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{186816,
        author = {E. Susmitha and A. Mahendra and Deshavath Venkateswara Naik and Yenugu Chenna Kesava Reddy and Sagili GangaMaheswara Reddy},
        title = {A Data-Driven Hybrid Framework for Automobile Insurance Fraud Detection using Evidential Reasoning and Random Forest Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {4910-4918},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186816},
        abstract = {Automobile insurance fraud continues to cause sub- stantial financial loss to insurers worldwide, and existing expert- driven rule-based systems struggle to adapt to evolving fraud behavior. This paper proposes a hybrid data-driven framework integrating Evidential Reasoning (ER) with a Random Forest (RF) classifier for enhanced automobile insurance fraud detec- tion. The ER mechanism transforms expert-defined indicators into belief distributions, providing interpretable reasoning for fraud likelihood, while the RF model learns complex patterns from historical claim records to improve predictive performance. A cost-sensitive learning strategy is incorporated to address class imbalance without altering the original dataset distribution. Ex- perimental evaluation on a benchmark dataset and a real-world automobile insurance dataset demonstrates that the proposed ER–RF hybrid model achieves higher accuracy, improved F1- score, and reduced false positives compared to traditional ER or standalone machine learning techniques. This integration enables a more reliable and intelligent fraud detection system suitable for modern insurance analytics},
        keywords = {Evidential Reasoning, Random Forest, Hybrid Fraud Detection, Automobile Insurance, Cost-Sensitive Learning, Machine Learning},
        month = {November},
        }