Forecasting results widely variation
Open
question
- Dominant language
- Python
- Stars
- 20.4k
- Forks
- 4.6k
- Avg merge
- 19h 52m
- Merged PRs (30d)
- 1
Description
Hi,
I'm currently facing a problem with the forecasting results with prophet. With the same version environment (prophet 0.7.1) my predictions are widely varying in different computers. When I execute only in my computer (windows) the results have a minimum variation. When executing on databricks or linux, the results have a huge variation with a huge RMSE between the predicted datasets?
Any thoughts what can be causing this?
Contributor guide
Assessment
This issue has not been assessed yet.