classification-with-unbalanced-data-resized-600

Imbalanced Learning

Introduction by Yi:

Since everyone is working with machine learning, the reading group for the next week would be about imbalanced learning.

Required Reading:

Take-home message:

You have to be careful when you generate new data to make sure they follow the original distribution. There is a bias with ROC curves when your data is imbalanced, PR curves are better.

Leave a Reply

Your email address will not be published. Required fields are marked *