This paper provides a comprehensive survey of decision tree classifier (DTC) methodology, highlighting their advantages and potential issues. DTCs are widely used in various fields such as radar signal classification, character recognition, and medical diagnosis due to their ability to break down complex decisions into simpler, interpretable steps. The paper discusses the design of DTCs, including tree structure design, feature selection, and decision rules. It explores different approaches to tree structure design, such as top-down, bottom-up, hybrid, and growing-pruning methods. The paper also addresses the challenges of feature selection, decision rules, and search strategies, and discusses other related issues like incremental tree design, tree generalization, missing data handling, robustness, and the relationship between decision trees and neural networks. Finally, it concludes with future research directions and remarks on the potential of DTCs.This paper provides a comprehensive survey of decision tree classifier (DTC) methodology, highlighting their advantages and potential issues. DTCs are widely used in various fields such as radar signal classification, character recognition, and medical diagnosis due to their ability to break down complex decisions into simpler, interpretable steps. The paper discusses the design of DTCs, including tree structure design, feature selection, and decision rules. It explores different approaches to tree structure design, such as top-down, bottom-up, hybrid, and growing-pruning methods. The paper also addresses the challenges of feature selection, decision rules, and search strategies, and discusses other related issues like incremental tree design, tree generalization, missing data handling, robustness, and the relationship between decision trees and neural networks. Finally, it concludes with future research directions and remarks on the potential of DTCs.