AI in identity verification: Improve pass rates and reduce fraud

A 75% identity verification pass rate might look perfectly healthy. But what if customers under 25 are passing at 60%, one market has suddenly started underperforming, or a particular check is creating unnecessary friction for thousands of genuine customers? 

Looking at individual verification outcomes won’t necessarily tell you that. If you look at the patterns emerging across thousands or millions of identity journeys, though, you can work out what those patterns mean for your onboarding process. 

That’s where AI is starting to change identity verification. 

AI already authenticates digital identity documents, matches faces, detects liveness and flags fraud in Know Your Customer (KYC) and Know Your Business (KYB) onboarding flows. But increasingly, it’s turning verification data into intelligence that shows you what customer segments are struggling to pass, why, what a realistic pass rate is, and what’s worth testing next. It’s also a reliable way to catch AI-generated fraud. 

Discover how Foresight, our AI-powered intelligence layer, can help optimize your pass rates while staying ahead of increasingly sophisticated fraud. Book a demo.

What’s changing about AI in identity verification? 

In modern digital identity verification, AI is often used to enhance and automate checks that confirm someone is who they claim to be. It can, for example, review an ID document for signs of tampering, such as a missing security element or fonts that don’t match, much faster – and with greater accuracy – than a human reviewer. We cover this in greater detail in a section below. 

Now, AI can help you understand why groups of customers fail and provide recommendations to optimize your verification journeys and improve pass rates. 

However, while AI can be useful, it’s important to remember that it isn’t a replacement for human judgment. Most implementations still pair automated decisioning with human oversight for edge cases. 

How to use AI to optimize identity verification pass rates: 6 strategies (including peer benchmarking) 

Optimizing your pass rate isn’t about just waving more people through. You need to find the spots where genuine customers are hitting friction they shouldn’t have to and fix them – without loosening the controls that keep fraud and compliance risk out. 

Here’s how: 

1. Analyze pass rates by customer segment to uncover hidden friction 

A healthy overall pass rate can mask much lower pass rates among specific groups. AI can break results down by factors like age and geography to show exactly which groups are struggling and where a journey needs to adapt. 

A verification journey built on the assumption that every customer has an established credit history, or is savvy enough to navigate a multi-step digital process may struggle to match certain groups of users – not because they’re fraudulent but because the journey wasn’t built for them. For example, a GBG analysis over a 3-month period that included more than 10 million transactions representing multiple industry sectors revealed that younger demographics (those under 30 years of age) experienced identity failure alerts at twice the rate of older customers. 

AI-driven segment analysis tells you which of these frictions is hurting your pass rate rather than leaving your team guessing. 

What’s more, you can use these insights to personalize verification journeys at scale.  

For example, if most of your customers are under 25, do you really need to run mortality checks on everyone? And if certain customers struggle with document-based verification, could another compliant verification route provide a better experience? 

2. Benchmark performance before deciding what needs fixing 

A 75% pass rate might look good based on your history – until you learn comparable journeys are achieving closer to 85%. When you use AI-powered benchmarking to compare your performance across relevant peers, customer segments, markets, or journey types, you learn what pass rate you should be aiming for. 

Benchmarks also stop you from chasing problems that aren’t just yours. If similar organizations are experiencing the same shift, the cause is probably market-wide, not something broken in your configuration. 

Either way, benchmarking gives you an evidence-based target before you touch any rules. 

3. Pinpoint the checks and data gaps lowering your pass rate 

How do you turn the vague problem of “my pass rate is down” into a specific one you can actually solve? 

Here’s an idea: use AI to break down the performance of individual checks and rules to uncover where your customers are failing and why. 

For example, a failed verification doesn’t always mean the person isn’t genuine. Sometimes it’s a misconfigured check or a data source with weak coverage in a particular market. A credit reference check that performs well in the UK may have thinner records to draw on in a market where fewer people have formal credit histories. 

4. Turn performance insights into targeted recommendations 

AI can recommend specific fixes: adjustments to your verification configuration, data capture, data sources, or the capabilities used within a journey. If a segment is failing because the current data source isn’t producing enough matches, AI might identify an additional source worth testing. 

5. Test AI recommendations before rolling them out at scale 

You should treat AI recommendations as a starting point, not a hard rule. 

Instead of implementing a recommendation and hoping it works, test it against a subset of traffic or over a defined trial period and measure what happens. 

This way, you’ll know a change works because you’ve seen it in action. 

6. Treat optimization as continuous (not a one-time event) 

Optimizations that you make today may not work months from now. 

Customer behavior, fraud patterns, data coverage, and your own configurations can change over time, which creates new performance issues that weren’t there when you last reviewed a journey. AI-powered ongoing monitoring can alert you to changes. 

Why AI is crucial to combating AI fraud 

AI-enabled fraud puts identity teams in a difficult position: the same technology that makes verification more powerful is also helping fraudsters beat it. After all, deepfakes, synthetic identities, manipulated documents, and injection attacks aren’t threats that the human eye or static rules can reliably detect. 

Effective fraud prevention increasingly requires AI on the defensive side. Machine-learning models can comb through large volumes of identity, behavioral, and biometric data to identify subtle anomalies and fraudulent activity that would slip past a human reviewer or a fixed rule. 

Where AI is already being used 

Of course, AI has been used in IDV for a long time now. These are some of the most common ways AI is automating individual verification checks: 

• Document verification: AI scans government-issued IDs like a passport or driver’s license and pulls out the relevant fields like name and date of birth. It looks for security features like holograms and optically variable ink and spots tampering a human might not, such as portrait lighting that doesn’t match the rest of the image or a barcode that doesn’t line up with the printed text. 
  
  
• Biometrics and liveness detection: Is the person in the selfie the same as the one in the ID? And are they actually there, not a photo, screen, mask, or deepfake impersonating them? Using facial recognition and liveness detection, AI can handle these checks, too. 
  
  
• Fraud detection: Individual checks can miss patterns that only show up at scale (several accounts with different names and addresses that all share the same device, for example). AI helps by sifting through large volumes to surface what a single review might miss. 
  
  
• Decisioning and automation: Every check gets weighed against your rules and thresholds, so low-risk users can clear automatically, and others get flagged for review. 

The above scenarios use AI to help determine whether an individual verification attempt can be trusted. But when you use AI to analyze the data generated by thousands or millions of attempts as well, it can help you understand if your verification process is working overall. 

How GBG helps businesses optimize identity verification with AI-powered insights 

There’s a difference between knowing your pass rate and understanding what you can do to improve it, and that’s what our Foresight solution was built to address. It’s an intelligence layer that sits on top of your identity journey performance, adds anonymized peer benchmarking, and turns both into recommendations tailored to where and how you can improve. 

Foresight runs on top of our clients’ GBG solution sets. For example, this can be GBG Go, our identity verification platform with more than 110 configurable modules like document and biometric verification that use AI to authenticate documents, match faces, and detect liveness in onboarding flows. What’s more, Foresight requires no implementation. 

Here are three ways you can use Foresight to improve your identity verification process: 

Use AI to better interpret your verification data (and get tailored recommendations) 

GBG processes about 400 million identity verification transactions a year across more than 20,000 customers. This scale gives our Foresight solution’s recommendations real context. 

Instead of handing you raw performance data you must interpret yourself, our solution provides AI-powered recommendations based on your existing GBG integration. This includes potential improvements to your configurations, data sources, data capture, and capability usage. And it doesn’t only suggest what to add: it also points out what may be worth removing, like a low risk check that’s actively hurting your pass rates, along with the evidence to back up the suggestion. 

Understand the gaps in your pass rate with peer benchmarking 

Our Foresight solution measures your numbers against relevant peer groups and sector trends, drawn from anonymized data across our customer base. 

Here’s an example of what it can reveal: In the fintech sector alone, a GBG analysis using Foresight shows that under-30 pass rates are about 80% compared to 90% for those over 30. What would it mean for your revenue if you knew you could confidently increase pass rates for a target segment by over 10%?   

Hear directly from one of our clients about the value they see in using Foresight: 

Be proactive and save time with real-time performance metrics and automated alerts 

With Foresight, you can be proactive with alerts that signal when something has shifted, such as an unexpected change in pass rates within a customer segment. From there, you can explore failure reasons to understand the underlying drivers, pinpoint where the change is occurring, and determine what is contributing to the shift. 

It also helps you respond sooner, and more precisely, when risks change. By analyzing performance across customer segments and markets, you can identify where controls need tightening rather than introducing additional friction for every customer. Tracking rule effectiveness over time tells you whether existing controls continue to perform as expected as fraud patterns shift. 

How Foresight helped a customer increase its pass rate by 10% 

One of GBG’s financial services clients had a 70% identity verification pass rate. Our Foresight solution’s peer benchmarking showed an 80% pass rate was achievable in their sector. 

Foresight analyzed the client’s performance and recommended adding a data source to its verification journey. Rather than implementing a change based on the AI recommendation alone, we worked with the client to test the proposed change and measure its impact. 

Real-time performance metrics demonstrated a 10% uplift in pass rate, taking the client from 70% to 80%, which is exactly what the benchmarking predicted. 

Turn identity verification data into continuous improvement with Foresight 

AI is changing not only how businesses verify identities, but what they can learn from every attempt. There’s an opportunity to use those insights to build an identity strategy that evolves alongside your customers and the threats you face. 

Ready to see what Foresight can uncover in your identity verification data? Book a demo today. 

FAQ: AI in identity verification