Abstract: Now a days due to de-monetization everyone had started using credit cards for different types of transactions. So there will be a more chances for occurring fraud. Banks have many and enormous databases. Important business information can be extracted from these data stores. Fraud is an issue with far reaching consequences in the backing industry, government, corporate sectors and for ordinary consumers. Increasing dependence on new technologies such as cloud and mobile computing in recent years has encountered the problem. Physical detections are not only time consuming they are costly and they don’t give accurate results. Not surprisingly economic institutions have turned to automated process using numerical and computational methods. Traditional approaches relied on manual techniques such as auditing, which are inefficient and unreliable due to the difficulty of the problem. Data mining-based approaches have been shown to be useful because of their ability to identify small anomalies in large data sets. So we have used some of the supervised algorithms to detect the fraud which gives accurate results. There are many different types of fraud, as well as a variety of data mining methods, and research is continually being undertaken to find the best approach for each case. Financial fraud is a term with various potential meanings, but for our purposes it can be defined as the on purpose use of illegal methods or practices for the purpose of obtaining financial gain . Fraud has a large negative impact on business and society credit card fraud alone accounts for billions of dollars of lost revenue each year.

Keywords: Fraud detection, Financial fraud, Decision tree.