Posted On: Dec 8, 2020

Amazon Lookout for Metrics uses machine learning (ML) to detect anomalies, or unexpected changes in your metrics, helping you proactively monitor the health of your business, diagnose issues and find opportunities quickly – with no ML experience required. 

Organizations of virtually every size use data to monitor trends and changes in their metrics to find unexpected anomalies, such as a dip in product sales or a sudden increase in qualified sales leads. Finding these anomalies is challenging. Traditional rule based methods look for data that falls outside of arbitrary ranges, which results in too many false alarms if the range is too narrow or missed anomalies if the range is too broad. These ranges are also static, and don’t change based on time of the day, day of the week, or seasons, and need to be manually updated frequently. When anomalies do get detected, developers, analysts, and business owners can spend weeks trying to identify the root cause of the change, before they can take any meaningful action. 

Amazon Lookout for Metrics automatically connects to 19 different data sources, including popular AWS services such as S3, CloudWatch, Redshift and RDS, and SaaS applications such as Salesforce, Marketo and Amplitude, to continuously monitor metrics that you care about. It detects anomalies with high accuracy by using the ML algorithm that’s best suited for your data, leading to lower false alarms and fewer cases of missed anomalies. Amazon Lookout for Metrics groups related anomalies together, and ranks them by severity, so that you can focus on what matters the most. It provides you with actionable results by highlighting potential root causes of anomalies. It sends you alerts through channels such as SNS, Datadog, PagerDuty, Webhooks and Slack, or triggers custom actions using Lambda, enabling you to resolve an issue or react to an opportunity quickly. It also uses your feedback on detected anomalies to automatically tune the results and improve accuracy continuously. 

Customers like NextRoll, Playrix, and Digitata are already using Amazon Lookout for Metrics, and seeing improvements in accuracy, fewer false alarms and faster time to resolution compared to existing solutions. See details about their usage of Lookout for Metrics here

Amazon Lookout for Metrics Preview is available starting today in the AWS console, via the AWS SDKs, and the AWS CLI in the following regions: Northern Virginia, Ohio, Oregon, Dublin, and Tokyo. You can request access to the preview here. See the AWS Region Table for more details.