Advanced Machine Learning Models for Detecting Credit Card Fraud

B. Vijaya Bhaskar Reddy, Kawser Naaz Shaik, Neelima Bakkanarappagari, Jaisnavi Pami Reddy Gari, Jahnavi Reddy Vanna

2025

Abstract

Issues of bank cards fraud detection still represents a huge challenge for financial institutions which increasingly have to deal with more and more complex actions of crimineity. This work takes up this challenge by harnessing the power of algorithms to make detection systems more efficient. We use a Kaggle dataset to develop the following five models and compare them together: LSTM network, CNN-based neural network, Decision Tree, Random Forest, and Stacking Classifier. CNNs are used to learn complex patterns from transaction data, while LSTM model sequential relationships and temporal patterns. Decision Trees and Random Forests offer strong classification through cascaded decisions, combined with ensemble learning. Furthermore, a Stacking Classifier combines these algorithms well to possibly have better overall performance. The objective of comparison of these methods is to compares the best method for realtime fraud detection. It is anticipated that the outcome of the project will make a substantial contribution to making credit card transaction systems more secure, so as to reduce financial losses and to promote consumer confidence.

Paper Citation

in Harvard Style

Reddy B., Shaik K., Bakkanarappagari N., Gari J. and Vanna J. (2025). Advanced Machine Learning Models for Detecting Credit Card Fraud. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 290-299. DOI: 10.5220/0013912000004919

in Bibtex Style

@conference{icrdicct`2525,
author={B. Reddy and Kawser Shaik and Neelima Bakkanarappagari and Jaisnavi Gari and Jahnavi Vanna},
title={Advanced Machine Learning Models for Detecting Credit Card Fraud},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={290-299},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013912000004919},
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 - ICRDICCT`25
TI - Advanced Machine Learning Models for Detecting Credit Card Fraud
SN - 978-989-758-777-1
AU - Reddy B.
AU - Shaik K.
AU - Bakkanarappagari N.
AU - Gari J.
AU - Vanna J.
PY - 2025
SP - 290
EP - 299
DO - 10.5220/0013912000004919
PB - SciTePress