This message was deleted.

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.