Onboarding and Preprocessing

Once per week we perform a full scan of all the metrics, to determine which series are producing data, and at which frequency and how often the value changes. This step also onboards new environments and new resources connected to the machine learning pipeline. Data are then downsampled and smoothened to ensure the best anomaly detection.

Onboarding

• Onboarding environments and metrics

Data resolution

• Anomaly detection frequency and smoothning - the best resoltion for the anomaly detection is determioned based on the unique behaviour of each metric