0
$\begingroup$

Suppose my data is a time series with multiple features such as wind, temperature, holidays, etc.. and I'm predicting a target variable Y. After I go through the whole process of splitting data into training and test and after having good predictions/forecasts I save my model.

Can I now give extra information as input to my model? If I want to predict tomorrow's Y values and I know the wind and temperature forecasts (from weather services) for tomorrow, can't I use them to get a better prediction for tomorrow?

$\endgroup$
1
$\begingroup$

Yes, by customizing the model with new information. But, you have to run atleast one training, with complete cycle and export output.

the general example from tensorflow is here

$\endgroup$
1
  • 1
    $\begingroup$ Can you provide any example/reference where something similar is being done? $\endgroup$ – Numbermind Dec 7 '20 at 16:06

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.