====Outlier Detection Model====

Outlier Detection Models are the simplest form of anomaly detector.

Unlike [[value prediction models|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.

===Adjustments===

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.

===Use Case===

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

  * Don't have very much data, \\
  * Have no context information, or \\
  * Have significant gaps in context information

They are simple, relatively un-complicated, and work in situations where there simply isn't enough usable data to predict what values should be.

===AI Types===

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