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{199137,
        author = {Jyotiranjan Rout and Dr. Uttam Panda and Dr. Rasmilata Nayak and Saroj Kumar Patra},
        title = {Fraud Detection in Financial Transactions: An Ensemble Learning Framework for Risk Management},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {15905-15915},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199137},
        abstract = {The study investigates the effectiveness of several machine learning models in identifying both legitimate and fraudulent transactions. A thorough comparison study reveals that the ensemble model is the best strategy, with exceptional performance metrics across numerous assessment criteria. The ensemble model achieves an accuracy of 0.99, a precision of 0.990, a recall of 0.99, and an F1-score of 0.98, suggesting excellent ability to reliably identify both positive and negative examples while reducing mistakes. The confusion matrix analysis verifies the ensemble model's accuracy and recall, with a low number of false positives and negatives. Furthermore, the ensemble model has an ROC of 0.99, exceeding models such as Random Forest (ROC 0.97), Gradient Boosting Algorithm (ROC 0.96), and Naive Bayes (ROC 0.94), exhibiting higher class distinguishing capacity. While other models perform admirably, the ensemble model's ability to combine the strengths of multiple algorithms leads to significantly improved predictive accuracy and robustness, making it the preferred choice for detecting fraudulent transactions in real-world scenarios.},
        keywords = {Machine learning, Ensemble model, Fraud detection, Transaction classification.},
        month = {April},
        }