Say I am using Xgboost on a binary classification task. eval_metric is one of the model parameter. How should I think about the impact of using different eval_metric(e.g rmse/mae/logloss) in general? Is there a guide on using each of them under different scenario?
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
Which metric to choose is not related to the model, but to the problem to be solved. If you are unsure, go back and think about the objective - why we need to build the model, and what the model needs to achieve. Base on this understanding we then pick a metric, or craft our own.
