RBR models tend to give Downstream error or loads late for the first time after delay like 15 min.
Custer feels RBR is unstable and inconsistent which is reducing the use of RBR model.
Where as ML model does not show any such issues, Ideally we need long term fix and RBR Model should perform , instant load and hold model in memory.
I feel Rule based model team should release long term solution which will help a lot.
Why is it useful?
|Who would benefit from this IDEA?||Any customer who wants to use RBR model for on the fly annotations|
How should it work?