5.4.2 Model Training and Scoring

This topic describes the systematic instructions to train the model for the selected use case and use the trained model to predict and score multiple records at a time.

The predicted values persist in the database and are available in the prediction column maintained for the user case.

Specify User ID and Password, and login to Home screen.

1. On Home screen, click Machine Learning. Under Machine Learning, click Model Training and Scoring..
   The Model Training and Scoring screen displays.

   Figure 5-10 Model Training and Scoring

   
   

   
   Description of "Figure 5-10 Model Training and Scoring"

   
   

   For more information on fields, refer to the field description table.

   Table 5-14 Model Training and Scoring – Field Description

   Field	Description
   Use Case Name	Select the Use Case name from the drop-down list.
   Description	Displays the description of the use case.
   Use Case Type	Displays the type of use case.
   Training Data Source	Displays the training data source.
   Unique Case Identifier	Displays the unique case identifier.
   Target Column	Displays the target column of the model.
   Partition Column(s)	Displays the partition column of the model.
   Model Name	Displays the name of the model.
   Inference Data Source	Displays the Inference data source.

2. Select the use case name from the drop-down list.
3. Click Train Model to train the model for the selected use case.
4. Click Batch Scoring to predict the score for the data source records.
   The predictions of batch scoring are now available for business consumption.