---
schema_version: "1"
id: 264f5eb0cfe3e2100ba02a16d158a5dd4e50e617a58515b04074488e008e625c
title: View the Accuracy Analytics App 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_analyze_view.md
canonical_url: https://help.salesforce.com/s/articleView?id=analytics.bi_edd_model_manager_accuracy_analyze_view.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: 381054897382da10aa0adec88460349ef07f8e5e44ae38c60cc2fb24fb4d72c7
description: After creating Accuracy Analytics, view its dashboard to see prediction accuracy metrics and a chart.
products:
  - CRM Analytics
  - Cross Cloud
release: "264"
---
# View the Accuracy Analytics App for a Prediction Definition

After creating Accuracy Analytics, view its dashboard to see prediction accuracy metrics and a chart.

![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 Einstein Discovery stories are now models. We wish we could snap our fingers to update the name everywhere, but you can expect to see the previous name in a few places until we replace it.

**Update Data in the Dataset (Optional)**

When you create Accuracy Analytics, its dataflow populates the dataset with a snapshot of the predictions for the Salesforce object. To get the latest data for your dashboard, refresh the data in the dashboard’s dataset by running the associated dataflow. You can run the dataflow in several ways:

- In the Data Manager, run the dataflow manually. For instructions, see [Run a Dataflow Manually](https://help.salesforce.com/s/articleView?id=analytics.bi_integrate_dataflow_run.htm&release=264.0.0&type=5 "Run a dataflow for the first time to create the datasets it defines. Run it again to update the dataset with the latest synced data.").
- In the Data Manager, schedule the dataflow to run periodically. For instructions, see [Schedule a Dataflow to Run Automatically](https://help.salesforce.com/s/articleView?id=analytics.bi_integrate_dataflowjob_reschedule.htm&release=264.0.0&type=5 "You can schedule a dataflow to run after an event, such as when a sync job completes. Or you can schedule it to run hourly, weekly, monthly, or on specific days of the week or dates.").
- In the Model Manager, reconfigure the app and save changes, which triggers the dataflow to run.

**View Prediction Accuracy**

To open an Analyze Accuracy App for a prediction definition:

1. [View a Prediction Definition](https://help.salesforce.com/s/articleView?id=analytics.bi_edd_model_manager_view.htm&release=264.0.0&type=5 "Manage a prediction definition and its associated models.") in Model Manager.
    
    If your prediction definition meets the prerequisites, you see the **Analyze Accuracy** button in the upper right corner of your screen. Click this button to open an existing app.
2. Click **Analyze Accuracy**.
    
    If found, the app opens.
    
    ![All Items tab for the Analyze Accuracy app](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_accuracy_analyze_existing.png)
3. Click **Run App**.
    
    Einstein runs the App and displays its dashboard.
    
    **Dashboard for Logistic Regression**
    
    ![Logistic regression dashboard, showing summary statistics and line chart](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_accuracy_analyze_logistic.png)
    
     
    | Area | Description |
    | --- | --- |
    | **Accuracy** | Accuracy of this prediction definition. Number of correct predictions divided by the total number of predictions. Excludes nulls in the predicted or actual field. |
    | **Total # of Predictions** | Number of all predictions made. |
    | **Total # of Correct Predictions** | Number of predictions that were correct. |
    | **Confusion Matrix** | Used to evaluate the trade-offs between different error types based on the threshold value. It displays how many times the model correctly and incorrectly classifies a record as true and false at the associated threshold. |
    | **Details Table** | Each row represents a scored record (such as an Opportunity) with the predicted value, actual value, and other details. |
    | **Accuracy Trend Chart** | Shows prediction accuracy (x-axis) over time (y-axis). |
    
    **Dashboard for Linear Regression**
    
    ![Linear regression dashboard, showing summary statistics and line chart](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_accuracy_analyze_linear.png)
    
     
    | Area | Description |
    | --- | --- |
    | **Average MSE** | Measures the average squared error of the prediction definition’s predictions. Computes the square difference between the observed (actual) outcome and the predicted values, and then averages them. |
    | **Total # of Predictions** | Number of all predictions made. |
    | **Predicted Values vs Actual Values** | Residuals plot chart that reveals the robustness of your model. A residual represents the difference between the actual value and the model’s predicted value. |
    | **Details Table** | Each row represents a scored record (such as an Opportunity) with the predicted value, actual value, and other details. |
    | **Accuracy Trend Chart** | Shows prediction average MSE (x-axis) over time (y-axis). |
4. If you want, drill down into the data by filtering columns.