We have tested our system metrics (CPU, Memory,Disk IO........etc) with the new version of elasticsearch machine learning system(Version-6.2.3)
As per your documentation we understood that the boundary conditions are calculated dynamically it will be wider in the beginning and get refined as more data comes in.
we would like to know the details on the following,
Is it is possible to have a static threshold limit set as lower and upper boundary limit values? we want to apply this logic for some of our system metrics.
Is it possible to have a feedback mechanism incorporated into ES Anomaly system?. User will provide the feedback on the anomalies detected by ES is actually an anomaly or not. the ES machine should take this feedback input into consideration while predicting the future anomalies.
Thanks in advance.