Theoretical Study of Decision Tree Algorithms to Identify Pivotal Factors for Performance Improvement: A Review

摘要: tree is a data mining technique used for the classification and forecasting of data. It supervised learning algorithm that follows greedy approach works in top down manner. Decision uses white box model classifies hierarchical structure. makes easy to represent understand. can handle large database well with both numerical categorical variables. A variety decision algorithms are proposed literature like ID3 (Iterative Dichotomiser 3), C4.5 (successor ID3), CART (Classification Regression tree), CHAID (Chi-squared Automatic Interaction Detector). These have specific mechanisms based on certain criteria's. The study these criteria important requisite analysis DT algorithms. aim this paper identify inspect vital criteria's or factors major contribution review provide path select factor improvement as per requirement problem.