The ML.ARIMA_COEFFICIENTS function

ML.ARIMA_COEFFICIENTS function

The ML.ARIMA_COEFFICIENTS function lets you see the ARIMA model coefficients. This function only applies to the time series model.

ML.ARIMA_COEFFICIENTS returns the following columns:

  • time_series_id: the identifier of a time series. Only present when forecasting multiple time series at once. The column name and type are inherited from the TIME_SERIES_ID_COL option as specified in the model creation query.
  • ar_coefficients (ARRAY<FLOAT64>): the autoregressive coefficients, which corresponds to non-seasonal p.
  • ma_coefficients (ARRAY<FLOAT64>): the moving-average coefficients, which corresponds to non-seasonal q.
  • intercept_or_drift (FLOAT64): the constant term of the ARIMA model. By definition, the constant term is called “intercept” when non-seasonal d is 0, and “drift” when non-seasonal d is 1. It is always 0 when non-seasonal d is 2.

ML.ARIMA_COEFFICIENTS syntax

ML.ARIMA_COEFFICIENTS(MODEL `project_id.dataset.model`)

Where:

  • project_id: your project ID
  • dataset: the BigQuery dataset that contains the model
  • model: the name of the model

ML.ARIMA_COEFFICIENTS examples

The following example retrieves the model coefficients information from mymodel in mydataset. The dataset is in your default project.

SELECT
  *
FROM
  ML.ARIMA_COEFFICIENTS(MODEL `mydataset.mymodel`)