A Pruning Method Based on Conditional Misclassification
The methods of pruning have great influence on the effect of the decision tree. By researching on the pruning method based on misclassification, introduced the conception of condition misclassification and improved the standard of pruning. Propose the conditional misclassification pruning method for decision tree optimization and apply it in C4.5 algorithm. The experiment result shows that the condition misclassification pruning can avoid over pruned problem and non-enough pruned problem to some extent and improve the accurate of classification.
W. X. Xu et al., "A Pruning Method Based on Conditional Misclassification", Applied Mechanics and Materials, Vols. 44-47, pp. 3448-3452, 2011