Business Icon

Business

Facial Age Estimation [white paper]

Facial Age Estimation [white paper]

Making it faster and safer to prove your age Our age estimation technology accurately estimates a person’s age by looking at their face. We built it to give everyone a secure and private way of proving how old they are in different everyday scenarios: from age checking on social platforms and online stores, to supermarket self-checkouts, bars and clubs. This privacy-friendly approach to age verification doesn’t require any personal details or documents, and all information is instantly deleted once someone receives their estimated age – nothing is ever viewed by a human.   Key takeaways from the report The current accuracy rates (Mean Absolute Errors) are: 2.96 years for 6-70 year olds. 1.52 years for 13-19 year olds. 1.56 years for 6-12 year olds. Users are not individually identifiable.  Helps organisations to meet Children’s Codes or Age Appropriate Design Codes. Does not result in the processing of special category data. Gender and skin tone bias minimised. True Positive Rate (TPR) for 13-17 year olds correctly estimated as under 23 is 99.65%. TPR for 6-11 year olds correctly estimated as under 13 is 98.91%. Download the executive summary (updated May 2022)Download the latest white paper (updated May 2022)Download the previous white paper (October 2021)

New Right to Work and Right to Rent guidance - a buyer’s guide

New Right to Work and Right to Rent guidance - a buyer’s guide

Since April 6th, employers are now able to perform Right to Work and Right to Rent checks using digital identity service providers (IDSP).  – read more about the changes here.  What are the advantages of using an IDSP for right to work and right to rent checks? Faster – no waiting for additional approvals. Pre-verified digital IDs can complete a check in seconds. Efficient – reduce the admin burden for your staff and make it more convenient for your customers. Inclusive – customers can complete checks wherever they are in the UK. Reduce friction – complete Right to Work or Right to Rent checks in seconds. Data security – improve your data security by removing the risk of sensitive data being left in your inbox. Statutory excuse – compliant with the steps an organisation can take to avoid liability for a civil penalty. What questions should you ask an IDSP? Certification Home Office recommends employers partner with a certified identity services provider (IDSP) – a list of certified suppliers will be published on the Home Office website. Certification gives you peace of mind that your Right to Work checks comply with the statutory excuse. Accessibility Some candidates may be unable or unwilling to complete checks online. How does your partner support them? Security accreditation As part of the scheme, alongside Home Office certification, get further assurance by comparing security accreditations. Trusted Sharing highly sensitive personal details can be scary, so ensure your partner shares your ethics with trusted security and processes. Reusable For organisations with a high seasonal variation in workforce, reusable digital ID offers a more economical option – more of the UK are embracing a reusable digital ID on their phones.  There will always be a balance to be made in terms of speed, friction, user experience and success rates in completing checks. Ensure your IDSP can provide the blend of service that suits your business requirements and risk profile.  Learn more about Yoti and Post Office’s Right to Work and Right to Rent solutions or get in touch for a demo. 

Future plans for Right to Work and Right to Rent guidance

Future plans for Right to Work and Right to Rent guidance

In December 2021, the Home Office announced that from April 6th, there would be changes to the guidance for completing right to work and right to rent checks.  Advice was amended at the start of the pandemic to allow right to work checks to be performed via a video call – following feedback from organisations, this temporary guidance has been extended until September 30th.  The updated Right to Work guidance will come into effect on 6th April, a new scheme under the Department of Culture, Media and Sport Identity and Attributes Trust Framework. The aim is to develop the market for digital identities, and engender trust in businesses and citizens to enable this future-focused, more efficient way of proving identity.  You will still be able to continue using video calls to complete checks – this temporary adjustment has been deferred until September 30th 2022.  However, the big change is that you will be able to accept digital remote checks from April 6th. There is a certification process being undertaken at the moment and Yoti, in partnership with Post Office, is actively undergoing its own certification.  So, how can I now perform right to work checks and ensure I’m meeting the guidelines? Video calls are still allowed until September 30th 2022 Physically checking a candidate’s document on day 1 and taking a copy is still valid From April 6, you can use a digital identity provider Read more about how our unique partnership with Post Office can help you with right to work and right to rent checks.

The different ways to check age

The different ways to check age

Checking age no longer has to rely on seeing an ID document. In fact, you don’t even need to see a name.  With Yoti Age Verification, businesses can check the age of their users without processing or storing any personal data. Users choose their preferred way to prove their age, from convenient things like a selfie or a mobile number. We work out the age, delete the personal data and share just the result with the business. That way, businesses can be confident they’re delivering age-appropriate services to the right people, whilst protecting their privacy. Here are the different ways to check age. Remember, it doesn’t matter which method someone chooses to prove their age. Yoti will always remove any personal data and share just the result of the age check. Facial age estimation People simply look at the camera on a device and have their photo taken. The image is analysed by an algorithm that has been trained to determine age by analysing facial features. A robust facial age estimation process should also include liveness detection technology to ensure it’s a real person in front of the camera. Good for: People without ID documents Global coverage Low friction   ID document  Your customers scan a photo ID document and take a selfie using the camera on their device.  Their ID can be analysed to make sure it’s genuine and the document photo is matched to the selfie.  Good for: High assurance Global coverage   Digital ID Your customers scan a QR code using their digital ID app and share a verified age attribute, such as 18+ or 21+. This requires a one-time onboarding process with an ID document and a selfie. Once created, users are verified for life and can use their digital ID to prove their age or identity details with businesses online and in person. Good for: Reusable authentication High assurance Global coverage   Credit card check Verify your customer is over 18 using their credit card details. This method proves your customer is in possession of a registered credit card, which in most countries, can only be issued to people old enough to sign a credit agreement.  Good for: Background checks Specific countries   Mobile number check Verify your customer is over 18 using their mobile provider details. Mobile phone numbers can be checked against contracts issued by mobile carriers. You should ensure the phone is in the possession of the contract holder before checking their contract and be aware parents will take out contracts for their children. Good for: Accounts linked to a mobile number Background checks Specific countries   Database check Verify your customer’s name, date of birth and address against a credit reference agency database. In some countries, users will be on a database if they have signed a credit agreement. This may exclude those in lower income groups or younger adults and students. Good for: Background checks Specific countries

Why it’s time to automate your customer verification process

Why it’s time to automate your customer verification process

You want the digital experiences your business offers customers to be highly functional and efficient. At the same time, customers expect a seamless online experience, as well as frictionless and secure payment choices.  In order to meet those needs, verifying your customer’s identity with Artificial Intelligence (AI) and machine learning should be a fundamental first step for every business to deliver better online customer onboarding processes.  However, many companies are still relying on outdated processes, causing unnecessary friction for customers and exposing their businesses to errors and potential costly reputational damage.  Automating certain parts of the identity verification process with AI encourages digital user experiences without compromising usability. It also provides better security and protects your customers, business and services from fraud in the digital world.   Here’s our guide to why you need the process and why our solution can provide you with the right level of automated identity verification.    What is automated identity verification?  Automated identity verification uses artificial intelligence and machine learning to strengthen the verification process. With a higher level of security and more efficient ID checks, it’s easier than ever to prove who your customers really are. In the broader sense, automation can support essential business needs: Improve internal operations Increase response time  Assist in necessary manual checks Reduce costly errors  Get higher success rates  Provide more accurate, quality data for better decision making    What does your company achieve with automation?   When you automate, you can: Have a streamlined user experience: Provide a smoother experience for customers. Achieve a faster onboarding process and reduce drop off rates.    Handle spikes in the volumes of onboarding: By automating some or most parts of the process, you can reduce the time taken to verify new users manually and improve your team’s speed.   Design your own user flows: With automation, you choose where to add verification within your carefully crafted user experience.     Reduce internal costs: Using automated processes allows you to choose how much of the verification process to optimise, making it cheaper for you and more efficient for customers.   Scale globally across multiple jurisdictions: Entering new markets is challenging, but with automation, you will successfully serve multiple jurisdictions without increasing cost. Plus, your teams are better equipped to verify users in newer markets in line with regional regulations.     Make AML, KYC processes more robust: Automated AML helps teams check and investigate more profiles a lot faster than manual evaluation. Provide your teams with accurate quality data and the capability to react quickly to detected misuse. Your teams can mitigate risk and reduce the possibility of exposing your customers or business to fraud.    What processes can be automated?  With our complete solution, you can automate any part of the verification process, from the document and facial verification to anti-money laundering watchlist screening. This way the level of automation you use works alongside your industry requirements.  Here’s what processes you can automate:  Data extraction checks. We extract data using Optical Character Recognition (OCR) from the document’s visual zone or by reading Machine Readable Zone (MRZ), barcodes or PDF417 barcodes whenever present (On North American documents it is printed on the back of the card). Using Near Field Communication (NFC) for ePassports, we can read the chip data, including the photo.   ID document authenticity checks. Our AI and machine learning systems can do multiple comprehensive checks on an ID document to ensure valid data. We scan the document against police databases to check they are not fraudulent, reported, lost or stolen. We test to ensure that the document is original (not a copy or damaged) and doesn’t have signs of tampering.    Biometric face match. Using machine learning, we assess whether the user’s face matches the face on the checked ID document. Our systems can quickly evaluate the face of customers against their ID’s image to identify and match their characteristics accurately.    Liveness detection. Our AI confidently detects that a person is physically present to prevent spoofing attacks and checks that your user is a real person. We can accurately detect that the image is not an automated bot. Likewise, it is not a bad actor wearing a mask or using a photo of someone else.   Address verification. To assist your teams when needing to complete proof of address, we’ll extract customer address information from supporting documents like a utility bill or bank statement using OCR technology. We’ll check their name, date of birth, or address against an official third-party database.    AML watchlist screening. Your compliance teams can automatically screen extracted customer details against thousands of AML databases as part of the identity verification process:    Sanctions and watchlists. Against 1,000 global government regulatory and law enforcement watchlists and over 100 International and National Sanctions lists. Politically Exposed Persons (PEP). To comply with enhanced due diligence (EDD) regulations, we can screen customers against a database of more than 5,000 structured sources that are monitored daily. Adverse media. We screen against the world’s most accurate database of adverse information and media entities. The data is collated into a comprehensive, structured profile through machine learning classification techniques. Relevant adverse articles related to a single entity are presented  in one structured profile with FATF-aligned categorisation. Ongoing monitoring. We can monitor a user’s profiles or entities on an ongoing basis with automated adverse information and media monitoring. You can receive alerts to any changes in a customer or business client’s risk status against real-time databases.   What are the challenges of automated identity verification? While automation can benefit your business with improved processes and help get customers through faster, it doesn’t replace human experts with knowledge and experience in verification. A combination of automation and human experts is needed for those tricker submissions. That is why we champion a hybrid approach. This approach provides a balance of automation for some, and where required, an added layer of security that automation is not capable of delivering to the process. Our leading AI technology is enhanced with our expertly-trained identity verification specialists. Layering in verification specialists gives you a 100 per cent document submission rate. It provides you with a multifaceted defence against fraud.  As a result, your platform is built on solid identity verification that is more accurate, secure, and faster to detect misuse.   Get the right level of automation

Safer Internet Day: Helping young people thrive online

Safer Internet Day: Helping young people thrive online

Today we’re celebrating Safer Internet Day (SID) – an EU-lead initiative encouraging safer and more responsible use of online technology. On this day, organisations around the world promote the safe and positive use of digital technology for young people. As part of the global landmark event, this year, the UK will explore the theme ‘All fun and games? Exploring respect and relationships online’. Young people are shaping the interactive entertainment spaces they are a part of and SID 2022 celebrates their role in creating a safer internet, whether gaming and creating content or interacting with their friends and peers. This year’s theme is a direct response to the negative behaviour young people are faced with on gaming platforms – bullying, verbally abusive language, groups ‘ganging up’ against other groups, and hate directed at LGBT+ users being just some examples. As well as creating a harmful environment, it also distracts from all the positive aspects that gaming and social platforms have to offer.  With age assurance tools like our facial age estimation technology, we know we can help to create more positive experiences for young people using these channels. Here’s how…   Providing age-appropriate services to all As of September 2021, the UK’s independent data authority, the Information Commissioner’s Office (ICO), introduced the Age Appropriate Design Code, also known as the Children’s Code. The Code aims to give young people a safe place to play, learn and explore online and is now a legal requirement. It outlines a set of standards that social media, dating, gaming, and other online services likely to be accessed by minors should follow.  It also requires businesses to design services to be age-appropriate from the ground up.  Before we can safeguard children online, we need to prove they are in fact children in the first place. Our facial age estimation allows us to do exactly this and we believe it will prove a valuable tool going forward in re-shaping the standards for gaming and social platforms!   Following the children’s code We’re leading the world in age assurance to enable children to enjoy their online experience. Our work with social media, dating, gaming and other online services help them to make their platforms safer by design and ensure compliance with the Code. We can support platforms to recognise their users are a minor and discourage them from employing nudge techniques and ensure children aren’t asked to provide unnecessary personal data or make their real-time location publicly available.  We’ve developed an array of sophisticated age assurance methods that let businesses gain the right level of assurance that someone is the appropriate age. They can choose from a range of age assurance methods to do so, from an estimated age based on a real-time selfie or a verified date-of-birth from an ID document. We only share the result of the age check, and instantly delete all personally identifiable data.  Our formidable AI-powered facial age estimation technology allows anyone to be age checked by just looking into a camera on a device. The technology is built to be anonymous and has been proven to be much more accurate than humans, estimating 6-12-year-olds within 1.28 years and 13-19-year-olds within 1.55 years. To discover more about the accuracy rates, read our regularly-updated white paper. Once you’ve discovered that your user is a child, you can then design a different user experience for them in line with the code. Our age assurance tools make it about knowing they’re a child and then providing them with age-appropriate gaming and social experiences, allowing them to thrive in the digital world! Learn more about our age assurance tools.