A Hybrid Classification Approach Based on Decision Tree and Naïve Bays Methods

Data classification as one of the main tasks of data mining has an important role in many fields. Classification techniques differ mainly in the accuracy of their models, which depends on the method adopted during the learning phase. Several researchers attempted to enhance the classification accuracy by combining different classification methods in the same learning process; resulting in a hybrid-based classifier. In this paper, the authors propose and build a hybrid classifier technique based on Naïve Bayes and C4.5 classifiers. The main goal of the proposed model is to reduce the complexity of the NBTree technique, which is a well known hybrid classification technique, and to improve the overall classification accuracy. Thirty six samples of UCI datasets were used in evaluation. Results have shown that the proposed technique significantly outperforms the NBTree technique and some other classifiers proposed in the literature in term of classification accuracy. The proposed classification approach yields an overall average accuracy equal to 85.70% over the 36 datasets.