About pre-trained AI algorithms
These algorithms don’t require models to derive insights. They are enabled by default. You do not need to set up training for these AI algorithms; they are automatically enabled for you, except for the statistical baseline log anomaly detection algorithm, which is enabled by default, but can be disabled.
Click here for more information about the pre-trained AI algorithms:
- About probable cause
- About scope-based grouping
- About statistical baseline log anomaly detection
- About topological grouping
About probable cause
The probable cause AI algorithm is enabled by default and cannot be disabled. To indicate this, the word Enabled appears in grayed out text at the bottom of the "Probable cause" tile in the AI Model Management.
For more information on the probable cause AI algorithm, see About probable cause ranking.
About scope-based grouping
The scope-based grouping algorithm is enabled by default and cannot be disabled. To indicate this, the word Enabled appears in grayed out text at the bottom of each of the event grouping tiles in the AI Model Management.
For more information on the event grouping AI algorithms, see About scope-based grouping.
About statistical baseline log anomaly detection
Leave this AI algorithm turned on to see details about statistical baseline anomalies in your ChatOps feed and in your Alert Viewer.
Statistical baseline log anomaly detection is an unsupervised learning algorithm that automatically detects unusual patterns in logs and notifies you when they occur. Data that is used for analysis is updated every 30 minutes so this algorithm provides value quickly. This algorithm supplements the natural language log anomaly detection algorithm by reporting extra log anomalies to your ChatOps interface and to the Alert Viewer.
By default, this algorithm is turned on and it is recommended that you leave it turned on. If you turn it off, you won't see details about statistical baseline anomalies in either your ChatOps feed or in your Alert Viewer.
Note: If both statistical baseline and natural language log anomaly detection algorithms are active, then any log anomalies discovered by both will be reconciled, so that only one alert is generated.
About topological grouping
The topological grouping AI algorithm is enabled by default and cannot be disabled. To indicate this, the word Enabled appears in grayed out text at the bottom of each of the event grouping tiles in the AI Model Management.
For more information on the event grouping AI algorithms, see About topological grouping.