Knowledge Extraction from Support Vector Machines

Abstract

Support Vector Machines have been a promising tool for data mining during these years because of its good performance. However, a main weakness of SVMs is its lack of comprehensibility: people cannot understand what the “optimal hyperplane” means and are unconfident about the prediction especially when they are not the domain experts. In this section we introduce a new method to extract knowledge with a thought inspired by the decision tree algorithm and give a formula to find the optimal attributes for rule extraction. The experimental results will show the efficiency of this method.