A decision tree construction approach:two-step forward is better than one
Hua Ji · Journal of Shandong University · 2010
In order to increase the probability of finding the global optimum,a novel decision tree construction algorithm adopting the two-step forward idea was proposed based on the C4.5 algorithm. The algorithm was more likely to get the global optimum of a classification task because it considered information gained from selecting two attributes simultaneously,rather than the information gained from just selecting an optimal single attribute.Experimental results on 10 UCI benchmark data sets showed that it outperforms C4.5.