It deals with minimization of problem posed by the old magnetic stripe card technology. For this purpose we are using EMV (Euro pay -Master card-Visa) chip card design in the credit card business. This EMV chip card technology efficiently deduces the conflicts and problems in the old magnetic stripe card method. There must be detection methods available like fall back in which the technology will fail. WEKA is a data mining tool which is used to classify the transaction tool. In this existing work the Naive Bayes machine learning classifier tries to predict a class which is known as outcome class based on probabilities, and also conditional probabilities of its occurrence from the training data.This kind of learning is very efficient, fast and high in accuracy for real-world scenarios ,and also this learning type is known as supervised learning. In the credit application domain, changing legal behavior is exhibited by communal relationships and can be caused by external events. This means legal behavior can be hard to distinguish from fraud behavior, but it will be shown later in this work that they are indeed distinguishable from each other. The detection system needs to exercise caution with applications which reflect communal relationships. It also needs to make allowance for certain external events. This work is meant for improving the credit card fraud detection. This proposed work is made up of various important facts.