Abstract: Fast Development in electronic trade has led to increase in the use of credit card payment mode. Frauds related to credit cards are also increase with usage of credit card payment mode. Data mining techniques are used to disclose fraudulent activity in credit card payment mode. Data mining process is to extract information from a dataset and transform it into an understandable structure for future use. Clustering method is used for dividing the objects in such way that objects in same group are more similar to each other than to those in other groups. In this paper, we are using hybrid approach that comprise of k-means clustering and that followed by Distance based techniques that detect outliers from dataset. The experimental results show the comparison of actual dataset accuracy and accuracy of proposed with dataset.

Keywords: Fraud detection, Credit card fraud, clustering, hybrid approach.