@SeanAdams I didn't know lizards could give such advise.
Hey there Sean,
I think that I saw one of your posts on the Slack forum about lesson 3 of ARIMA models from Udacity. Is that you taking that certification or is someone else using the same name and last name?
If you are, probably you completed the certification by now; I am also enrolled into that certification and almost done.
:-) Hey @JORGE4900 - you're absolutely right about the Udacity course - finished this about a month ago. I must say, the team did a great job of this course ( @PatrickN) - and I'd recommend this to anyone who has not used the predictive tools.
Good luck with the final pieces Jorge, and thank you for mentioning this!
No wonder your name seemed familiar @SeanAdams.
I am about to go into the 7th lesson just before the capstone project. Have you already put into practice some of these techniques at work? I immediately started doing a linear regression model to calculate prices on some pieces of equipment at my work and modified the workflow to project dynamic monthly prices for the next 12 months depending on changing variables; however, this model has not been adopted by the company despite its accuracy and usefulness.
Here's my solution.
I'm a little confused by this one... I went the macro route to score each product type. Based on that I chose my model and did another model to get the forecast. The scoring is already a little odd - all forecasts look alright, except for bakery which is just flat. Then when I run the forecast all numbers are flat other than produce. The same happened when I ran the solution - doesn't look anything like the solution in the start file. @ChristineB - I know this is an old challenge, but is there any reason you know of why me running your solution file on my computer could produce different results? The last screenshot below is from me running the solution workflow.
I've added a new start file and solution to this challenge to address the changes to Time Series calculations with the ARIMA tool since version 2018.2 (with an accompanying upgrade to the version of R used in the predictive tools). I've attached them to this post and provided additional instructions on the challenge description.
@ChristineB. It looks like you're from the future! Your solution and macros were developed with 2018.3. I put on my CSE hat, figured out how fix the version info on all 3 and also updated the paths to the macros in the .yxmd. The revised package is attached.
It looks like @kat's concerns are still valid though. When using ARIMA, the forecasts are still flat for most of the products. Any idea why this might be?
Kat. How are you progressing with the challenges? This is 125 for me.