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{196364,
        author = {Mr.M Ramakrishna Raju and J.S.Sathvika Gayathri Devi and B.Durga Harshitha and D.G.Anvesh Varma and K.Rohith},
        title = {Online Payment Transaction Analysis and Risk Insights},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {3222-3226},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196364},
        abstract = {The rapid expansion of digital payment systems and the parallel rise in sophisticated financial fraud. While digital transactions offer speed, convenience, and global accessibility, they also create opportunities for cybercriminals engaging in unauthorized transactions, phishing, identity theft, and account takeovers. Traditional rule-based fraud detection systems—though once effective—are increasingly inadequate because they rely on static rules and historical patterns. These systems struggle to detect evolving fraud tactics, leading to higher false positives that inconvenience legitimate users and false negatives that allow fraudulent activities to go undetected.
To address these limitations, the content presents a machine learning-driven fraud detection framework that processes large-scale transaction data through stages such as data cleaning, feature engineering, and advanced classification modelling. Algorithms like Logistic Regression, Random Forest, and XGBoost are evaluated for their ability to identify complex fraud patterns, with ensemble methods—particularly XGBoost—showing superior performance. Unlike static rule-based systems, machine learning models adapt continuously to new fraud trends and assign dynamic risk scores to transactions, enabling real-time decision-making. Overall, the approach strengthens digital payment security by improving detection accuracy, reducing fraud losses, and enhancing customer trust in modern financial systems.},
        keywords = {Online Payments, Fraud Detection, Machine Learning, Risk Analysis, Transaction Monitoring, Financial Security},
        month = {April},
        }