ETS Time series
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Mute
- Printer Friendly Page
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Notify Moderator
Hi,
I am using an ETS forecast container followed by a TS Forecast container connected to the O part of the previous ETS.
My dataset contains data from 2010 month 1 to 2017 to month 9, I am doing a monthly prediction, but the ETS forecast begins the forecast output from 2015 year month 11 instead of 2017 month 10, it always ignores the last 21 records in the input dataset. I tried removing and adding few rows and saw that it always neglects the last 21 rows. How do I fix it>
Solved! Go to Solution.
- Labels:
- Input
- Predictive Analysis
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Notify Moderator
Hello @goutamgm92,
I'm having trouble reproducing this. Is there any chance you can share your workflow? Options => Export Workflow
Thanks!
Hoss Carroll
Customer Support Engineer
Alteryx
Customer Support Engineer
Alteryx
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Notify Moderator
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Notify Moderator
Hey @goutamgm92,
I think I've got it figured out! While the forecast is correct, the Period and Sub_Period fields are returning the wrong values because the Series starting period is not set. After setting this value to 2002 and 10, the first period that is forecast becomes 2017 month 8. The updated workflow has been attached.
Set series starting period
Let me know if this does not resolve your issue!
Hoss Carroll
Customer Support Engineer
Alteryx
Customer Support Engineer
Alteryx
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Notify Moderator
Helfull, Thank you
it resolved my issue with Period and Sub_Period being random to exactly what it should be
