Skip to main content
Documentation
Documentation
Administrator Guide
Last Updated: 2024-03-08
Steps: Set Up Recommendations and Defaulting for Expense Items on Credit Card Transactions

Steps: Set Up Recommendations and Defaulting for Expense Items on Credit Card Transactions

  • 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.
You can enable machine learning defaulting and recommendations for expense items on credit card transactions. The machine learning inference only happens at credit card transaction load time. If you're testing based on loaded transactions before the model implemented, you won't see any recommendations.
The machine learning model defaults expense items or displays recommendations on expense lines built out of these fields from credit card transactions:
  • Amount
  • Currency
  • Merchant
  • Merchant Category Code
  • Payee
  • Transaction Date
Recommendations and defaulting for expense items is available for these users:
  • Self-service
  • On-behalf of users
  • Delegates
Defaulting and recommendations streamline the expense report submission process and reduce the number of miscategorized expense items.
  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.
  2. 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.
  3. Access the
    Maintain Machine Learning Prompt Recommendations
     task.
    1. On the initiation page, select the
      Expenses
       product area.
    2. In the Expenses grid, select the
      Expense Item for Credit Card Transactions
       check box.
      Security:
      Set Up: Tenant Setup - Financials
       domain in the System functional area.
When machine learning has a high confidence level, Workday automatically defaults expense items on credit card transactions. Expense submitters can view the defaulted expense item in the expense lines. They can view recommendations in the pills under the
Expense Item
 prompt.
Workday now prioritizes this order when determining expense items on expense reports:
  • Manually entered or updated expense item on expense line
  • Defaulted expense item by machine learning on credit card transaction
  • Defaulted expense item by mappings from merchant category codes
  • Manually entered expense item on quick expense by expense submitter
  • Defaulted expense item by machine learning on quick expense
Expense administrators can use the
ML Defaulted Expense Item
 report field to view machine learning defaulted expense items associated with expense lines.