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{185774,
        author = {Rushikesh Bhoyar and Samiksha Gole and Rehan Khan and Revti Nimje and Rajesh Nasare and Rajas Deshpande and Roshan Deotale},
        title = {Multi-Modal Fraud Detection in Digital Transactions},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {5},
        pages = {3801-3806},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=185774},
        abstract = {This research presents a real-time fraud detection framework that leverages heterogeneous data sources to enhance detection accuracy and system reliability. Departing from conventional single-dataset approaches, the proposed system synthesizes transaction records, behavioral analytics, network topology, geospatial intelligence, and textual data to identify sophisticated fraud patterns. Individual data stream undergo rigorous preprocessing including data cleaning, feature normalization, and attribute extraction prior to classification through ensemble machine learning architectures comprising Random Forest, XGBoost, HistGradient, SVM fusion strategies (weighted aggregation and meta-learning), and key features (real-time processing, stability, modularity) It provides a practical solution for fraud mitigation in evolving digital transaction ecosystems, The architecture demonstrates scalability for high-volume streaming data environments, while its modular design facilitates seamless integration of additional data modalities and algorithmic components.},
        keywords = {},
        month = {March},
        }