Machine Learning is the technology, in which algorithms which are capable of learning from previous cases and past experiences are designed. It is implemented using various algorithms which reiterate over the same data repeatedly to analyze the pattern of data. The techniques of data mining are no far behind and are widely used to extract data from large databases to discover some patterns making decisions. This paper presents the Naïve Bayes improved K-Nearest Neighbor method (NBKNN) for Fraud Detection of Credit Card. Experimental results illustrate that both classifiers work differently for the same dataset. The purpose is to enhance the accuracy and enhance the flexibility of the algorithm.