Using the time series forecasting model

To use our BigQuery ML model, we'll use the ML.FORECAST function to specify the parameters for the prediction.

The query will extract all the fields produced by the forecast function that accepts the following parameters:

• The model name, `08_sales_forecasting.liquor_forecasting`, preceded by the keyword MODEL.
• A STRUCT that includes the horizon of the forecast: 30 days and the confidence_level chosen for the prediction – in this case, 80%:

  SELECT
    *
  FROM
    ML.FORECAST(MODEL `08_sales_forecasting.liquor_forecasting`,
                STRUCT(30 AS horizon, 0.8 AS confidence_level)); 

The execution of the query generates the records shown in the following screenshot:

Figure 8.14 – The results generated by the forecast function

We can notice in Figure 8.14 that the predictions are chronologically...