Applied Taxonomy Techniques Intended for Strenuous Random Forest Robustness

Globalization and economic trade has change the scrutiny of facts from data to knowledge. For the same purpose data mining techniques have been involved in copious real world applications. This paper illustrates appraisal of assorted data mining techniques on diverse data sets. There are scores of data mining techniques for prediction and classification obtainable, this article includes most prominent techniques: J48, random forest, Na ve Bayes, AdaBoostM1 and Bagging. Experiment results prove robustness of random forest classifier by conniving accuracy, weighted average value of ROC and kappa statistics of various data sets