Abstract

As a result of the growing IT and producing methods and collecting data, it is admitted that today the data can be warehoused faster in comparison with the past. Therefore,  knowledge discovery tools are required in order to make use of data mining. Data mining is typically employed as an advanced tool for analyzing the data and knowledge discovery. Indeed, the purpose of data mining is to establish models for decision. These models have the ability to predict the future treatments according to the past analysis and are of the exciting areas of machine learning and adaptive computation. Statistical analysis of the data uses a combination of techniques and artificial intelligence algorithms and data quality information. To utilize the data mining applications, including the commercial and open source applications, numerous programs are currently available.

In this research, we introduce data mining and principal concepts of the decision tree method which are the most effective and widely used classification methods. In addition, a succinct description of the three data mining software, namely \textit{SPSS-Clementine}, \textit{RapidMiner} and \textit{Weka} is also provided. Afterwards, a comparison was performed on 3515 real datasets in terms of classification accuracy between the three different decision tree algorithms in order to illustrate the procedure of this research. The most accurate decision tree algorithm is \emph{Decision Tree} by 92.49\% in \emph{Rapidminer}.

This work is licensed under a Creative Commons Attribution 4.0 License.