An implementation of decision tree algorithm augmented with regression analysis for fraud detection in credit card

Hammed, Mudasiru and Soyemi, Jumoke (2020) An implementation of decision tree algorithm augmented with regression analysis for fraud detection in credit card. International Journal of Computer Science and Information Security (IJCSIS), 18 (2). pp. 79-88.

[img] Text
An_Implementation.pdf

Download (1MB)

Abstract

Credit card fraud is a common crime committed with the aid of credit card to defraud people of their funds during transaction. The intension of fraudsters most times is to obtain goods without payment or to get funds from unauthorized accounts. Of recent, the use of credit card to complete transactions is on the rise because of the introduction of online shopping and banking. Although, there are several fraud detection systems proposed by previous studies, yet, credit card fraud is still on the increase. Some techniques used in detecting credit card fraud have been compromised due to improvement in technology. Many studies that used decision tree to build detector system did not use regression analysis. This study presented a decision tree algorithm augmented with regression analysis to build a very strong fraud detector system. The system covers all areas in terms of monitoring and reporting fraud in credit cards. The analysis of result here shows that this technique is 81.6% accurate with 18.4% misclassification error and the system successfully verified all the injected intrusions used for the purpose of testing.

Item Type: Article
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Engineering, Science and Mathematics > School of Electronics and Computer Science
Depositing User: Dr J. Soyemi
Date Deposited: 03 Jun 2020 11:05
Last Modified: 03 Jun 2020 11:05
URI: http://eprints.federalpolyilaro.edu.ng/id/eprint/363

Actions (login required)

View Item View Item