Year: 2025
Type: conference-paper
Abstract: Credit card fraud presents a risk to businesses and their clients. To combat security breaches, organizations implement different administrative and technical security controls to protect their data. With the increasing use of online transactions, organizations implement fraud detection systems. In this paper, we propose a novel credit card fraud detection system that integrates K-Nearest Neighbors and Naive Bayes machine learning algorithms. It educates employees on adherence to company guidelines and enhances their ability to handle cyber threats. The proposed system examines online transactions and notifies administrators of suspicious transactions to act. The system is trained and tested on a dataset of 188 transactions. It achieved 94.3% accuracy, 94.4% sensitivity, and 94.1% specificity. The research findings demonstrate effectiveness of the proposed system in improving e-commerce security and safeguarding businesses and customers from this risk.
Institutions: Shenandoah University, Higher Colleges of Technology
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4411550147