Free Trial

Weekly Challenges

Solve the challenge, share your solution and summit the ranks of our Community!

Also available in | Français | Português | Español | 日本語
IDEAS WANTED

Want to get involved? We're always looking for ideas and content for Weekly Challenges.

SUBMIT YOUR IDEA

Challenge #24: ARIMA Time Series

DavidLane
8 - Asteroid

Had not used the ARIMA time series predictive tool before so this was a nice intro.

 

Spoiler
DavidLane_0-1590322871394.png

 

jarrod
ACE Emeritus
ACE Emeritus

Forecasts are spot on, but the min/max's are off a bit.. 

Spoiler
jarrod_0-1590607483697.png

Need to average annual and monthly for back filling null months.

Lucatelli
8 - Asteroid

Please find attached my proposed solution.

iakovidc
7 - Meteor
Spoiler
challenge 24.PNG
maazinh
8 - Asteroid

Kept wondering why my values were off by a bit until I read the comments!

mattreynolds
9 - Comet

Dusted off the ol' econometrics book. Was able to get very close, but not spot on to the expect output. Checked against the solution - possibly a difference between versions?

neilgc
5 - Atom

Hi All,

 

This is my first weekly challenge submission!

 

 

I did each step quite broken out but would probably go back and reduce the steps if this was a production model. Also, I found that I had to order the data to get the right predictions, and set the number of units as an integer (which makes sense because you can't have non-whole units).

 

Spoiler
flow.PNGresult.PNG

 

 

treepruner
9 - Comet

Looks like if you have decimals in the averages your forecast will be a little different. Makes real world sense, but I'm too lazy to change it now...

treepruner
9 - Comet

I don't quite match the results, but I think it is because I have fractional units in my averages

FlorianC
Alteryx
Alteryx

As others have mentioned, I had to update the expected results with the values from the solution file in order to get the output data to match.

 

Spoiler
WorkflowWorkflow
Florian Carrier
Strategic Solution Consultant
Alteryx