After blending multiple queries from several databases I'm producing a table that shows aggregate metrics at the monthly level. When attempting to use the ARIMA and TS Forecast tools I'm only getting the overall forecast results and not broken out by metric. I would like to have a 6 month forecast for each metric seprately. I've attached a sample spreadsheet of what my table looks like after the union. Thanks in advance for the help (still new at using the R Tools).
Solved! Go to Solution.
Could you generate six models (one for each metric) and forecasts for each, then join them together for comparisons, etc?
Thanks for the quick response @JohnJPS. I suppose I could but was hoping to avoid this because the forecast would only be a small portion of the overall report. Essentially, I will be pulling in 30+ metrics, building the table in Alteryx, exporting to .TDE, build Tableau dash, run extract refresh on Alteryx server, and generate snapshot report via email for Stakeholders at a weekly or monthly cadence.
Is there a way to parse by field name (in my case the metric) when building the model? If not, I can try the solution you had mentioned. Thank you.
Very high level, (responding via mobile phone) -- could you transpose the metric names into a single "metric" field, then turn your model/forecast flow into an iterative macro that grabs the next set of "metric" and feeds only that into the forecast?
Thanks @JohnJPS. This is a very good idea. I will give it a try. Thank you!