Prediction and detection analysis of bank credit card fraud using regression model: novel approach.

Abstract

financial institutions are interested in ensuring security and quality for their customers. Banks, for instance, need to identify and stop harmful transactions in a timely manner. In order to detect fraudulent operations, data mining techniques and customer profile analysis are commonly used. Thus, we propose EVA, a Visual Analytics approach for supporting fraud investigation, fine-tuning fraud detection algorithms, and thus, reducing false positive alarms. Due to the theatrical increases of fraud which results in loss of dollars worldwide each year, several modern techniques in detecting fraud are persistently evolved and applied to many business fields. The goal of this paper is to provide a security in credit card transaction using EVA technique to detect fraud. The credit card fraud detection features uses user behavior and location scanning to check for unusual patterns.

Nowadays, the use of credit cards has significantly increased on both online and offline purchases because of the fast growth of the e-commerce and online banking system. When Someone uses other persons credit card for personal benefit without the knowledge of the owner of the credit card is known as credit card fraud. The Association of Certified Fraud Examiners defines a fraud as "the use of one’s occupation for personal enrichment through the deliberate Misuse or application of the employing organization’s resources or assets" [63]. Individual’s and government suffer large financial losses across the world every year due to the lack of sophisticated fraud detection system.