Xero Introduces Machine Learning Into Accounting Platform

SME accounting firm Xero is integrating machine learning technology into its solution, the company announced this week.

Reports Tuesday (March 14) said Xero is deploying a machine learning automation system that will help businesses’ specific needs, including automated invoice categorization. According to the company, the technology will learn over time how to categorize those invoices so accountants and small business owners will no longer have to do so manually.

The tool is rolling out to a select few clients first, Xero said, and will see a broader launch later this year.

“Before we work with a client, we always review their balance sheet to see if items are correctly allocated,” said Andrew Erkins, director of business development and technology at Digit Books, a Xero partner. “They very rarely are, and so a lot of our time is spent playing catch-up, fixing errors. Xero’s machine learning can help us spend less time on these low value exercises and more time adding value to our clients by providing expert advice.”

Xero explained that its machine learning technology will suggest an account code for invoices with platform users that those users can either accept or reject.

“Every business is different, and how one client needs transactions to be allocated for their reporting will be different from another,” Erkins continued. “For that reason, we need personalized machine learning which reflects the unique scenarios of every business. Generic machine learning would probably cause more issues than it solves for a lot of small businesses and their partners if it was applied as a broad brush.”