Currently working on a finance dataset which has more than 20 input variables with high imbalance.
[Apparently, the target variable is also imbalanced (for this I am currently considering to handle it using class_weights parameter of scikit-learn)]
5
-
$\begingroup$ What is the type of your variables? Can you provide a concrete example of an imbalance of such variables? $\endgroup$– EduardCommented Jan 27, 2023 at 11:00
-
1$\begingroup$ Why do anything for either the inputs or the target? $\endgroup$– DaveCommented Jan 27, 2023 at 11:16
-
$\begingroup$ @Eduard all of them are categorical. $\endgroup$– bh7781Commented Jan 27, 2023 at 14:49
-
$\begingroup$ @Dave wouldn't you treat class imbalance differently? $\endgroup$– bh7781Commented Jan 27, 2023 at 14:50
-
$\begingroup$ Imbalance of what, and why is it a problem? // Statistics sees minimal problem with target imbalance, yet apparent myths persist. Please refer to this question for details on why and this for additional links. $\endgroup$– DaveCommented Jan 27, 2023 at 14:59
Add a comment
|