Define and Build a Prediction
Let Einstein Predict for You
Now that you have your special Developer Edition org, you’re ready to take the steps in this project to create a prediction. Let’s begin by defining a prediction.
The first step in crafting a prediction is to determine the question you want to answer. In this case, it’s “Is this person likely to want to join VeloStars?”
- In your hands-on org, click and choose Setup from the drop-down menu.
- From Setup, in the Quick Find box, enter
Einstein Prediction Builder
and select Einstein Prediction Builder. Or, click Get Started on the Einstein Prediction Builder tile. - Now, click Get Started next to Try Einstein Prediction Builder. It can take a few minutes to launch. If you're still waiting after a few minutes, refresh your browser to see if you can start building your prediction. You'll see the New Prediction button when it's ready.
- From the Einstein Prediction Builder Setup page, click New Prediction. This brings up the Guided Setup flow.
- On the Name & Type page, name your prediction
VeloStars Membership Likelihood
. - Tab or click to auto-populate the API Name. Add a description if you like.
- Select the Yes/No prediction type. Then click Save & Next.
- On the Object page, from the list of objects, select Contact. Then click Save & Next.
- On the Segment page, leave the default All Contacts selected. Then click Next.
- On the Example Records page, define the Yes and No examples. You may need to scroll down to see the Yes and No fields.
- In the Yes Example, leave the default Meet All Conditions. Select the VeloStars Member field, the Equals operator, the Boolean type, and the True value.
- In the No Example, leave the default Meet All Conditions. Select the VeloStars Member field, the Equals operator, the Boolean type, and the False value.
- Click Add Condition. Select the First Purchase field, Earlier than or equal to operator, and Date type. Then enter a date of
Jan 1, 2018
, and click Save & Next.
- Click Add Condition. Select the First Purchase field, Earlier than or equal to operator, and Date type. Then enter a date of
- On the Included Fields page, leave all fields selected to use all fields for the prediction. Then click Next.
By default, Einstein scores all records that aren’t included in your example set. You can choose to have Einstein score records that are in your example set. Or, you can define filters to score a specific set of records. - On the Records to Predict page, select Predict on all records that aren't example records. Then click Next.
- On the Score Field page, name the score field
Membership Likelihood
. Tab or click in the subsequent field to auto-populate the API Name. Click Save & Next. The custom field stores your prediction results as scores. - Now that you've created your prediction, it’s time to build it. Click Data Checker to verify that you have enough records. If all looks good, click Build.
Enable and Score Your Prediction
Once your prediction has finished building, you need to enable it so predictions can be assigned to your contacts. This is called scoring.
- Click the down arrow next to the status of your prediction and from the dropdown menu, choose Enable. The prediction’s status changes to Enabled, and you see a message saying that Einstein will begin scoring your records.
- To learn about your prediction quality, click the down arrow again and choose View Scorecard.