End-to-end user journeys for time series forecasting models
This document describes the user journeys for BigQuery MLtime series forecasting models, including the statements and functions thatyou can use to work with time series forecasting models.BigQuery ML offers the following types of time seriesforecasting models:
Model creation user journeys
The following table describes the statements and functions you can use to createtime series forecasting models:
| Model type | Model creation | Feature preprocessing | Hyperparameter tuning | Model weights | Tutorials |
|---|---|---|---|---|---|
ARIMA_PLUS | CREATE MODEL | Automatic preprocessing | auto.ARIMA1 automatic tuning | ML.ARIMA_COEFFICIENTS | |
ARIMA_PLUS_XREG | CREATE MODEL | Automatic preprocessing | auto.ARIMA1 automatic tuning | ML.ARIMA_COEFFICIENTS | |
| TimesFM | N/A | N/A | N/A | N/A | Forecast multiple time series |
1The auto.ARIMA algorithm performs hyperparameter tuning for the trend module. Hyperparameter tuning isn't supported for the entire modeling pipeline. See themodeling pipeline for more details.
Model use user journeys
The following table describes the statements and functions you can use toevaluate, explain, and get forecasts from time series forecasting models:
1You can input evaluation data to theML.EVALUATE functionto compute forecasting metrics such as mean absolute percentage error (MAPE).If you don't have evaluation data, you can use theML.ARIMA_EVALUATE function to output information about themodel like drift and variance.
2TheML.EXPLAIN_FORECAST function encompasses theML.FORECAST function because its output is a superset of theresults ofML.FORECAST.
Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2026-02-18 UTC.