Real-Time Credit Card Fraud Detection Using Optimized XGBoost with Intelligent Pattern Adaptation

P. U. Anitha, N. Sowmiya, P. Mathiyalagan, V. Padmapriya, B. Veera Sekharreddy, Bala Murugan M.

2025

Abstract

A realtime fraud detection system is proposed by applying a tuned XGBoost model in high-frequency credit card transactions. The model can dynamically adjust to changing fraud activities with the help of dynamic feature selection and threshold adjusting mechanism. A thorough evaluation on benchmark datasets demonstrates its better detection accuracy, less false positives, and faster decision-making performance than classical ensemble and deep learning methods. The system has also interpretability capabilities that can improve transparency and trust of automated systems for financial decisions, making the system feasible for deployment at scale in real-world financial infrastructure.

Paper Citation

in Harvard Style

Anitha P., Sowmiya N., Mathiyalagan P., Padmapriya V., Sekharreddy B. and M. B. (2025). Real-Time Credit Card Fraud Detection Using Optimized XGBoost with Intelligent Pattern Adaptation. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 608-614. DOI: 10.5220/0013870200004919

in Bibtex Style

@conference{icrdicct`2525,
author={P. Anitha and N. Sowmiya and P. Mathiyalagan and V. Padmapriya and B. Sekharreddy and Bala M.},
title={Real-Time Credit Card Fraud Detection Using Optimized XGBoost with Intelligent Pattern Adaptation},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25},
year={2025},
pages={608-614},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013870200004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - Volume 1: ICRDICCT`25
TI - Real-Time Credit Card Fraud Detection Using Optimized XGBoost with Intelligent Pattern Adaptation
SN - 978-989-758-777-1
AU - Anitha P.
AU - Sowmiya N.
AU - Mathiyalagan P.
AU - Padmapriya V.
AU - Sekharreddy B.
AU - M. B.
PY - 2025
SP - 608
EP - 614
DO - 10.5220/0013870200004919
PB - SciTePress