Review and Start Training

[#1]

This article describes optional review steps and how to initiate the first training for your model.

In this article:

• Review your Model Before Publish (Optional)
• Edit the Model and Output Attribute Name (Optional)
• View your Included and Excluded Attributes (Optional)
• Save and Publish to Start Training

Review your Model Before Publish (Optional)

Use the following sections as a guide to review your model and start training. Revising your model using these steps is optional.

If no changes are needed, skip this section and click Save/Publish to Start Training.

Edit the Model and Output Attribute Name (Optional)

Use the following steps to view and edit the your model name and/or your output attribute name:

1. From the Model Dashboard, click View Model Details.
2. Click Edit in the top right-hand corner of the View Model Details screen.
3. In the Edit Model Information screen, edit the model name and/or the output attribute name and descriptive notes.
4. Click Done.

If you need to change Target Attribute details or your Output Attribute (e.g. add or remove attributes to exclude from your model, prediction timeframe, or training date range) you will need to create a new model.

View your Included and Excluded Attributes (Optional)

Use the following steps to view your included and excluded attributes:

1. From the Model Dashboard, click View Model Details.
2. Click Training and then click View Training Details.
3. In the Training Details screen, select the Attributes tab. A list of your included and excluded attributes appears.
4. Click the three vertical dots next to the attribute you want to view and select View Attribute Details.

Save and Publish to Start Training

Your model is currently in the Requires Publish stage.

Complete the following steps to start training:

1. Save and Publish your model. We recommend using the Save As option and typing a meaningful title and description.
   

   Before saving and publishing, your model has been saved, but not published. If no errors are encountered, training begins automatically upon publish.

2. Click OK.
   If no errors are encountered, your model is now in training.
   Your model is now Version 1 with a status of In Training.
   

   Training is a one-time event and each retraining results in a new version number. For example, when you retrain Version 1, the resulting version is Version 2.

3. Check to ensure the model status now displays In Training.
   After the training date range has lapsed, the model status is updated to Ready to Deploy.

Next Steps

For next steps, go to Evaluating the Trained Version.