Copyright © 2025 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{162663,
        author = {Dr. V. Dhanakoti and R. Maanasa and P. Mohan Kumar and B. Muthu Kiruba},
        title = {Analytiguard: Pioneering Data Analytics For Proactive Credit Card Fraud Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {10},
        number = {10},
        pages = {673-678},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=162663},
        abstract = {Credit card fraud detection is a critical challenge in today's digital economy, where fraudulent activities can easily hide among numerous legitimate transactions. This paper presents a novel approach that leverages a random forest classifier along with a web-based interface to enhance the accuracy and efficiency of credit card fraud detection. Unlike traditional methods, our approach incorporates a unique representation of each transaction based on a user's past behaviors, allowing for more accurate pattern recognition. Additionally, we introduce enhancements to the classifier, including a time-aware gate, a current-historical attention module, and an interaction module, which improve the model's ability to detect fraudulent actions. Our results demonstrate that our proposed system achieves an impressive accuracy rate of 93%, outperforming existing methods commonly used for fraud detection. Furthermore, we provide a user-friendly web-based interface, which allows for easy access and interpretation of the detection results, enabling financial institutions to take timely actions against fraudulent activities.
Moreover, our methodology incorporates several enhancements to the random forest classifier, each designed to bolster its efficacy in detecting fraudulent activities. These enhancements include a time-aware gate, which accounts for temporal dynamics in transactional data, a current-historical attention module, which prioritizes recent transactions while considering historical patterns, and an interaction module, which captures complex relationships between various transactional features. Collectively, these refinements empower the classifier to more accurately identify anomalous patterns indicative of fraudulent behavior.
},
        keywords = {Credit card fraud detection, Random forest classifier, Web-based interface, Pattern recognition, Time- aware gate, Current-historical attention module, Interaction module, Accuracy.},
        month = {},
        }