A new innovative machine learning automation system from Xero is set to transform the accounting practices of small businesses and their partners, saving valuable time and money.
Xero’s new technology is the first example of personalized machine learning in a small business cloud accounting system.
Developed in-house by a specialist team of engineers working full-time for a year across three different locations, the system uses detailed statistical analysis to learn from and assist the individual business and their partner based on their own specific circumstances.
The automation will mean small businesses no longer need to worry about where their invoice is filed – an invoice for time spent on site should be recorded against “Sales - Labor”, not “Sales – Materials”, for example.
The machine learning automation evolves with the processes used by the business and their advisor - when the small business comes to create their next invoice, Xero automatically suggests the account code so they don’t inadvertently make a mistake.
The new technology is the first step in Xero’s plan to build a bespoke, personalized assistant for small businesses and their accountants to cut the administrative burden, prevent mistakes, and enable them to spend more time growing their business.
The machine learning automation initially will be made available to a initial group of small business customers and their accounting partners for testing, before being launched to all Xero customers later this year.
“Simply talking about machine learning isn’t enough," says Luke Gumbley, Xero Business Product Lead. "The truth is, it’s really difficult to do beautifully. While many claim to use machine learning principles, actually implementing them across complex platforms to address customer’s real needs takes intricate, specialized knowledge of the technology, the platform and the user.”
For every second machine learning helps to shave off that average edit time, Xero’s machine learning automation will collectively save small businesses around a working month every day.
Gumbley says Xero's machine learning automation will give each Xero business and their advisor the unique insights and processes they need to cut the burden on manual tasks and let them spend more time growing their business. "We’re not asking them to learn something new - we’re saving them time and money by ensuring the system learns from and for them,” he says.
Andrew Erkins, Director of Business Development and Technology at Xero Partner Digit Books, says that before the company works with a client, it reviews their balance sheet to see if items are correctly allocated.
"They very rarely are, and so a lot of our time is spent playing catch-up, fixing errors," Erkins says. "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. Every business is different, and how one client needs transactions to be allocated for their reporting will be different to another."
For that reason, Erkins says that accounting professionals need personalised machine learning that 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,” he says.
Accuracy and productivity set to improve
Xero set out to tackle a common problem among their customer base: account codes are hard. There are more than 10.1 million unique account codes in Xero created by small businesses, meaning items are often entered incorrectly, creating hours of work for the accountants who need to correct them.
Small businesses take an average of 1 minute and 38 seconds to create an invoice in Xero — that works out to 13,600 hours across the 500,000 invoices raised in Xero each day. For every second machine learning helps to shave off that average edit time, Xero’s machine learning automation will collectively save small businesses around a working month every day.
Learning likely to lead to further transformation
Although the true impact of the technology will only become apparent when the product goes live, the benefits have already been demonstrated in early testing.
After just one invoice, machine learning techniques understood invoicing behavior in general better than Xero experts. By the fourth invoice, early machine learning implementations are accurate over 80 percent of the time and by the 50th they consistently reach over 90 percent.
“We expect the wider adoption of machine learning to lead to further insights and improvements that will help small businesses, their advisors and other partners fundamentally change the way they work," Gumbley says. "In the future, Xero will be able to use aggregated, non-identifying data to identify trends, patterns, behaviors and industry insights. This is just the beginning.”