Dealing with Imbalanced Classes in Machine Learning
Published in
5 min readFeb 2, 2018
Introduction
Most real-world classification problems display some level of class imbalance, which is when each class does not make up an equal portion of your data-set. It is important to properly adjust your metrics and methods to adjust for your goals. If this is not done, you may end up optimizing for a meaningless metric in the context of your use case.