Data mining classification experiments with decision trees over the forest covertype database

The paper exposes the behavior of the Decision Trees (DT) algorithms on a big database with many cases and many attributes: Forest Covertype (FC) from UCI Knowledge Discovery in Databases Archive. In classification experiments considered have been taken into account 22 splitting criteria and two pruning methods whose performances were presented in terms of classification error rate on test data, data completely unknown on decision tree induction, and in terms of number of decision rules. The results of the experiments were compared with the results obtained from over 100 other algorithms in the literature that were used on the same FC database.