Decision Trees

explains about the similarities and how to measure. which is the best split? based on SSE and GINI (good info about gini here).
  • For classification the Gini cost function is used which provides an indication of how “pure” the leaf nodes are (how mixed the training data assigned to each node is).
Gini = sum(pk * (1 – pk))
  • Early stop - 1 sample per node is overfitting, 5-10 are good
  • Pruning - evaluate what happens if the lead nodes are removed, if there is a big drop, we need it.



  1. 1.
    One is based on cost sensitive learning.
  2. 2.
    Other is based on a sampling technique


  1. 1.
    A comparison between random forest and extra trees Fig. 1: Comparison of random forests and extra trees in presence of irrelevant predictors. In blue are presented the results from the random forest and red for the extra trees. The results are quite striking: Extra Trees perform consistently better when there are a few relevant predictors and many noisy ones