An array of time ranges to exclude from use when the anomaly detection model is trained. Use this to make sure that events that could cause unusual values for the metric, such as deployments, aren't used when CloudWatch creates the model.

The metric dimensions to create the anomaly detection model for.

An array of metric data query structures that enables you to create an anomaly detector based on the result of a metric math expression. Each item in <code>MetricDataQueries</code> gets a metric or performs a math expression. One item in <code>MetricDataQueries</code> is the expression that provides the time series that the anomaly detector uses as input. Designate the expression by setting <code>ReturnData</code> to <code>true</code> for this object in the array. For all other expressions and metrics, set <code>ReturnData</code> to <code>false</code>. The designated expression must return a single time series.