Vol. 3, Issue 6, Part C (2017)

Abstract
Classification is an important data mining task with broad applications to classify the various kinds of data used in nearly every field in our day to day life. Classification is used to classify each item according to the features of the item with respect to the predefined set of classes or groups. In this paper we focus on the performance evaluation based on the correct and incorrect instances of data classification using Naïve-Bayes, J48 and Random Forest classification algorithms. Naïve-Bayes algorithm is based on probability. J48 algorithm is based on decision tree and Random Forest is a way of averaging multiple deep decision trees. This work deals with comparative evaluation of classifiers NAÏVE-BAYES, J48 AND RANDOMFOREST in the context of dataset to maximize true positive rate and minimize false positive rate using WEKA tool. Experimental results shows that the Random forest algorithm achieves an accuracy of 94.50% for the CAR dataset