A Decision Tree Algorithm Combined with Linear Regression for Data Classification

Along with the enormous development of computer systems and the fast spread of internet, data processing and analysis have become a significant concern. Different soft computing techniques of data analysis have been introduced to extract valuable information from data. These techniques applied in different areas and reflected useful promising results. In this paper, a novel decision tree algorithm combined with linear regression is proposed to solve data classification problem. The proposed method is applied to Turkey Student Evaluation and Zoo datasets that are taken from UCI Machine Learning Repository and compared with other classifier algorithms in order to predict the accuracy and find the best performing classification algorithm. The results show that the proposed method performs better than all other algorithms.