What is the best way to deal with imbalanced data for XGBoost? [closed]

Question

There are a lot of way to deal with class-imbalanced data like undersampling, oversampling, changing cost function etc.

https://machinelearningmastery.com/tactics-to-combat-imbalanced-classes-in-your-machine-learning-dataset/

Here is the post talking about them all.

I am working with an imbalanced multiclass classification problem and trying to solve it using XGBoost algorithm. I wanted to understand which method works best here. Since XGBoost already has a parameter called weights (which gives weight to each train record), would it be wise to directly use it instead of undersampling, oversampling, writing a cost function etc.?

Answer 1

I think using something like this could help in your case.

• https://github.com/dmlc/xgboost/blob/master/demo/kaggle-higgs/higgs-train.R#L17
• http://xgboost.readthedocs.io/en/latest/how_to/param_tuning.html

Hope this helps at least a bit!