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.
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 thetarget_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 thetarget_column_name
.
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
.