Skip to main content
All CollectionsPayhawk for administratorsExpense fields
Automatic population of expense field data
Automatic population of expense field data

Learn about the automatic data extraction (OCR) and suggestion strategies at Payhawk and select the way expense fields are populated.

Updated over 9 months ago

Payhawk helps with expense automation by reducing the manual work when reviewing, confirming the details, or paying company expenses.

Payhawk utilizes optical character recognition (OCR) technology reading more than 65 languages including Cyrillic, an advanced AI data extraction algorithm, and multiple machine learning (ML) algorithms, to name a few, to leverage the data and automatically suggest as many expense fields as possible.

Automatic data extraction with OCR

Optical character recognition or reader (OCR) is the electronic conversion of images of typed or printed text into machine-encoded text, whether from a scanned document or a photo of a document. Payhawk uses OCR for images and scanned documents that were taken while using the mobile application. Once Payhawk detects the text from the image, the system continues with the data extraction process, figuring out the total amount, the invoice number, and so on.

As part of its expense management solution, Payhawk has developed an AI-powered data extraction algorithm, which automatically extracts the relevant information from uploaded invoices and receipts. The avoidance of manual data input reduces errors in accounting data and increases the productivity of Finance teams.

From expense and payment documents, the data extraction tool takes out the following expense information:

  • Supplier (name, VAT number, country)

  • Document date

  • Document number

  • Due date

  • Total amount

  • Tax amount

  • Document currency

  • Document type (invoice or receipt)

For more information on the Payhawk OCR implementation, see the Smart data extraction made simple with OCR technology blog post by Trish Toovey.

Automatic suggestions for expense categorization

Expense categorization contains not only the information from the document, but also other fields such as Category (G/L code), custom fields (Project, Cost center, and so on), and VAT code.

As the value of those fields cannot be determined based on the information in the document, Payhawk applies different strategies to suggest the correct value for each of those fields.

Payhawk supports different suggestion strategies for the Category built-in expense field and any custom expense field that you have created.

Suggestion strategy for Category and the custom expense fields

The suggestion strategies are part of the settings Payhawk administrators define for each custom expense field or the Category built-in expense field. These settings are located in the Expense fields > Custom fields > [Selected custom field] > Settings or Expense fields > Built-in fields > Categories > Settings tab respectively.

None suggestion strategy

If Suggestions is set to None, then the expense field will remain blank and won't be automatically populated.

One default value suggestion strategy

If Suggestions is set to One default value, you need to define that default value so that it will be automatically filled in the expense field for each expense. This is useful if you have a custom field that has one value for more than 90% of the expenses and the Finance team rarely changes it on the review step.

Payhawk AI suggestion strategy

If Suggestions is set to Payhawk AI, the expense field will be automatically populated based on the historical data the Payhawk system has gathered for your account. The advanced ML model considers the employee, supplier, historical field values, merchant category (in the case of card transactions), and other parameters to decide on each expense and each categorization field.

The Payhawk AI option is set by default to all custom fields and is appropriate for any business case in which automation is needed. This option is especially powerful for fields where you don't have strict rules.

Supplier suggestion strategy

If Suggestions is set to Supplier, then, the expense field suggestion will be driven by the supplier selected for the expense. This is useful for custom fields and categories when they are strictly driven by the supplier - for example, if the supplier is Uber, the category is Taxi allowance, if the supplier is Facebook Ads, the category is Marketing Ads, and more.

Once you select that the suggestion strategy for a field is Supplier, you will be able to pick a field value for each of your suppliers.

The expense field will be displayed in the Expense categorization tab for all suppliers. Then, you can go to Suppliers, select a specific supplier, go to the Expense categorization tab, and set a value for that expense field. As a result, all expenses associated with that supplier will display the configured value for the defined field under the Categorization section.

Having values for more and more suppliers means your expense automation will be at a higher rate and Payhawk will be able to support you more.

By selecting a value from the Default value for all suppliers list, you can specify the expense field value in case there is no value set for a supplier. To display a default value if there is no supplier value, you can select it from here - for example, if the Supplier location custom expense field is not pre-selected, then always select Germany as a default value.

Employee and team suggestion strategy

If Suggestions is set to Employee/Team, you'll be able to set a default value for that expense field for all employees and teams. This is useful for fields that are strictly driven by the employee or the team - for example, the Cost center, Department, or Location custom expense fields.

Once you select the Team/Employee option as the suggestion strategy for a field, you will be able to pick a field value for each of your teams and employees in the platform.

By default, the employee inherits the default value from their team - in this case, you will see the Use team default option in the expense categorization section.

If there is no value for the team in which the employee is, the system will check the parent team of the team, and so on. This approach allows you to set, for example, Project Website redesign to Marketing - Website team, and all employees within this team will get Project Website redesign as their suggested value.


Using the Employee/Team inheritance saves time and effort for individual configuration and adds to consistent categorization data across the board.

By selecting a value from the Default value for all teams/ employees list, you can specify the expense field value in case there is no value set for that employee and their teams - for example, if there is no pre-selected value for the employee, always select Contractors expenses for the Cost Center custom expense field.

Tax rate suggestion strategy

The tax rate is significant for the tax reclaim process and the way you categorize your expenses. Payhawk supports the following strategies for the Tax rate built-in expense field:

  • Supplier-driven tax rate suggestion - You can specify the tax rate per supplier or leave it blank and assign a value to each expense for that supplier. You can set the Tax rate value in the same way as the supplier suggestion strategy by going to Suppliers > [Selected supplier] > Expense categorization> Tax rate.

  • Category-driven tax rate suggestion - You can also specify the tax rate per category. In this case, it will be the category that will drive the tax rate and suggest it based on the category the respective people at your company have selected.

Category-driven suggestions for tax rates do not work if you have a live ERP (accounting software) integration and your tax rates and categories are coming from there.

Useful resources

Did this answer your question?