Documentation Home
HeatWave User Guide
Related Documentation Download this Manual
PDF (US Ltr) - 2.1Mb
PDF (A4) - 2.1Mb


HeatWave User Guide  /  ...  /  Forecasting Model Types

3.9.1 Forecasting Model Types

To review the list of supported forecasting models, see Forecasting Models.

As of MySQL 9.1.1, HeatWave AutoML supports the Orbit Model.

  • Currently, the HeatWave AutoML Orbit Model only supports Local Global Trend (LGT).

  • The Orbit Model supports exogenous variables as inputs.

  • It is a univariate forecasting model, so it only accepts one endogenous variable.

Univariate and Multivariate Models

Depending on the number of numeric columns that are used for training the model, you will need to use the appropriate model.

  • Univariate forecasting models support a single numeric column, specified as a JSON_ARRAY. This column must also be specified as the target_column_name, because that field is required, but it is not used in that location.

  • Multivariate forecasting models support multiple numeric columns, specified as a JSON_ARRAY. One of these columns must also be specified as the target_column_name.

Selecting Forecasting Models

To specify which models that are considered for training, use the model_list option and enter the appropriate model names. If only one model is set for model_list, then only that model is considered.

If the model_list option is not set, then ML_TRAIN will consider all supported models during the algorithm selection stage. If options includes exogenous_variables, all supported models will still be considered, including models that do not support exogenous_variables.

For example, if options includes univariate endogenous_variables with exogenous_variables, then ML_TRAIN will consider NaiveForecaster, ThetaForecaster, ExpSmoothForecaster, ETSForecaster, STLwESForecaster, STLwARIMAForecaster, SARIMAXForecaster, and OrbitForecaster. ML_TRAIN will ignore exogenous_variables if the model does not support them.

Similarly, if options includes multivariate endogenous_variables with exogenous_variables, then ML_TRAIN will consider VARMAXForecaster and DynFactorForecaster.

If options also includes include_column_list, this will force ML_TRAIN to only consider those models that support exogenous_variables.