“CloudWatch applies machine-learning algorithms to the metric’s past data to create a model of the metric’s expected values”
https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/CloudWatch_Anomaly_Detection.html
How does this work?
– Rik
“CloudWatch applies machine-learning algorithms to the metric’s past data to create a model of the metric’s expected values”
https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/CloudWatch_Anomaly_Detection.html
How does this work?
– Rik
Although new to AWS, other logging software (Splunk, SumoLogic) have had this type of thing for years. They don’t usually disclose publicly what the underlying techniques are, but it will be something along the lines of these.
This is exactly the business of Grok, which uses NuPIC.
