0

I'm working with a really imbalanced binary classification dataset so I decided to use SMOTE for only on the train data. Class rates were 95% -5% before SMOTE and 75-25% after SMOTE. In other words, I achieved a class balance ratio of 3: 1 (majority class: minority class). But I could not find any scientific evidence that indicates how much this ratio of class imbalance should be. In several studies, it has been said that 3: 1 imbalance ratio is sufficient, but is there any article you can recommend to me on class imbalance ratio?

Thank you.

Berke Akkaya
  • 1
  • 1
  • Unbalanced classes are almost certainly not a problem, and oversampling will not solve a non-problem: [Are unbalanced datasets problematic, and (how) does oversampling (purport to) help?](https://stats.stackexchange.com/q/357466/1352) – Stephan Kolassa May 22 '21 at 19:27

0 Answers0