If we want to apply a classification model to imbalanced data we should
- Apply weights to the classes or use a cost matrix.
- Use the metrics more robust to imbalance, for example the AUC PR better than the AUC ROC, and the Phi MCC better than the F1, and the F1 better than the Accuracy.
Should we use only one of these recommendations or both simultaneously?
if we are using the AUC_PR… Do we still need to apply weights to the input?
and vice versa
if we are using weights… Is it still recommended to use the AUC_PR instead of the Accuracy?
Is it more important to properly weight the classes or use the proper metric/score?