2

In this article http://xgboost.readthedocs.io/en/latest/model.html under the caption Tree Ensemble, the diagram shows 3 prediction score under the 3 nodes, +2, +0.1, and -1. How were these numbers derived? The article gave no clue.

bhomass
  • 557
  • I believe they are just for illustration. You compute the predictions from the regression trees in a gradient booster in the same way as any other regression tree: as the mean of y over all the training samples share the same leaf node as the given sample point. – Matthew Drury Jul 23 '17 at 22:25
  • https://stats.stackexchange.com/questions/353406/what-are-the-final-predictions-in-tree-based-models .. please answer here if you found it – figs_and_nuts Jun 27 '18 at 14:40

0 Answers0