0

I want to train a binary classifier but I have an expected unbalanced dataset (90%/10%). Should I train an unbalanced dataset or to downsample the first class? This ratio is natural and will be always present in my data for prediction.

kjetil b halvorsen
  • 77,844
snowflake
  • 103
  • 1
    See suggestions here: http://stats.stackexchange.com/questions/220026/can-a-classifier-trained-with-oversampled-data-be-used-to-classify-unbalanced-da/220116#220116 – DaL Sep 20 '16 at 06:17

1 Answers1

1

Try and see which works better.

Given that you have a training set, a validation set and a metric that you want to optimize, you can answer all sorts of questions like this by simply trying.

psarka
  • 1,150