Submit Your Manuscript Online

Detecting Credit Card Frauds Using KPCA with Classification Methods

	International Journal of Scientific Research and Engineering Development (IJSRED)	Full Text:
	Published Issue : Volume-4 Issue-1
	Year of Publication : 2021
	Unique Identification Number : IJSRED-V4I1P107
	Authors :Sumira Jabin, Hamid Ghous
	: Click Here | DOI : Update Soon

Abstract :

Regardless of various techniques adopted for credit card fraud detection. Credit card frauds are increasing day by day. Credit card fraud detection is a serious issue and incurs loss to financial institutions and customers. As credit card has become a popular method of payment. There are various ways to steal money like skimming, stealing card and making duplicate card. This study has tried to find out and make a review that how these frauds could be detected using different techniques. Different methods have used till now to tackle this issue. Some of these are classification techniques like Artificial Neural Network, Biological Neural Network and Outlier Detection. But instead of all this it has observed that the credit card frauds are increasing, that has caused a great loss to banks and customers. Due to imbalanced and high dimensional data sets fraud detection in the field of credit card became difficult and ambiguous. Our main objective is to find a way to detect credit card frauds using feature selection and classification methods. In this study, we are using Kernel Principal Component Analysis (KPCA) as a feature selection method with decision tree and boost as classification methods. We have found better and improved results than the previous studies.