0
$\begingroup$

I'm working on a logistic regression model in order to model a relationship and am facing a class-imbalance problem (way too many 0's and not enough 1's). In order to resolve this, I'm planning to use the SMOTE algorithm to create a more balanced dataset.

My question is: Once I model the relationship and generate probabilities from each of the coefficients, do I need to do any further transformations since I fixed the class-imbalance?

That is, do I need to "re-adjust" the "adjusted" model since the coefficients are modeled off of simulated values? Or can I just apply the interpretation from the balanced model?

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.