Posted On: Jun 3, 2022

Amazon Lookout for Metrics announces the launch of backtesting when using Amazon CloudWatch as a data source connector. Backesting is a new anomaly detection mode you can now select when setting up your detector. You can seamlessly connect to your data in CloudWatch to set up a highly accurate anomaly detector across metrics, dimensions, and namespaces of your choice. Amazon Lookout for Metrics uses machine learning (ML) to automatically detect and diagnose anomalies (outliers from the norm) without requiring any prior ML experience. Amazon CloudWatch provides you with actionable insights to monitor your applications, respond to system-wide performance changes, optimize resource utilization, and get a unified view of operational health.

Previously, when you select CloudWatch as a data source, you were only able to detect anomalies on continuous data. With this launch, you can now use historical data in CloudWatch to analyze detected anomalies in the past, as well as setting up a continuous anomaly detector. You can simply select the new backtest mode or select the continuous mode while configuring you data to get started.

To learn more about this capability, read through our blog here or see our documentation page. You can use this capability in all Regions where Amazon Lookout for Metrics is publicly available. For more information about Region availability, see AWS Regional Services.