A study on Credit Card Fraud Detection Methods using Genetic Algorithm

B. John; B. Jabber; V. Sudharshan

In Modern day the fraud is one of the major causes of great financial losses, not only for merchants, individual clients are also affected. The aim in this study is we develop a method which improves a credit card fraud detection solution currently being used in a bank .Improving a credit card fraud detection system using genetic algorithm three methods to detect fraud are presented. Firstly, cluster model is used to classify the legal and fraudulent transaction using data clusterization of regions of parameter value. Secondly, Gaussian model is used to model the probability density of credit card user’s past behavior to detect any abnormalities from the past behavior. Lastly, Bayesian networks are used to describe the statistics of a particular user. The main task is to explore different views of the same problem.

Select Volume / Issues:

• Volume 3 Issue 3, May 2012

Year:

2012

Type of Publication:

Article

Keywords:

Clustering; Bayesian Networks; Genetic Algorithm; abnormalities; Credit card Fraud Detection

Journal:

IJECCE

Volume:

3

Number:

3

Pages:

572-574

Month:

May