# Deploying predictions with components and writeback

*CRM Analytics and Einstein Discovery Consultant Study Guide · Einstein Discovery · Last updated November 3, 2026 · https://www.certifyforce.com/study-guide/crm-analytics-and-einstein-discovery-consultant/einstein-discovery/deploying-predictions-with-components-and-writeback*

Deploying an Einstein Discovery model to a prediction definition (object connection, variable mapping, supplemental datasets, segmentation filters, actionable variables), then surfacing scores with the Einstein Predictions component, automated prediction writeback and bulk scoring.

- Certification: Salesforce CRM Analytics and Einstein Discovery Consultant
- Exam section: Einstein Discovery
- Study guide: https://www.certifyforce.com/study-guide/crm-analytics-and-einstein-discovery-consultant

**Official exam objective:**

> Enable prediction features on Lightning record pages across Salesforce and CRM Analytics.

## What the exam expects

- Deploy a model through the Deploy Model wizard: target prediction definition, object connection, variable mapping, segmentation filters and actionable variables.
- Use a supplemental dataset when a model variable has no field on the Salesforce object.
- Add the Einstein Predictions component to a Lightning record page and configure it for the model type, with the right permissions for admins and viewers.
- Decide when automated prediction writeback fits, including its multiclass restriction and field-level security step.
- Refresh stored scores with bulk scoring after a model changes.

Key terms: **prediction definition** (a container for one or more deployed models; each model scores a different segment); **segmentation filter** (a condition that picks the records a model scores); **actionable variable** (a factor users can control, needed for suggested improvements); **supplemental dataset** (a dataset that supplies variables not found on the object); **prediction field** (a writeback field only Einstein can write to).

## Key facts

| Fact | Detail | Source |
|---|---|---|
| Add the component | Customize Application | [Lightning Pages](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_einstein_predictions_lightning.htm&type=5&language=en_US) |
| View predictions | View Einstein Discovery Recommendations | [Lightning Pages](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_einstein_predictions_lightning.htm&type=5&language=en_US) |
| Models per prediction definition | Up to 10 active, one per segment | [Capacities and Requirements](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_limits.htm&type=5&language=en_US) |
| Segmentation filter values | Case-sensitive exact match | [Segmentation Filters](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_model_deploy_filter.htm&type=5&language=en_US) |
| Writeback model types | Numeric and binary; not multiclass | [Prediction Writeback](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_prediction_automated.htm&type=5&language=en_US) |
| Writeback mapping | All variables mapped | [Map Model Variables](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_model_deploy_map.htm&type=5&language=en_US) |
| Supplemental dataset sharing | Only Salesforce sharing rules apply | [Map Model Variables](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_model_deploy_map.htm&type=5&language=en_US) |
| Improvements | Need an actionable variable; binary and numeric only | [Actionable Variables](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_model_deploy_variable.htm&type=5&language=en_US) |
| Bulk scoring limit | 1,000,000 records per rolling 24 hours | [Capacities and Requirements](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_limits.htm&type=5&language=en_US) |

## Check yourself

- Why can a component show a score while the record's prediction field still shows an older one?
- When does a bulk scoring job pause on its own?
- Which sharing applies to data read from a supplemental dataset at scoring time?
- What does Show prediction warnings tell a user?
- What happens next in the wizard when you choose Update an existing model?

## Sources

- [Deploy Models](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_model_deploy.htm&type=5&language=en_US)
- [Get Predictions on Lightning Pages](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_einstein_predictions_lightning.htm&type=5&language=en_US)
- [Display Einstein Predictions Using Automated Prediction Writeback](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_prediction_automated.htm&type=5&language=en_US)
- [Select a Target Prediction Definition or Model](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_model_deploy_new_existing.htm&type=5&language=en_US)
- [Select Whether to Connect to a Salesforce Object](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_model_deploy_object.htm&type=5&language=en_US)
- [Map Model Variables](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_model_deploy_map.htm&type=5&language=en_US)
- [Configure Segmentation Filters](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_model_deploy_filter.htm&type=5&language=en_US)
- [Select Actionable Variables for Suggested Improvements](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_model_deploy_variable.htm&type=5&language=en_US)
- [Edit Model Settings (Model Manager)](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_model_manager_model_edit.htm&type=5&language=en_US)
- [Get Predictions With Bulk Scoring](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_model_manager_score.htm&type=5&language=en_US)
- [Permission Sets and Permissions for Einstein Discovery](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_setup_user_permissions.htm&type=5&language=en_US)
- [Einstein Discovery Capacities and Requirements](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_limits.htm&type=5&language=en_US)

## About the full unit

The "Core concepts", "Exam traps" and "Worked scenario" sections of this unit, its 7 linked practice questions, and unlimited timed mock exams are included with the CRM Analytics and Einstein Discovery Consultant pack (USD $19): https://www.certifyforce.com/practice-exams