A framework for fraud detection system in automated data mining using intelligent agent for better decision making process

In global world fraud detection is one of the major problem and it is increasing every year. The statistical report of global economy says that nearly 30% of multi level people have been suffered by fraud in past year [1]. The term fraud involves one or more than one people, where they deliberately act secretly to take away some one valuable thing for their benefit. The statement fraud is as old as human being but it takes various forms with irrespective to situation. In recent days, the development of new technologies and techniques is also one of the victim advantages for criminals to commit fraud [2]. The investigators investigating techniques are mostly a traditional based methods of data analysis have long been used for fraud detection. Frauds are happened based on instance or incidents, but they are repeated offences using some methods (old and new), instances are more similar in content and appearance but they are non-identical while comparing. Fraud deduction is one of difficult process not only technically, but also in crime investigations. The method of fraud detection is based on simple comparisons, but also based on association, clustering, perdition and outlier detections. In consideration of these techniques this, paper proposed an automated fraud detection frame work is proposed to identify the fraud using intelligent agents, data fusion techniques and various data mining techniques.