The ML.ARIMA_COEFFICIENTS function

This document describes theML.ARIMA_COEFFICIENTS function, which lets yousee the ARIMA coefficients and the weights of the external regressors forARIMA_PLUS andARIMA_PLUS_XREG time series models.

Syntax

ML.ARIMA_COEFFICIENTS(  MODEL `PROJECT_ID.DATASET.MODEL`)

Arguments

ML.ARIMA_COEFFICIENTS takes the following arguments:

• PROJECT_ID: your project ID.
• DATASET: the BigQuery dataset that containsthe model.
• MODEL: the name of the model.

Output

ML.ARIMA_COEFFICIENTS returns the following columns:

• time_series_id_col ortime_series_id_cols: a value that contains theidentifiers of a time series.time_series_id_col can be anINT64 orSTRING value.time_series_id_cols can be anARRAY<INT64> orARRAY<STRING> value. Only present when forecasting multiple time seriessimultaneously. The column names and types are inherited from theTIME_SERIES_ID_COL option as specified in the model creation query.
• ar_coefficients: anARRAY<FLOAT64> value that contains the autoregressivecoefficients, which corresponds to non-seasonal p.
• ma_coefficients: anARRAY<FLOAT64> value that contains the moving-averagecoefficients, which corresponds to non-seasonal q.
• intercept_or_drift: aFLOAT64 value that contains the constant term ofthe ARIMA model. By definition, the constant term is calledintercept whennon-seasonal d is0, anddrift when non-seasonal d is1.intercept_or_drift is always0 when non-seasonal d is2.
• processed_input: aSTRING value that contains the name of the modelfeature input column. The value of this column matches the name of thefeature column provided in thequery_statement clausethat was used when the model was trained.
• weight: when theprocessed_input value is numerical,weight contains aFLOAT64 value and thecategory_weights column containsNULL values.When theprocessed_input value is non-numerical and has been converted todummy encoding, theweight column isNULL and thecategory_weightscolumn contains the category names and weights for each category.
• category_weights.category: aSTRING value that contains the categoryname if theprocessed_input value is non-numeric.
• category_weights.weight: aFLOAT64 that contains the category's weightif theprocessed_input value is non-numeric.

SELECT*FROMML.ARIMA_COEFFICIENTS(MODEL`mydataset.mymodel`)

• For information about model weights support in BigQuery ML, seeBigQuery ML model weights overview.
• For more information about supported SQL statements and functions for timeseries forecasting models, seeEnd-to-end user journeys for time series forecasting models.