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{191012,
        author = {Vedangi Kulkarni},
        title = {Fraud Detection in Financial Transactions Using Graph AI},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {6766-6771},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191012},
        abstract = {The exponential growth of online financial transactions has escalated the challenges posed by sophisticated fraudulent activities. Traditional rule-based fraud detection systems suffer from scalability issues and high false positive rates, which impair timely and accurate detection. This paper presents a novel fraud detection framework utilizing Graph Artificial Intelligence (Graph AI) to model transaction networks and extract relational features indicative of fraud. Transactions are represented as graphs where nodes correspond to users or accounts and edges represent financial transactions. Machine learning classifiers, particularly Extreme Gradient Boosting (XGB), are trained on graph-derived features to identify fraudulent activities. The framework includes interactive visualization tools to assist fraud analysts in exploring complex transaction relationships. Experimental evaluation on labelled transaction datasets achieved a 96% classification accuracy with reduced false positives. The system is designed for scalable, real-time deployment in banking and fintech environments, addressing the critical need for efficient, adaptive fraud detection. Future work will focus on integrating Graph Neural Networks and explainable AI to further enhance performance and transparency.},
        keywords = {Fraud Detection, Graph AI, Transaction Graph, Machine Learning, NetworkX, Visualization, Real-Time Scalability.},
        month = {January},
        }