I'm using Databricks AutoML for time series forecasting, and I would like to include additional feature columns in my model to improve its performance. The available parameters in the databricks.automl.forecast() function primarily focus on the target_col and time_col. Although there is an identity_col parameter for multi-series forecasting, it doesn't seem to be intended to specify additional feature columns directly.
Is there a way to make Databricks AutoML consider additional feature columns when training the forecasting model? If not, what are the best practices for incorporating additional features to enhance my time series forecast using Databricks AutoML? Any suggestions or workarounds would be greatly appreciated.
Thank you!
