Note that when doing a prediction with DSS visual ML, in most algorithms, DSS will use scikit-learn's capabilities for rebalancing by setting appropriate instance weights.
When I convert the model settings to python code, I found no parameters were set for rebalancing samples. Of course the code is not exactly the same as the one used to build the model but It would be nice that we have this option in "Design" tab. Many business use cases deal with rare events.
