Time Series - With Future Feature Value Input

Hi Folks,

I was wondering if there is a way to have a time series forecast but to input some predicted feature values (from user), to see the impact a change in the value of that feature value would have on the prediction.

For example, lets say the price of a commodity price was to go up to X. See what the impact of that would be based on inventory and everything else. So we can input the future feature value as X and let the model use that in it’s calculation.

Best regards,
Seamus

Hi @Seamus_McMahon

Welcome to the TensorFlow Forum!

Please refer to the TF Tutorial on Time series forecasting and Working with RNNs for this scenario which might be helpful to you.