Improvement accuracy for C۴.۵ decision tree algorithm

The decision tree is indeed the most widely used approach to represent classifiers. Initially, it has been studied in the field of decision theory and statistics. However, it was found to be effective in other disciplines, such as data mining, machine learning and pattern recognition. This research deals with the problem of finding the parameter settings of the decision tree algorithm in order to achieve higher accuracy for a given domain. The proposed approach, Improved C۴.۵ (IC۴.۵), is a supervised learning model based on the C۴.۵ algorithm to construct a decision tree. The modification to the C۴.۵ algorithm includes using improved gain instead of the gain ratio measure to choose the best attribute and increase the accuracy of the decision tree. The introduced algorithm has been experimented with on some data sets from the UCI repository. The results obtained from experiments show that the accuracy of IC۴.۵ is greater than C۴.۵ in increasing the accuracy of the decision tree.

کلیدواژه ها:

Decision Tree ، Data Mining ، C۴.۵ Algorithm ، IC۴.۵ ، Accuracy ، Classifiers