---
sourceDocument: Xanadu Enable AI
sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/xanadu/intelligent-experiences

 Release :

    - xanadu

ft:locale :

    - en-US

ft:publication_title :

    - Xanadu Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Configure class recall for a classification solution

# Configure class recall for a classification solution {#ariaid-title1}

* Release version: Xanadu
* 
* Updated August 1, 2024
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read

Create and apply a class recall parameter to an ML solution prior to training its
data. For example, you set and apply this solution parameter to 90% accuracy for all records
you train in the Email class.

## Before you begin

Note:  
Configuring advanced settings on your ML solutions is optional. If you choose to configure any of these settings, make sure you're well informed regarding the technology you're enabling in the solution, and that you have a use case that benefits from what the technology offers.

* Create and save a classification solution definition or use an existing one.
* Role required: admin or ml_admin
{#configure-class-recall-for-classification-solution__ul_clq_rxs_1kb}

## About this task

The class recall solution parameter enables you to steer a solution's training to bias a specific
class. For example, classifying an incoming email as a Phish or not can be an
important use case in a security-related machine learning solution. In this
situation, it's very important to identify every Phish, and it may be okay to report
a non-Phish as a Phish occasionally. However, no real Phish should be classified as
a non-Phish. In such situations, the recall metric must have a high value, which
might lead to lower percentages for precision and
coverage.

## Procedure

1. Navigate to AllPredictive IntelligenceClassificationSolution Definitions.
2. Open a saved classification solution definition form.  
   In this example scenario, you use an Incident Categorization solution definition form that you haven't trained yet.  
3. On the Advanced Solution Settings tab in the Related Links section of the form, click New.  
4. Create a parameter record.
   1. In the Solution Parameters field, click the search icon.
   2. In the ML Solution Parameters screen, select Add class recall value while training.  
   {#configure-class-recall-for-classification-solution__substeps_ow5_5tj_zjb}
5. Click Submit.  
   The Advanced Solution Setting record appears.  
6. Configure the User inputs field.
   1. Enter the class name on which you want to track the Recall value.  
      In this scenario, you enter <kbd class="ph userinput">Phish</kbd> for the ClassName.
   2. Enter the Recall value.  
      Enter <kbd class="ph userinput">90</kbd> for the RecallValue.

   {#configure-class-recall-for-classification-solution__substeps_gt3_kyp_bkb}  
   Here you're specifying Phish as the target class, and 95 is the recall percentage you're requesting the system to deliver during solution training.  
7. Click Submit.  
   Result: Class recall is configured for your
   classification solution. Its solution parameter appears on the Advanced
   Solution Settings tab of your classification solution definition form.  

## What to do next

Train your saved classification solution.
**Related concepts**   

* [Configuring target metrics for a trained classification solution](https://servicenow-prod.fluidtopics.net/Hgh8Ln08UiXyNuAJis2xZA "Set values for precision, coverage, and recall statistics for a trained machine learning solution.")  
**Related tasks**   

* [Create and train a classification solution](https://servicenow-prod.fluidtopics.net/78~nLudSwaZPxXTQ~5F0aA "Specify the records used to train a classification solution, what fields trigger a prediction, and how often you want to retrain your solution.")
* [Configure TF-IDF for solutions](https://servicenow-prod.fluidtopics.net/igZA6vCg9y1zV5w07e9ZvA "Apply Term Frequency–Inverse Document Frequency (TF-IDF) encoding to classification, clustering, or similarity solutions for Predictive Intelligence.")

*[\>]: and then