Query-Based Learning Decision Tree and its Applications in Data Mining

Abstract

Decision tree is one of the most significant classification methods applied in data mining. By its graphic output, users could have an easy way to interpret the decision flow and the mining outcome. However, decision tree is known to be time consuming. It will spend a high computation cost when mining the large scale dataset in the real world. This drawback causes decision tree to be ineligible in processing the time critical applications. In these years, we have introduced the query-based learning (QBL) method to different neural networks for providing a more effective way to learn the large dataset. These neural networks have achieved good clustering and classification results. In this paper, a novel mining scheme called QBLDT (query-based learning decision tree) is proposed to apply the QBL concept in decision tree construction. Experimental results show our proposed method is better than the traditional decision tree in different performance metrics. It makes learning quicker and can achieve better prediction results.