Hi, I have a few questions related to Forecast stage:
Can we update the model or retrain the model after testing phase of Forecast stage?
During the evaluation phase of Forecast stage, what if the code fails? e.g. API error, connection issue, change of data format, and other unexpected things that do not happen during testing phase
You will only be able to update and retrain the model during the testing phase. Once the testing phase ends and the evaluation phase begins, models should not be changed.
There will be ways to address unexpected issues, such as rerunning failed jobs or allow limited fixes that do not substantively change the model. More details about this will be provided later.