Hybrid Ensemble of classifiers using voting

Today ensemble learning techniques became more interested in the field of predictive modelling. It is an effective technique which combines various learning algorithms so as to improve the overall prediction accuracy. The Ensemble technique works on a philosophy that a group of experts gives more accurate decisions as compared to a single expert. Ensemble modelling combines the set of classifiers to create a single composite model which is better in accuracy. In this paper we proposed a hybrid ensemble classifier that combines the representative algorithms of Instance based learner, Naïve Bayes Tree and Decision Tree Algorithms using voting methodology. We apply this ensemble classifier on 28 bench mark dataset. The ensemble is also compared with the Naive Bayes, Rule Learner, Decision Tree, Bagging and Boosting Algorithms.