What about class imbalance in training data?

[kbenoit]

Are there specific strategies in keras to deal with class imbalance in the training set? or any recommendations about models to be aware of when this is a problem? Many classification problems are for rare outcomes, >= 5% of the cases.

[dougmet]

I would say class imbalance is the same in keras as with any machine learning problem. So you can down/up sample outside of keras (potentially with something like {rsample}) and feed in directly. Happy to hear about other ways to do this. Maybe there’s some generator that I don’t know about yet.

[dougmet]

Nearest I could find in google https://imbalanced-learn.readthedocs.io/en/stable/generated/imblearn.keras.BalancedBatchGenerator.html but it would need some reticulating for R.