AWS Launches Machine Learning Tool for Business Metrics
To give organizations better insight into their internal metrics, Amazon Web Services (AWS) has launched a tool that uses machine learning to spot and diagnose sudden anomalies in business data.
Amazon Lookout for Metrics is now generally available through the AWS console, according to an announcement. Customers can also work with AWS partners for more customized deployments of the service.
Amazon Lookout for Metrics is designed to track patterns in a business' key performance indicators (KPIs) -- for example, revenue, usage rates, page views and so on -- and identify the causes of major changes. It's meant to be an improvement over traditional business intelligence (BI) platforms, which often rely on arbitrarily set ranges to define what's normal for a particular KPI. If a range is too narrow, the solution might overlook a problem; too wide, and it can create false alarms. Moreover, the ranges may not be regularly adjusted according to changing business cycles.
As a result, according to AWS, analyzing and rectifying anomalies using traditional BI methods can be time-consuming. "[C]atching and diagnosing anomalies in metrics can be challenging, and by the time a root cause has been determined, much more damage has been done than if it had been identified earlier," said Swami Sivasubramanian, head of Amazon Machine Learning for AWS, in a prepared statement.
The machine learning technology powering Amazon Lookout for Metrics promises to reduce that time investment.
"Machine learning offers a compelling solution to the challenges posed by rule-based methods because of its ability to recognize patterns in vast amounts of information, quickly identify anomalies, and dynamically adapt to business cycles and seasonal patterns," according to AWS.
Amazon Lookout for Metrics currently works with 19 "popular" data sources, including AWS services like Amazon S3, Redshift, RDS and CloudWatch, as well as third-party services like Salesforce. The tool "automatically inspects and prepares the data, selects the best suited machine learning algorithm, begins detecting anomalies, groups related anomalies together, and summarizes potential root causes," AWS said. It also ranks anomalies by their expected impact so users can make informed decisions about what to address first.
Users can set up alerts and automate their responses to anomalies using Amazon Simple Notification Service (SNS) and AWS Lambda, or third-party services like PagerDuty or Slack.
"We're excited to deliver Amazon Lookout for Metrics to help customers monitor the metrics that are important to their business using an easy-to-use machine learning service that takes advantage of Amazon's own experience in detecting anomalies at scale and with great accuracy and speed," Sivasubramanian said.
More information on Amazon Lookout or Metrics, including pricing, is available here.
Gladys Rama is the senior site producer for Redmondmag.com, RCPmag.com and MCPmag.com.