- Ahead of the UK’s Online Safety Act, Yoti releases the latest facial age estimation white paper, with improved accuracy rates
- Yoti enhances teen age accuracy to just 13 months
22nd July 2025, London, UK – Today, Yoti has released the latest facial age estimation white paper, showing improved accuracy for all ages, most notably for young people aged 13-17. This comes just days before the UK’s Online Safety Act comes into force, requiring platforms to introduce highly effective age checks, of which facial age estimation is an approved method.
Key takeaways from the white paper:
- 13-17 year olds now have a Mean Absolute Error (MAE) of 1.1 years; giving regulators and businesses increased confidence in the technology when considering 15+/- or 16+/- minimum age limits for social media.
- Improved accuracy for 18-24 year olds, with MAE reducing to 2.1; another key age group for online safety.
- 99.3% of 13 to 17 year olds will be correctly estimated as under the age of 21, and 99% of 6 to 12 year olds will be correctly estimated as under the age of 13
- Regulators are focused and most concerned with these two age ranges to ensure that under 13s and under 18s are only able to access age-appropriate content, goods and services.
“We’re delighted to share our latest accuracy rates for facial age estimation, days before the Online Safety Act comes into force,” said Robin Tombs, CEO of Yoti. “Facial age estimation is a practical and effective way of ensuring children can enjoy an online experience without being able to access inappropriate content. It has already been named by Ofcom as a highly effective age method, but today’s results should give content and data protection regulators, businesses and the public more trust and confidence in the technology.”
Given the increasing evidence and improving accuracy of the technology, Yoti is now calling on the two key UK regulators, Ofcom and the ICO, to give guidance on the thresholds platforms should use for facial age estimation.
“With a growing demand for effective age assurance and increasing regulatory engagement, we have continued to invest and improve the accuracy of facial age estimation,” continued Tombs. “It is fast becoming an essential tool to help protect young people online, create safer, age-appropriate experiences and respect people’s privacy. The improved accuracy means even more people will now be able to use our privacy-preserving facial age estimation to easily prove their age online.”
Yoti has completed over 850 million age checks to date – the equivalent to over 1/10 of the global population – and completes over 1 million checks every day. Facial age estimation doesn’t share any information about who a user is. It only shares a yes/no response as to whether the user meets a minimum age threshold, such as over 16 or over 18.
The full white paper is available at: https://www.yoti.com/blog/yoti-age-estimation-white-paper/
Notes to editors
Most practical use cases, especially for accessing adult content, e-commerce and social media, don’t require an exact age estimation. Instead, they tend to focus on a simple decision: is this person under or over 18? Some have other requirements, such as: is this person aged over 13 or under 18. Rarely is there a need for age estimation technology to distinguish between a 49-year-old and a 58-year-old.
Yoti has developed a number of anti spoofing and fraud prevention tools to stop people from tricking the system with a photo, video or mask.
About Yoti
Yoti is a global leader in privacy-focused identity and age verification solutions, helping businesses and people build trust online and in the real world. Over the past 10+ years, Yoti’s market-leading technology has transformed how people verify their details, empowering people with more control over their data. Yoti is helping businesses worldwide to tackle global challenges like creating age-appropriate experiences, protecting young people online, reducing fraud and stopping deepfakes. With global experience across multiple industries – including social media, adult, retail, dating, gaming, gambling, and vaping – Yoti helps some of the world’s biggest brands to meet regulatory requirements, enhance platform safety, and build secure, seamless user experiences. For more information, please visit www.yoti.com.
1 A lower MAE = higher accuracy. For example, an MAE of 1.1 years means the age of someone will be estimated within 1.1 years of their age.
