Learning Higher Accuracy Decision Trees from Concept Drifting Data Streams

摘要

In this paper, we propose to combine the naive-Bayes approach with CVFDT, which is known as one of the major algorithms to induce a high-accuracy decision tree from time-changing data streams. The proposed improvement, called CVFDTnbc, induces a decision tree as CVFDT does, but contains naive-Bayes classifiers in the leaf nodes of the induced decision tree. The experiment using the artificially generated time-changing data streams shows that CVFDTnbc can induce a decision tree with more accuracy than CVFDT does.