Parallel learning for per-segment models / transforms #478
d-a-bunin
started this conversation in
Improvements
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Description
Currently, per-segment models / transforms aren't using parallel computation. It could improve the performance and make them more applicable if there are a lot of segments.
Thoughts
Implementation should take into account the possible contention with parallel backtest.
Related
Beta Was this translation helpful? Give feedback.
All reactions