology Improves Flexibility And Scalability In Ever-changing Financial Contexts. Results From Experiments Show That The Suggested Method Offers A Reliable, Effective, And Scalable Way To Identify Financial Fraud, Reducing Losses And Enhancing Security In The Quickly Changing Digital Economy.

Published:

06-3-2026

Issue:

Vol. 26 No. 3 (2026)

Page Nos:

55-61

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite