Class imbalance


This refers to data where the number of samples per class is not uniform.
For example, if you are trying to create a model to classify whether or not a customer will sign up for a service, in most cases, the number of customers who do not sign up will actually be larger than the number of customers who sign up out of the total sample.
VARISTA AI ML Knowledge Class Imbalance
If the number of samples is not uniform, it will have a bad effect on the generalization performance when classifying a small number of classes.
To solve the problem of unbalanced data, we can use techniques such as undersampling, oversampling, SMOTE (Synthetic Minority Over-Sampling Technique), and weighting.


VARISTAは機械学習モデルの開発、管理をノーコードで効率的に行うことができる新しいプラットフォームです。
データをお持ちでしたらすぐに始められますので、是非ともお試しください。

or

Made with
by VARISTA Team.
© COLLESTA, Inc. 2021. All rights reserved.