Combining Decision Treesusing Systematic Patterns

摘要

Tree ensemble or combining methods that use re-sampling techniquernhave been highlighted recently in Statistical classification and Data mining.rnIn this paper, we propose a new ensemble method in decision trees that utilizesrnsystematic patterns of classification. The new method improved thernprediction accuracy of a single decision tree algorithm. It is also observedrnthat this method performs reasonably well with fewer number of re-samplesrncompared to the popular Bagging or Boosting methods. An experiment withrnreal dataset is carried out to see the performance of the new method.