The following forecasting and anomaly detection functions and updates are

## Feature Feature The following forecasting and anomaly detection functions and updates are[generally available](https://cloud.google.com/products#product-launch-stages)(GA): * The[AI.DETECT\_ANOMALIES function](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-ai-detect-anomalies)supports providing a custom context window that determines how many of the most recent data points should be used by the model. * The[AI.FORECAST function](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-ai-forecast)supports specifying the latest timestamp value for forecasting. * The[AI.EVALUATE function](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-ai-evaluate)supports the following: * You can provide a custom context window that determines how many of the most recent data points should be used by the model. * The function outputs the[mean absolute scaled error](https://en.wikipedia.org/wiki/Mean%5Fabsolute%5Fscaled%5Ferror)for the time series. ## Feature Feature You can now create BigQuery [non-incremental materialized views over Spanner data](https://docs.cloud.google.com/bigquery/docs/materialized-views-create#spanner)to improve query performance by periodically caching results. This feature is[generally available](https://cloud.google.com/products/#product-launch-stages) (GA).