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{187481,
        author = {Joe Uzuegbu C. K},
        title = {Design and Implementation of an Intelligent Real-Time Credit-Card Fraud Detection and Response System Using Machine Learning and API-Based Event Streaming},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {6838-6845},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187481},
        abstract = {This study presents the design and implementation of an intelligent real-time credit-card fraud detection and response system that integrates machine learning (ML) and API-based event streaming. The system leverages ensemble learning models (Random Forest, Gradient Boosting, and Neural Network) deployed through an API-driven architecture for live transaction monitoring. By incorporating Apache Kafka for event streaming and FastAPI for inference serving, the framework achieves real-time performance, adaptability, and scalability. Preprocessing techniques, including normalization and synthetic minority oversampling (SMOTE), are applied to handle data imbalance and ensure model stability. Experimental results demonstrate that the ensemble model achieved an accuracy of 99.21%, with high precision and recall, outperforming individual classifiers. The system’s architecture demonstrates its capacity for low-latency response and continuous model improvement through feedback streaming, positioning it as a viable prototype for modern financial fraud prevention.},
        keywords = {Credit-card fraud detection, Machine learning, Event streaming, API-based architecture, Kafka, FastAPI, Ensemble learning, Real-time analytics.},
        month = {November},
        }