Splitting Method for Decision Tree Based on Similarity with Mixed Fuzzy Categorical and Numeric Attributes

Classification decision tree algorithm has an input training dataset which consists of a number of examples each having a number of attributes. The attributes are either categorical, when values are unordered or continuous, when the attribute values are ordered. No previous research has considered the induction of decision tree using a wide variety of datasets with different data characteristics. This work proposes a novel approach for learning decision tree classifier which can handle categorical, discrete, continuous and fuzzy attributes. The most critical issue in the learning process of decision trees is the splitting criteria. Our splitting approach is based on similarity formula as feature selection strategy by choosing the greatest similarity attribute as splitting node. An illustrative example is demonstrated in multiple test dataset to verify the validity of the proposed algorithm which is less affected by the type and the size of training dataset.