Hello I have 50 time series that I am predicting using Arimas models, however I want to know if anyone knows how to optimize the flow, since each model uses different parameters for an arima, I have chosen to create flow lines for each series, no se si es posible crear a line of code that allows me to create everything in a more optimized way.
I appreciate any suggestion
This is an image as I have the flow now, the first thing I do is filter the store of a joint base and then I predict with R
if when talking about optimization you are thinking less nodes then you can use loop and have this sequence of nodes only once. From what you said seems that Group Loop Start node is node (loop) you need. Inside a loop you’ll have to parametrize nodes using flow variables. Keep in mind that loop will run one store at the time meaning execution time will increase compared to current, parallel, execution.
It’s so interesting the topic that you’ve shared. However I’m glad to know that it’s possible.
I need to learn about this nodes, it’s the first time that I’m going to use them,
This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.