Prediction results are saved as [events to customer cards](/docs/ai-hub/predictions/custom#understanding-prediction-events). Thanks to this, a prediction can be used as a parameter in a segmentation that is the audience of a workflow. The number of uses for churn prediction is practically unlimited. In this example, an email is sent automatically to every customer for whom the risk of churn is calculated as high after completing the prediction described in [Predict churn](/use-cases/churn-prediction).
Reduce churn
Reduce churn
## Prerequisites --- - Prepare a churn prediction (for example, as described in [Predict churn](/use-cases/churn-prediction)). - Prepare the template for the email you want to send to customers who are at risk of churn, as described in [Creating email templates](/docs/campaign/e-mail/creating-email-templates). ## Process --- 1. Create a [segment](/use-cases/predictions-automation#create-a-segment-based-on-predictions) based on predictions. 2. Create [workflow](/use-cases/predictions-automation#create-workflow-to-message-customers-at-risk-of-churn) to message customers at risk of churn. ## Create a segment based on predictions --- In this stage, you create a segment of customers who are at high risk of churn. The segment will be used in an Audience Trigger for a workflow. 1. Go to Decision Hub icon **Decision Hub > Segmentations > New segmentation**. 2. Give the segmentation a meaningful name, for example `Customers at risk of churn`. 3. Click **Choose filter** and select the `snr.prediction.score` event.
The event may have a custom label in the list, but can always be found by entering the system name (`snr.prediction.score`) in the search field.
3. Add the following conditions to the event: - `score_label` parameter equals `High` - `modelId` parameter equals the ID of the prediction you want to use.
The model ID can be copied from the Three-dot icon menu in the Prediction list.
4. Click **Save**. **Result:** The segmentation is saved and can be used in automations, analytics, and more.
Segment configuration
Segment configuration
## Create workflow to message customers at risk of churn --- 1. Go to Automation Hub icon **Automation Hub > Workflows > New workflow**. 2. Add an **Audience** trigger node. 3. In the settings of the node, as the audience select the segment you created earlier. 4. Add boolean and set it as **true**. 4. Save the node configuration. 5. Add a **Send email** node. 6. Configure the sender and prepare the content as described [here](/docs/automation/actions/send-email). 7. Save the node configuration. 8. Add and **End** node. 9. Perform one of the following actions: - If you want to send the messages immediately, click **Save & Run**. - If you want to send the messages later, click **Save**. **Result:** When the workflow starts, a message is sent to all customers who belonged to the segmentation at the time of starting the workflow. ## What's next --- You can configure the workflow differently, for example by: - using the prediction event as a trigger, - sending other types of messages, - adding more conditions to the audience filter, - and more nodes, depending on your business scenario and familiarity with Automation Hub. ## Check the use case set up on the Synerise Demo workspace --- You can find the analyses created in this use case in our Synerise Demo workspace at the following links: - [Propensity prediction](https://app.synerise.com/ai-v2/predictions/generic-scoring/bgycsoovxgby) - [Segmentation](https://app.synerise.com/analytics-v2/segmentations/9ec901b4-2ea0-47dc-9285-023d2000e8cf) - [Workflow configuration](https://app.synerise.com/automations/automation-diagram/e0f72659-611a-4122-91a0-a99e4832a106) If you’re our partner or client, you already have automatic access to the **Synerise Demo workspace (1590)**, where you can explore all the configured elements of this use case and copy them to your workspace. If you’re not a partner or client yet, we encourage you to fill out the contact [form](https://demo.synerise.com/request) to schedule a meeting with our representatives. They’ll be happy to show you how our demo works and discuss how you can apply this use case in your business. ## Read more --- - [Predictions](/docs/ai-hub/predictions) - [Workflow](/docs/automation)