Simplify the method of decision tree: an example for surface modeling
Xumin Liu, Houkuan Huang, Weixiang Xu · 2005
Classification is an important problem in data mining. Given a database of records, each with a class label, a classifier generates a concise and meaningful description for each class that can be used to classify subsequent records. A number of popular classifiers construct decision trees to generate class models. In this paper, the idea of algorithm for building a decision tree is introduced by comparing the algorithm of information gain or entropy. According to the theory of rough sets, the method of constructing decision tree is discussed. The produced process of decision tree is given as an example of surface modeling. Compared with ID3 algorithm, the complexity of decision tree is decreased, the construction of decision tree is optimized the better rule of data mining could be built.