What is AI (artificial intelligence)?
Artificial intelligence leverages computer processing to mimic the decision making capabilities of the human brain. It’s become commonplace across our everyday lives, and offers significant benefits – performing some tasks and analysis faster and more accurately than humans. From powering the ‘smart’ assistants in our smartphones, enabling computer vision (whereby machines can interpret visual stimuli), to analyzing vast quantities of data, as will be required by the smart cities of the future, AI applications are growing every day.
Artificial intelligence has developed exponentially since the term was coined in 1956, thanks to a number of factors. Computer processing power has profoundly increased in the past 20 years; smartphones are now millions of times more powerful than Apollo 11’s guidance computers. Data, the lifeblood of any AI algorithm, has also become far more readily available, in part thanks to the critical infrastructure that harnesses it – the internet.
AI (artificial intelligence) explained
When most people think of artificial intelligence they likely think of something which is both perfect and independent. A supreme power, which eclipses the human brain in every way. But in actuality, we’re a far cry from developing this kind of ‘General AI’.
Instead, we've been able to create more specific AIs, thanks to advances in technology, ever-increasing data availability, and algorithmic developments. These systems still outperform humans, but only when applied to specific tasks. These ‘Applied AIs’ are what allow us to automate specific processes to be completed accurately and quickly.
At Onfido we use AI for the purposes of identity verification – to create trust between businesses and their customers, so they can remotely access goods and services.
How can AI verify someone's identity?
AI can be used to verify identity in a number of ways. It can help in taking user-provided data like a home address, name, and date of birth, and matching it against trusted data sources. It can analyze passive fraud signals to help businesses spot anomalies at sign-up. And it can also be used to power document verification and biometric verification.
AI is well suited to these tasks because both businesses and their customers expect them to be completed quickly and accurately – in order to grant the customer quick access to services, and enable the business to prevent fraud and conduct efficient know your customer (KYC) processes, which they are often regulatory mandated to complete. AI can automate these processes more quickly and accurately than humans are able to process them.
AI in KYC, AML, and CDD
Many regulated businesses need to complete CDD (customer due diligence) as part of their KYC and AML (anti-money laundering) requirements. One part of these checks is identity verification – in which the business needs to gather information from potential customers and verify it is legitimate. Traditionally, these processes have been burdensome for both parties. Customers may have had to travel to a business in person to provide documentation to be verified, or submitted documentation digitally and waited for it to be processed manually.
AI has enabled customers to submit documentation digitally from wherever they are, and gain access to services in minutes versus hours. This reduces friction in onboarding processes and so increases acquisition rates for businesses, in turn, increasing revenue – while still enabling them to be regulatory compliant.
How is AI used in fintech?
Fintechs employ AI for many different purposes. It’s used across nearly all facets of customer acquisition, systems management, risk analysis, fraud detection and more. At Onfido, we partner with hundreds of leading fintechs to verify customer identities using AI – to navigate regulatory compliance, detect fraud at onboarding, and effectively onboard millions of customers.
AI is frequently used to power biometric analysis. Biometrics are measurements relating to human characteristics that are frequently used to enable access to systems and services, for example fingerprint, voice, and facial biometrics as used by smartphones to authenticate users.
Biometric verification using AI
AI can be highly effective at matching facial biometrics. For the purposes of KYC compliance and fraud detection, businesses often use a document and biometric based solution. A user provides the business with an image of a photo ID to be analyzed for authenticity. They also provide a selfie taken at the moment of onboarding. AI is used to match the facial biometrics between the photo ID and selfie to provide the business with assurance that the identity document was submitted by its rightful owner, and not by a fraudster who may have illegally obtained the document.
AI is particularly well suited to this task. A 2014 study found that even trained passport officers averaged a 14% error rate when matching faces – but the figure is likely to be even higher for untrained individuals conducting this examination for businesses.
However, AI is not infallible – and should be trained ethically and monitored for algorithmic bias. Algorithmic bias refers to systematic and repeatable errors that result in unfair outcomes, such as discriminating against or providing undue advantage to one group of people over another. Algorithmic bias in facial recognition can mean that the biometrics demographic groups are not accurately analyzed, leading to false rejections or false matches during the identity verification processes. At Onfido we use balanced data sets to train our AI models, and monitor results – you can learn more about how we mitigate AI bias here.
AI for document analysis
As part of identity verification processes, AI can also be used to analyze identity documents to help businesses meet their KYC requirements. Learn more about KYC processes in our blog – what is KYC.
Document verification is a high assurance method of verifying user identity compared to validating user supplied data against trusted sources. If processed manually by human agents it can introduce friction by increasing turnaround times – the time taken from receiving a capture of a document, analysis being completed, and action taken by the business to either reject or accept the applicant. AI can automate this analysis and complete accurate document analysis in a matter of seconds.
How does Onfido use AI?
At Onfido we use AI to provide automated digital identity verification for 800+ businesses worldwide. Our proprietary AI, Atlas™, has been built over 10 years by a dedicated team of hundreds of researchers and engineers to make our analysis fair, fast and accurate. Atlas’ analysis helps businesses acquire more customers, navigate global compliance, improve operational efficiency, and prevent identity fraud. You can learn more about ‘what is identity fraud’ in our blog.
What makes Atlas AI fair, fast, and accurate?
Fair. Atlas has been trained on balanced datasets that are representative of real-world variations in race and ethnicity to mitigate AI bias.
Fast. Atlas processes 95% of ID verifications in under 10 seconds – a year-over-year improvement of 54%.
Accurate. Atlas is built in-house using a unique micro-model architecture that combines over 10,000 models trained to detect specific fraud markers.
Powered by Onfido Atlas™
Atlas ensures our verification is fair, fast, and accurate.
The Real Identity Platform
Our end-to-end identity verification platform – designed for you to build identity around your business.
Seamlessly integrate compliance databases into your workflows to meet KYC and AML requirements.