ABSTRACT: This study primarily focused on detecting credit card fraud in the real world. For the qualified data set, we must first collect credit card data sets. Then, based on the user's responses, deliver inquiries to test the data set, use a credit card. Following the random forest algorithm employing a classification approach with a data set that has previously been examined and supplying a current data set. Finally, the data accuracy of the outcomes is improved. After then, a number of attributes will be processed so that fraud detection can be noticed when looking at the graphical model's depiction. Credit Card Fraud Detection is a typical sample of classification. In this process, we have focused on analyzing and pre-processing data sets as well as the deployment of multiple anomaly detection algorithms such as Local Outlier Factor and Isolation Forest algorithm on the PCA transformed Credit Card Transaction data.
|
DOI:
10.17148/IJARCCE.2021.106108
