Editing the training setup for an algorithm

You can edit the training setup for any of the existing algorithms.

Before you begin

You must save at least one algorithm training setup, as described in Setting up training for trainable AI algorithms.

Only algorithms that generate models can be edited. For more details, see Algorithm types.

From the AI Model Management, under the Training tab, click the tile of the algorithm you want to edit.
- Change risk: Deployment, Training schedule
- Log anomaly detection - natural language: Training data, Deployment, Training schedule
- Similar tickets: Training schedule
- Temporal grouping: Training schedule
- Metric Anomaly Detection: Training schedule
Modify the algorithm settings by clicking the Edit data icon next to the settings that you want to modify. After you make your changes click Save to return to the Overview page.

Your changes are now saved.

The following information is referenced in this task.

Column	Description
Latest model version	Latest version of the model. A new version of the model is generated everytime that the training succeeds.
Version deployed	Currently the deployed version of the model. If training is scheduled and deployment is automatic, then the value in this field always matches the value in the Version field.
AI algorithm	The AI algorithm that is related to this record. Possible values are: Change risk, Log anomaly detection - natural language vs statistical baseline, Similar tickets, Metric anomaly and Temporal grouping.
Date prechecked	Date and time this training setup was prechecked.
Date trained	Date and time that this training setup was last run. If it has never run then this field is blank.