Finally, you can select your best experiment and Publish it as a Scheduled Service which will score customers and their propensity to buy on a recurring basis.
Login to Adobe Experience Platform: https://experience.adobe.com/platform
From the left menu, click on Models.
In this exercise, we’ll use a prebuilt recipe to create a model for car insurance sales predictions.
In the top menu, click on Recipes.
In Recipes, you’ll find multiple recipes. Look for your own recipe in the list, which should be named
ldapCarInsurancePropensity recipe to open it.
Click to open the Model you created in the previous exercise,
ldap - CarInsurancePropensity Model.
You’ll then see this:
Click the button + Publish.
You then have to name your Service.
As a name, use
ldap - Car Insurance Propensity Service.
In this example, for ldap
vangeluw, the name should be
vangeluw - Car Insurance Propensity Service.
In the next screen, you need to select a Training Run to run as part of this Service.
Next, click Finish.
Your service is now almost created.
Click Set Schedule to configure your schedule for this service.
Configure your schedule so that your Service runs in the weekend, on Saturday or Sunday. You can choose the time yourself.
Next, you need to select the Scoring Dataset and the Scoring Results Dataset.
The Scoring Dataset should be
AEP Demo - Car Insurance Interactions.
The Scoring Results Dataset should be
AEP Demo - ML Predictions.
Next, click Create.
And you’re done. Your service is now created and the schedule is set.
Next Step: Summary & benefits