Is there any guide on how to include a list of exogenous variables for transfer learning?
And is it possible to make the model flexible enough such that the pre-trained model can receive varying number of exogenous variables?
For example, during training, I may train it with 5 exogenous variables. However when predicting the model, for reasons like missing data, I may only have up to 3 exogenous variables while the other 2 are missing completely.
09/05/2023, 5:32 PM
Hi @Afiq Johari! We have the following tutorial for exogenous variables: https://nixtla.github.io/neuralforecast/examples/exogenous_variables.html.
Models will always need to receive the same set of features, you can't reduce or increase the number of features. One alternative for your case is masking the missing variables (with 0s for example, but might depend on the values they can normally take). Also, train the models adding cases where some variables are missing (similar to dropout), following the behavior of missing data in the new domain.