An overview of fuzzy and non-fuzzy decision trees

The science of data mining has been introduced with the expansion of database systems and the high volume of data stored in these systems, in order to identify useful patterns in the data and help users to make important decisions by providing information. In data mining science, fuzzy set theory has played an important role and has given rise to "fuzzy data mining". Numerous studies have been conducted in the field of fuzzy data mining. In this article, the role of fuzzy topic in decision trees has been studied.Decision trees are one of the most common methods of learning with the observer. But if the data has shortcomings and problems such as confusion, low sample size, low accuracy, personal evaluation, etc., the decision tree will not be efficient enough. In addition, other problems, such as the presence of large continuous or discrete numerical properties, will affect the performance of these trees. In cases where the decision tree fails, an alternative approach is to combine fuzzy logic with decision trees. The result is fuzzy decision trees.It should be noted that unlike classical data mining, fuzzy data mining currently does not have criteria consisting of fuzzy data sets for comparing algorithms.The present article examines the concept of decision trees and fuzzy logic and then defines the combination of these two concepts, the fuzzy decision tree, and discusses its applications and importance.