Global retail report: Exploring how facial age estimation improves the self-checkout

profile picture Rachael Trotman 3 min read
Preview of the global retail report entitled "Exploring how facial age estimation improves the self checkout experience"

Nearly four years ago we integrated our facial age estimation technology into retail self-checkouts. Since then, it has been trialled by retailers in the US and Estonia, with further pilots taking place in Germany, Poland and Czech Republic. And last year UK supermarkets – including Asda, Morrisons, Tesco and Co-op – tested the technology as part of a Home Office regulatory sandbox. The aim of the sandbox was to trial digital age verification for the sale of alcohol under the UK Licensing Act (2003). 

Detailed reports from the Home Office and the supermarkets who participated in the sandbox are due to be published. But in the interests of transparency, we have shared our own insights from both the Home Office trials and our wider learnings of how our technology works in a retail setting. We hope this helps to answer common questions and dispel misconceptions, and build trust and understanding in this new approach to age verification, which can make the lives of retail staff easier and improve compliance rates. 

 

Key takeaways from the report:

  • Customers like the experience
  • Our technology gives customers a more private way to prove their age 
  • Digital age verification has the potential to improve retail staff safety and reduce friction between staff and customers 
  • Retail staff have more time to focus on other tasks, including spotting proxy sales and ‘walkaways’ 
  • Our technology is inclusive for those who do not own or have access to an ID document 
  • Lighting conditions and environmental factors impact success rates
  • Anti-spoofing is key to the success of digital age verification  

 

A note from our CEO

Our age verification technology can help make retail stores safer and give customers privacy-preserving ways to prove their age, without needing to show physical ID to staff. During the Home Office trials, I was particularly happy to see that some of the self-checkouts could successfully estimate over 90% of shoppers at the first attempt. This will be a game changer for retailers both here in the UK and abroad, who can use our technology to improve compliance rates and enhance the checkout experience for shoppers” – Robin Tombs, CEO of Yoti.

 

Related stories

Why do Yoti facial age estimation results published by NIST differ to those reported by Yoti in its white papers

In September 2023, we submitted our facial age estimation model to the US National Institute of Standards and Technology (NIST), as part of a public testing process. This is the first time since 2014 that NIST has evaluated facial age estimation algorithms. NIST age estimation reports are likely to become a globally trusted performance guide for vendor models. NIST assessed vendor Facial Age Estimation models using 4 data test sets at certain image sizes: NIST provides some example images: NIST note in their report that age estimation accuracy “will depend on

4 min read
An image of a girl looking at her smartphone. Surrounding her are illustrative icons such as a shield which represents privacy and a set of scales representing fairness.

The importance of transparency for facial age estimation

To protect young people online, businesses need to provide age-appropriate experiences for their users. This could apply to online marketplaces, social media networks, content sharing platforms and gaming sites. But to put the correct measures in place, businesses need to know the ages of their customers. It was previously thought that the only way to confidently establish a user’s age was with an identity document, like a passport or driving licence, or checks to third-party databases such as credit reference agencies or mobile network operators. However, regulators are now recognising facial age estimation as an effective alternative. As with

7 min read
A woman smiling and using her smartphone.

Making age checks inclusive

In today’s world, we can access a range of goods, services and experiences online. As a result, regulations are being passed across the globe to ensure that young people safely navigate the digital world. From the UK’s Online Safety Act to age verification laws in the US, platforms are being required to check the ages of their users. To do this effectively, the age assurance methods offered must be inclusive and accessible to as many people as possible.   Why can’t businesses just use ID documents? Most people tend to think of age assurance as checking a person’s age

8 min read