New AWS tool uses machine learning to watch your services and data for anomalies

New AWS tool uses machine learning to watch your services and data for anomalies

AWS has made available Amazon Lookout for Metrics, a service that uses machine learning (ML) to automatically monitor various metrics across business and operational data, detect anomalies and alert the user so they can take appropriate action.

According to AWS, Lookout for Metrics is based on technology used by Amazon itself in business operations, and so reflects 20 years of the firm’s experience in anomaly detection and machine learning. It was built to allow developers to set up autonomous monitoring of important metrics to detect anomalies and identify their root cause in a matter of few clicks. This, AWS claimed, would make it easier to diagnose the root cause of anomalies such as unexpected dips in revenue, high rates of abandoned shopping carts, spikes in payment transaction failures, or increases in new user sign-ups.

At launch, Lookout for Metrics supports 19 data sources, including Amazon S3, Amazon CloudWatch, the Amazon Relational Database Service (Amazon RDS), and Amazon Redshift, as well as widely used SaaS applications like Salesforce, Marketo, and Servicenow. Once configured, it automatically inspects data from the source, using ML to detect anomalies, groups related anomalies, and summarises potential root causes, AWS said. The service can also rank anomalies by severity so you can prioritise which issue to tackle first, the company added.

When configuring Lookout for Metrics, developers need to create detectors that observe data to find anomalies. This might be to monitor the availability of an application worldwide, or use a location field in the data as a dimension to monitor availability separately in each AWS Region or Availability Zone, for example.

The developer should set an interval from between five minutes and a day which determines how often the detector imports data and finds anomalies. Depending on the interval chosen, a detector could spend between a few hours and a few days learning about the data. Customers could also provide historical data to speed up the learning process.

Lookout for Metrics connects to notification and event services such as Amazon Simple Notification Service (Amazon SNS), Slack, Pager Duty, and AWS Lambda. Users can create customised alerts, or specify actions such as filing a support ticket or removing an incorrectly priced product from a retail website.

Once Lookout for Metrics begins returning results, users could then provide feedback on the relevancy of detected anomalies via the Lookout for Metrics console or the API provided. The service uses this feedback to continuously improve its accuracy over time, said AWS.

Lookout for Metrics is available now in a number of AWS Regions in the US, Europe and Asia. More details are available on the AWS Machine Learning blog.