Decision Trees Generation Method Based on Relative Entropy
Gui Xian-cai · Computer Knowledge and Technology · 2009
Decision Tree is one of the most important method for datamining. In the process of constructing a decision tree, the choice of testing attribute will touch the depth and nodes of decision tree. A new decision trees generation method is presented based on relative en- tropy. The experiments show that, compared with the ID3,C4.5 method, the new method has less compute capacity and constructed deci- sion tree is concision with higher classify precision.