Paper Contents
Abstract
Credit card fraud is a major and rising threat, particularly with the advent of e-commerce and online transactions in the modern day. The implications of identity theft and financial losses caused by such malicious activities might affect millions of individuals worldwide, posing a huge danger to the banking industry. The efficiency of fraud detection in credit card transactions is significantly influenced by the data set measurement method, variable selection, and detection algorithms employed. Information extraction is crucial in detecting online payment fraud, as are the strategies employed to address this issue. This study assesses the performance of the K-Nearest Neighbor algorithm on heavily distorted credit card fraud data. These procedures are evaluated using measures including accuracy, sensitivity, precision, and specificity. The results show K-Nearest Neighbor have optimum accuracy percentages of 96.91%, respectively.
Copyright
Copyright © 2024 J Rosary Nancy. This is an open access article distributed under the Creative Commons Attribution License.
