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{207410,
        author = {Mrs.Priyanka Mohan and Miss.Roopa J and Miss.Swarageetha A R},
        title = {Adaptive Hybrid Machine Learning Framework for Real-time E-Commerce Fraud Detection using Explainable AI},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {3},
        pages = {1040-1044},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=207410},
        abstract = {The rapid growth of e-commerce has brought a matching rise in financial fraud, as cybercriminals keep a coming up with new and more sophisticated methods that expose the cracks in traditional rule-based systems. This paper proposes an Adaptive Hybrid ML Frameworks for real-time credit card fraud detection that brings together Random Forest, XGBoost, and Deep Neural Networks to classify transactions more effectively. Random Forest relies on a collection of decision trees for classification, XGBoost applies gradient boosting to uncover complex patterns within transaction data, and the DNN com-ponent recognizes subtler patterns that the other models may miss. Beyond combining these models, the framework addresses class imbalance, adapts as fraud tactics evolve, and incorporates Explainable AI (XAI) through SHAP to make the prediction process more transparent. Together, these elements improve detection accuracy while giving analysts a clear rationale for why a transaction is flagged as fraudulent or legitimate.},
        keywords = {E-commerce fraud detection, adaptive hybrid framework, Explainable AI (XAI), deep neural networks, SHAP, imbalanced datasets, real-time monitoring.},
        month = {August},
        }