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{187784,
        author = {Ms. Sana Mohammad Sadique Shaikh},
        title = {AI Based Transaction Anomaly and Fraud Detection System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {6688-6697},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187784},
        abstract = {The rapid growth of digital payments has significantly increased the number of fraudulent online transactions. Traditional fraud detection systems rely on predefined rules, which makes them ineffective in identifying new, complex, and evolving fraud patterns. To address this challenge, this research proposes an AI-based Transaction Anomaly and Fraud Detection System that analyzes user behavior, spending patterns, temporal features, merchant categories, and location-based signals to detect suspicious activities. The system utilizes machine learning and anomaly detection techniques, including Isolation Forest and XGBoost, to classify transactions and assign a risk score. Additionally, explainable AI methods are integrated to provide the reason behind each flagged transaction, ensuring transparency and trust. A dashboard is designed for real-time monitoring, visualization, and decision-making. This work aims to build a scalable, accurate, and intelligent fraud detection framework suitable for banking and financial sectors. Implementation and evaluation of the proposed model will be carried out in subsequent phases.},
        keywords = {Fraud Detection, Anomaly Detection, Machine Learning, XGBoost, Risk Scoring},
        month = {November},
        }