Skip to main content
Documentation
Documentation
Administrator Guide
Last Updated: 2026-06-12
Steps: Set Up Machine Learning for Customer Payment Matching

Steps: Set Up Machine Learning for Customer Payment Matching

You might need to take additional steps to enable this feature based on your organization's subscription service agreement. Your organization is either on the Main Service Agreement (MSA) or the Universal Main Service Agreement (UMSA). To determine your organization's subscription service agreement:
  1. Select your profile avatar on Workday Community.
  2. Select
    Profile
    .
  3. On your profile page, select your organization's name, which is beneath your name and next to your job title.
  4. View your
    Subscription Service Agreement
     value.
If the value is:
  • UMSA
    , the feature is automatically available. You can skip the
    Enable Innovation Services Feature and AI Data Contributions for MSA Customers
     step. For more information on Machine Learning data contributions, see Concept: Workday AI for Universal Main Subscription Agreement Customers.
  • MSA
    , you must enable this feature through Innovation Services using the
    Enable Innovation Services Feature and AI Data Contributions for MSA Customers
    step.
Note: UMSA customers don't have Innovation Services tasks and reports in their tenants as these are for MSA customers only. UMSA customers can ignore all information regarding Innovation Services.
  • Record customer payments. You must have at least 1 customer payment recorded in the last 30 days to complete the opt-in process for this feature and have a model trained for your tenant.
Machine Learning features that require data contributions will not function accurately in your Sandbox tenant. To test Machine Learning features before deploying them to your Production tenant, use your Sandbox Preview or Implementation tenants.
You can enable Machine Learning to get recommendations for matching payments to customer invoices and adjustments that have little or no remittance advice associated with the payment. The Machine Learning model uses insights from historical payment application data and also learns from current payment applications to determine invoice recommendations for a given payment. The model ignores:
  • Payments missing the remit-from customer on the payment header.
  • Consolidated invoices.
  • Invoices with term discounts.
  • Invoices that don’t add up to the payment amount when making recommendations.
This feature provides beneficial recommendations only when you’re processing customer payments in Workday. The recommendations:
  • Address how to apply prepayments.
  • Address how to apply on-account payments.
  • Identify mis-applied payments.
  • Prevent write-off of a payment or invoice that should be a payment application.
Workday doesn't include cross-currency payments in the recommendations.
  1. You might need to take additional steps to enable this feature depending on your organization's subscription service agreement. For more information, see this Community article.
    1. On the
      Innovation Services Opt-In
       task, select the
      Financial Management Generally Available Machine Learning Features and Third Party Services
       service on the
      Available Services
       tab in the
      Financials
       category.
    2. On the
      Maintain Innovation Services Data Selection Opt-In
       task, select the
      Customer Payment Data
       category for the
      Financial Management Generally Available Machine Learning Features and Third Party Services
       service.
  2. (Optional) Access the
    Run On-Demand Machine Learning Activation for Implementation Tenant
     task to set up testing on Implementation Tenants.
    After setting up the task, it can take up to 2 weeks to view the machine learning feature functionality in your tenant. Then, you have 2 weeks to complete testing.
    Workday recommends using a Preview tenant to test this functionality because compared to Implementation tenant, you have unlimited time to test. Also, you can more easily enable Financials machine learning.
  3. Access the
    Edit Tenant Setup - Machine Learning
     task.
    Select the region in which Workday hosts data used for improvement and personalization of machine learning and analytics functionality.
    Security:
    Set Up: Tenant Setup - Machine Learning
     in the System functional area.
When you enable the feature for the first time, it takes up to 2 weeks to train the machine learning model using your data.
When you opt out of the data contribution, Workday purges your data within 30 days.
Run the
Schedule Cash Application Insights
 task to schedule cash application recommendations.