The increasing digitization of financial services, driven by cloud computing, fintech innovation, and real-time payment systems, has significantly amplified the complexity and scale of financial fraud. Traditional fraud detection approaches, including rule-based systems and conventional machine learning models, are often inadequate for capturing the relational and dynamic nature of modern fraud schemes. In response, this study proposes a hybrid graph-neural and generative artificial intelligence (AI) framework for real-time fraud detection in cloud-native financial systems. The proposed framework integrates three core components: a transaction graph modeling layer that represents financial interactions as dynamic graphs; a graph neural network (GNN) detection layer that captures complex relational patterns and identifies fraudulent behavior; and a generative AI explanation module that provides interpretable, natural-language explanations for flagged transactions. These components are deployed within a cloud-native, real-time processing architecture, enabling scalable, low-latency fraud detection across high-volume transaction streams. To evaluate the effectiveness of the framework, experiments were conducted using financial and synthetic datasets within a distributed cloud environment. The results demonstrate that the GNN-based model significantly improves fraud detection performance by effectively capturing network-level dependencies, while the generative AI module enhances interpretability and supports investigative decision-making. The system also achieves competitive real-time performance in terms of inference latency and throughput, highlighting its suitability for deployment in operational financial environments. However, the study identifies trade-offs between detection accuracy and system latency, as well as challenges related to computational complexity, data privacy, and model governance. Despite these limitations, the findings underscore the importance of integrating relational modeling, explainable AI, and cloud-native deployment in modern fraud detection systems. The proposed framework contributes to the advancement of intelligent financial security by offering a scalable, interpretable, and high-performance solution for detecting fraud in increasingly complex digital ecosystems.
Graph neural networks; generative artificial intelligence; fraud detection; financial transaction analysis; explainable AI; cloud computing; distributed systems; real-time analytics; anomaly detection; enterprise AI architecture.
International Journal of Trend in Scientific Research and Development - IJTSRD having
online ISSN 2456-6470. IJTSRD is a leading Open Access, Peer-Reviewed International
Journal which provides rapid publication of your research articles and aims to promote
the theory and practice along with knowledge sharing between researchers, developers,
engineers, students, and practitioners working in and around the world in many areas
like Sciences, Technology, Innovation, Engineering, Agriculture, Management and
many more and it is recommended by all Universities, review articles and short communications
in all subjects. IJTSRD running an International Journal who are proving quality
publication of peer reviewed and refereed international journals from diverse fields
that emphasizes new research, development and their applications. IJTSRD provides
an online access to exchange your research work, technical notes & surveying results
among professionals throughout the world in e-journals. IJTSRD is a fastest growing
and dynamic professional organization. The aim of this organization is to provide
access not only to world class research resources, but through its professionals
aim to bring in a significant transformation in the real of open access journals
and online publishing.