Augmented Intelligence: The Best AI for Online Identity Verification

How does augmented intelligence strengthen digital identity protection?

Comparing Artificial vs. Augmented Intelligence

What is Artificial Intelligence?

Artificial intelligence (AI) is the broad concept of machines being able to carry out tasks that, if performed by a human, would require the person to use their “intelligence” to perform the tasks.

Machine learning is a popular application of AI where machines are fed large amounts of data and learn to make predictions on new data.

What is Augmented Intelligence?

Augmented intelligence emphasizes the fact that AI technologies have been developed specifically to help humans, rather than to replace them.

In this way, augmented intelligence applications combine human and machine intelligence. It is important in systems where the risk of failure is too great or the AI is not evolved enough to take humans completely out of the equation.

Does it matter which AI your identity verification solution provider uses?

The short answer is yes.
Augmented intelligence solutions use AI to identify suspicious IDs and expedites the decision-making process, enabling identity experts to make faster, better verification decisions.

Some identity verification solution providers rely solely on artificial intelligence to perform ID and “selfie” checks for online identity verification, claiming it eliminates the need for human review. The truth is, AI is almost, but not entirely ready to remove humans from the identity verification process.

What happens without augmented intelligence in AI verification?

If your AI verification provider fails to use augmented intelligence, the consequences can be costly.

Without augmented intelligence (via expert, real-time human review) your customers are frequently redirected to manual processes for verifications that fall in the “maybe” zone, which can result in:

  • Onboarding friction
  • Lost conversions
  • Time and expense of manual review
  • Dissatisfaction and poor customer experiences

Why does artificial intelligence fall short?

Artificial intelligence brings huge value to online identity verification. But it’s not ready to lead the way yet. Here’s where it falls short:

Need for Big Data

Effective algorithms require huge datasets for each type of ID you wish you verify.

Number of ID Types and Subtypes

A provider like Jumio can support over 3,500 constantly-changing ID types and subtypes. AI models must support them all.

Blurriness, Bad Lighting and Glare

Picture quality is dependent on user’s ability to capture a good image from their device.

The Challenge of Omnichannel

Verifying customers across devices presents additional challenges for AI models.

The Selfie Requirement

Many online companies require a selfie to ensure the picture in the selfie matches the picture in the government-issued ID. AI models are still perfecting this “match,” especially when ID photos are outdated.

Liveness Detection

New types of fraud, including spoofing attacks on selfies, can stump an AI model.

“But a dirty little secret about industrial-strength AI (artificial intelligence) is that many of these systems are trained and evaluated on datasets created and labeled by thousands of human raters.”
JOEL TETREAULT, GRAMMARLY

How does augmented intelligence work for online identity verification?

User performs identity verification
AI/machine learning evaluates the ID/identity
AI delivers yes or no answer OR routes to expert for review
Good customers go through the process without friction

How Jumio Uses Augmented Intelligence

Jumio uses machine learning and artificial intelligence to identify parts of the government-issued ID (e.g., driver’s license or passport) that are suspicious. This guides our ID experts to help speed the process and direct the focus of their review.
Big Data
Jumio has verified more than 225 million identities, which means we have deep experience reviewing large volumes of government-issued IDs from across the globe. This is key to training robust algorithms and accurately extracting and structuring the data, as well as spotting manipulation.
Informed AI
To better inform the algorithms, there needs to be a continuous feedback loop to incorporate the judgment of our verification experts. Jumio leverages verification experts to review and refine our algorithms which speeds up the learning curve.
AI Engineers
Jumio created AI Labs to boost the development of machine learning models, develop best practices and to continue as a platform of innovation.
Experience
Jumio has been developing our AI models by intelligently tagging valid and invalid ID documents over the last five years. This experience and our global scale enable us to more accurately recognize fraudulent IDs in seconds.

Get Started

Let a Jumio expert show you how easy it can be to integrate our automated verification solutions into your onboarding process, whether it be within your app or on your website. Request more information here and we’ll be in touch shortly.