Real-Time Credit Card Fraud Detection Using AdaBoost
Journals Fringe Multi-Engineering Proceedings · 2025
DOI: 10.69996/fmep.2025019 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journals Fringe Multi-Engineering Proceedings, 2025. Verfasst von Navya Sri Neelam und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Strong and smart detection systems are required to combat credit card fraud, which is a major problem for online retailers and banks. In order to enhance classification performance on extremely unbalanced datasets, this work presents an enhanced fraud detection model that integrates the AdaBoost algorithm with an AHMV ensemble technique. The approach integrates multiple base classifiers and applies a voting mechanism that enhances the sensitivity and precision of fraud detection, thereby minimizing false positives. The AHMV model beats conventional individual classifiers in every experimental metric (accuracy, recall, precision, and F1-score) when tested on publicly accessible credit card datasets. Apt for use in real-time fraud monitoring systems, the suggested framework guarantees strong detection capabilities while preserving computing economy. A trustworthy and scalable solution to the ever-changing credit card fraud protection scenario is brought to light by this effort.
Zitieren
APA
Neelam, N. S., & N, R. R. (2025). Real-Time Credit Card Fraud Detection Using AdaBoost. Journals Fringe Multi-Engineering Proceedings. https://doi.org/10.69996/fmep.2025019
Vancouver
Neelam NS, N RR. Real-Time Credit Card Fraud Detection Using AdaBoost. Journals Fringe Multi-Engineering Proceedings. 2025. doi:10.69996/fmep.2025019
BibTeX
@article{Neelam2025,
author = {Neelam, Navya Sri and N, Ramana Reddy},
title = {Real-Time Credit Card Fraud Detection Using AdaBoost},
journal = {Journals Fringe Multi-Engineering Proceedings},
year = {2025},
doi = {10.69996/fmep.2025019}
}
EUVIMED