I am using Gradient Boosted Trees for my dataset. The process output shows the Performance Vector which gives the accuracy and confusion matrix, and Gradient Boosted Model which gives the model metrics, Confusion matrix, Variable importance, model summary and scoring history. But both the confusion matrix are different. Which should confusion matrix should I consider to evaluate my model?
Solved! Go to Solution.
the confusion matrix in the model are _training_ errors. So you should usually work on the Performance Vector, not the Gradient Boosted Model values. These are sometimes interesting to have a look on overfitting (e.g. add more complexity or not).
> These are sometimes interesting to have a look on overfitting (e.g. add more complexity or not).
True, but in general I am in the school of "just forget training errors completely". They create more damage than anything else
Have a nice weekend,