You can extract and use features from your data model by customizing the recipes created by using the Due Date Predictions for Quote Line Items template.
| Available in: Lightning Experience |
| Available in: Enterprise, Performance, and Unlimited Editions of Communication Cloud with the Communication Cloud Intelligence and CRM for Comms Admin licenses |
To generate revised example and prediction datasets, update the existing set of recipes and then update the model settings.
Update Prospective Orders’ Due Date Prediction Recipes
Customize recipes to use additional features from your data model. Ensure that the recipes are run in the order listed in this table.
To view the recipes, from Analytics Studio, click 
, click Data Manager, and then go to the Recipes tab.
| Recipe | Description | Output |
|---|---|---|
| Get Example Set to Predict QLI Due Date | Evaluates data from quote members, quote line items, products, orders, order items, and orchestration items to create an example dataset that Einstein learns from. | Example Dataset |
| Get Scoring Set to Predict QLI Due Date | Evaluates data from quote members, quote line items, and products to create a prediction dataset for which Einstein generates predictions. | Prediction Dataset |
| Get Predicted Order Completion Duration | Evaluates the prediction dataset to get predictions about the order completion duration and the top three predictors. | Predicted Order Completion Duration & Predictors |
You can modify the recipes in these scenarios:
-
Your schema deviates from the Communications Cloud schema.
-
A custom field of an existing entity changes.
-
The use of feature data changes from an existing entity to a custom entity.
-
The data doesn’t load properly.
-
The app stops working because of incorrect data values.
Related Information
Update Prospective Orders’ Due Date Prediction Model
To get insights and predictions based on your custom features, edit and redeploy the Quote Line Item Due Date Predictions model settings.
- Edit and update the Order Delay Predictions model settings. For more information, see Edit Model Settings.
- Redeploy the model after updating the required features. For more information, see Review Your Selections and Deploy the Model.