Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{178787,
        author = {PEEKA JAHNAVI and Dr. R. VIJAYA KUMARI and M. L. SARANYA and V. V. NARAYANAMMA},
        title = {FRAUD DETECTION IN ONLINE BANKING TRANSACTIONS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {4966-4973},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178787},
        abstract = {This project introduces a robust Fraud Detection system that employs a sophisticated ensemble learning approach by combining XGBoost and AdaBoost models. The system leverages the strengths of these two powerful algorithms to train on transactional data and identify fraudulent patterns with high precision. Once trained, a soft voting mechanism is applied to integrate the predictions of the individual models, ensuring an optimized balance between accuracy and recall. The implementation seamlessly integrates with existing banking platforms to enable real-time anomaly detection and instant alerts for suspicious activities. The voting mechanism aggregates probabilistic outputs from the models, allowing the system to make informed and confident predictions. This approach not only minimizes false positives but also enhances the resilience of the detection framework against evolving fraud tactics. Used React as Front-end and Flask as Back-end. Designed for scalability, the architecture supports deployment across a wide range of banking systems, maintaining performance and reliability even with increased data loads. The system's adaptability ensures continuous improvement by learning from emerging fraud trends, further refining detection strategies over time. This advanced ensemble-based solution reinforces financial security, instilling trust among customers and financial institutions by safeguarding sensitive operations from malicious intent.},
        keywords = {Fraud Detection, AdaBoost, XGBoost, React, Flask},
        month = {May},
        }