Outlier Detection Models are the simplest form of anomaly detector.

Unlike value-predicting models, this type of AI simply gives a simple reading to say 'this is normal' or 'this is unusual'.

Unfortunately, they aren't able to explain why they are indicating an anomaly - they only let you know that the data coming from the asset(s) is unexpected.

Generally, these types of AI generate a value - you can adjust exactly how sensitive your anomaly detector is to changes by choosing the threshold the system uses to go from saying 'OK' to 'Anomalous'.

A high threshold will result in a less sensitive anomaly detector.

These sorts of models are ideal for when the assets….

• Don't have very much data,
  
• Have no context information,
  
• Have significant gaps in context information, or
• Are inherently inconsistent

They are simple, relatively un-complicated, and work in situations where there simply isn't enough usable data to predict a specific value.

The AI Anomaly Detector addon uses Support Vector Machines to provide this style of anomaly detection. See the differences between model types for more information.