Hello,
I'm developing a custom prediction model using AI Builder.
My dataset is unbalanced, the label is binary and only 5% of the records contain the positive class (the one I want to predict).
How can I train a model like this using AI Builder?
Oversampling? Generating syntetic data?
Thanks a lot, I had already read it 🙂
Hi @WebPortal
Here's our documentation to create your custom model
Overview of the prediction model - AI Builder | Microsoft Learn
Create a prediction model - AI Builder | Microsoft Learn
Hope it helps
Regards
Philippe