Classification: Classification is the process of predicting the class of a new object from the set of predefined classes. To prepare classification model, dataset is divided in two parts. One part is designated as training dataset and other as testing dataset. Whole model is designed using training dataset and then its accuracy is measured by validating the classes in which it classifies the test dataset instances. For example, Naïve Bayes classifier [4] works by assuming that the attributes of the database are independent of each other. It counts to both positive and negative points. Being positive this assumption contributes to simplicity and speed. Being on negative side this assumption might be wrong which results is not considering the relationship among attributes. This algorithm requires a small set of training data for building the model.