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{200905,
        author = {T. Praveena and A. Arush Alexander and S. Mukesh Kannan and T. Prabagaran},
        title = {Multi Model Insurance Fraud Detection Using Ai},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {no},
        pages = {34-39},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200905},
        abstract = {Insurance fraud has emerged as a critical challenge in the insurance sector, leading to substantial financial losses and inefficiencies in claim processing. This paper proposes a multimodal artificial intelligence-based framework for the detection of fraudulent insurance claims by integrating heterogeneous data sources, including vehicle images, textual information, and structured claim records. The system employs a deep learning- based object detection model for vehicle damage assessment and utilizes optical character recognition (OCR) techniques for accurate number plate extraction. Furthermore, a gradient boosting-based classifier is used to analyze historical claim patterns and classify claims as fraudulent or legitimate.
A feature-level fusion strategy is adopted to combine outputs from multiple modalities, enhancing the robustness and predictive performance of the model. Experimental evaluation demonstrates that the proposed approach achieves superior accuracy, precision, and recall compared to traditional single-modality methods. The system also reduces false positives and improves decision-making efficiency in claim verification processes. The proposed framework provides a scalable, automated, and reliable solution for real- world insurance fraud detection, with significant potential for deployment in modern insurance systems.},
        keywords = {.},
        month = {May},
        }