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{204520,
        author = {Shraddha A Dhikle and Pradnya S Aher and Ashok P Bhadane},
        title = {A Real-Time Credit Card Fraud Detection Framework using Differential Transformation-Based Feature Updating and Stream Mining Techniques.},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {2890-2893},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204520},
        abstract = {Real-time credit card fraud detection is a critical challenge in modern financial systems due to rapidly evolving transaction behaviours and highly imbalanced datasets. Traditional machine learning models fail to adapt efficiently in streaming environments. This paper proposes a deterministic mathematical framework based on a Differential Transformation-based feature updating operator integrated with stream mining techniques. The model introduces a recursive feature evolution system that captures temporal variation, drift magnitude, and uncertainty using entropy-based enrichment. The framework is supported by theoretical proofs of boundedness, stability, and convergence. Lyapunov stability analysis, complexity evaluation, and ablation studies are included to validate robustness. The proposed system is evaluated using real-world-inspired datasets and streaming simulations, demonstrating high accuracy and strong adaptability in dynamic fraud environments},
        keywords = {Fraud detection, stream mining, differential transformation, Lyapunov stability, entropy, online learning, feature evolution},
        month = {June},
        }