0
$\begingroup$

Bellow I have a Learning Curve plot How should I interpret this plot for my random forrest algorithm (the second one the most complex one)? Which one is the best?

enter image description here

enter image description here

enter image description here

$\endgroup$
  • $\begingroup$ Evaluating a random forrest tree algorithm doesn't make much sense, because the implementation in SPSS and R is working nearly perfect. If the learning curve error is too big, it's the fault of the input data, which aren't normalized. $\endgroup$ – Manuel Rodriguez Oct 19 '19 at 12:33
1
$\begingroup$

Note the X index is training set size. For the first and second case, teh training set size starts at 0(or 1). The model will overfit certainly at that data size. When data size increases, the model overfits less and less and eventually the model have enough data samples that it won't overfit. The data size continue to increase and the model performance increase as well. To a certain point, the validation loss increase start to diminish and the model slightly overfits the samples. For the third graph, it seems like originally teh loss is low and started to increase. Hopes it help

| improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.