---
schema_version: "1"
id: e8abdfd3a3919a63e70219f5f7abee9872242c4a1be2610aa100bacba83fee95
title: Configure Performance Monitoring for a Prediction Definition
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/analytics/264-0-0/bi_edd_model_manager_accuracy.md
canonical_url: https://help.salesforce.com/s/articleView?id=analytics.bi_edd_model_manager_accuracy.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: d6c3a09dd916bb7103f3f4bf8615b06f7c4c74c3279527226f8adad854531556
description: Configure performance monitoring if you want Einstein Discovery to display performance monitoring charts for a prediction definition. Performance monitoring is available for prediction definitions that use automated prediction writeback.
products:
  - CRM Analytics
  - Cross Cloud
release: "264"
---
# Configure Performance Monitoring for a Prediction Definition

Configure performance monitoring if you want Einstein Discovery to display performance monitoring charts for a prediction definition. Performance monitoring is available for prediction definitions that use automated prediction writeback.

To measure model performance, Einstein Discovery compares _predicted_ outcomes with _actual_ outcomes. An actual outcome represents data that has reached its _terminal state_, such as historical data that is not expected to change. For example, after an order ships, the ship date and the number of items shipped are finalized. You define the conditions under which data has reached a terminal state so that Einstein Discovery knows which data to include in its performance analysis.

To configure performance monitoring:

1. In Model Manager, view a prediction definition that uses automated writeback fields. If it's not enabled, then follow the instructions in [Configure Automated Prediction Writeback for a Prediction Definition](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_model_manager_prediction_field.htm&release=264.0.0&type=5 "Automated prediction writeback saves numeric prediction scores to a field in a Salesforce object. Using this feature requires that you deploy a model that outputs a numerical prediction (regression) or score (binary classification) and for which you can map all model fields back to Salesforce fields. You can use an existing AI Prediction field or create a custom field by specifying a label.") .
2. While configuring automated writeback, click **Save & Next**.
    
    ![Save and Next button while configuring automated writeback](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/bi/images/bi/bi_edd_model_manager_settings_performance_next.png)
3. When prompted, select **Monitor performance**.
    
    ![Prediction definition overview, showing the notification button](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/bi/images/bi/bi_edd_model_manager_settings_performance_prompt.png)
4. Select an **Outcome Field** to use for determining terminal state.
    
    ![Model Manager Settings tab, showing terminal state settings](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/bi/images/bi/bi_edd_model_manager_settings_performance.png)
5. Specify one or more conditions.
    
    - For each condition, select a field, select an operator (**Equals** or **Not Equals**), and set a value.
        
        ![Note](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-analytics-bi-264-0-0-production-enus/ec791473-f5b4-4f64-a656-9104f455d966/images/icon_note.png)
        
        Note
        
        - Filter expressions are case-sensitive. The value you specify must be an exact match. For example, "software" and "Software" are different matches. If your data contains variations in capitalization, consider cleansing your data during data prep to standardize patterns of uppercase and lowercase characters. For instructions on preparing data and data integration options, see [Integrate and Prepare Data for Analysis](https://help.salesforce.com/s/articleView?id=analytics.bi_integrate_data_integration.htm&release=264.0.0&type=5 "You can use CRM Analytics lenses and dashboards to analyze your data. To prepare the data for analysis and increase performance when processing large amounts of data, first load, clean, and transform the data into datasets.").
        - Einstein displays object fields to which you have access. If you don't see an object field you expect, check the field-level security settings for your user account to ensure that you have at least read access to that field in the Salesforce object.
    - To add multiple conditions, click **Add Condition**.
    - To delete a condition, click the trash icon next to it.
6. Click **Save Settings**.