Independent validation of AI
Greater Than’s AI has been independently validated for both its scientific methodology and its predictive power, meaning you can feel confident in the decisions you make based on its safety predictions.
The validation builds on more than two decades of AI development at Greater Than, during which we have continuously strengthened our predictive model using driving data from across the globe.
Results
25x
The AI successfully isolates a 25x differential in
crash probability between the safest
and riskiest driver profiles.
crash probability between the safest
and riskiest driver profiles.
91x
Drivers identified as highest risk are 91x
more likely to be involved in a crash associated with a severe or major claim.
more likely to be involved in a crash associated with a severe or major claim.
Higher risk drivers = more crashes
Drivers identified as high risk by our AI consistently account for a disproportionate share of claims.
Demonstrating strong predictive power, the AI successfully isolates a 25x differential in crash probability between the safest and riskiest driver profiles.
Following an independent technical validation, I confirm the scientific rigor of Greater Than’s Crash Probability Score. A defining characteristic of this model is its foundation on actual real-world crash outcomes, rather than the proxy indicators (such as harsh braking) commonly used in the industry.
Anders Arpteg, Independent validator
Ph.D. Artificial Intelligence
We're particularly effective at predicting serious crashes
The drivers identified as highest risk by our AI are 91x more likely to be involved in a crash associated with a severe or major claim vs the drivers identified as lowest risk.
These results have clear practical implications for road safety and risk management. By prioritizing highest risk drivers, organizations can focus interventions where they have the greatest impact – helping to prevent the most costly and harmful crashes, even if not all minor incidents can be avoided.
The AI also identifies the lowest risk drivers
Because it measures driving behaviors across the entire risk spectrum, our AI is also effective at identifying drivers with lowest risk.
This matters, as it enables organizations to provide balanced feedback to drivers, supporting positive reinforcement, driver engagement and a stronger safety culture.
Because crash events are statistically rare, effectively training an AI to predict them requires a massive volume of historical and global data. Given the model performance, it is clear that sufficient data from many years and countries has been used.
Anders Arpteg, Independent validator
Ph.D. Artificial Intelligence
Meet the validator: AI expert, Anders Arpteg, Ph.D.
As VP of AI & Data at Saab Group, Anders Arpteg’s mission is to scale value from AI & Data to keep people and society safe. He has a Ph.D. in AI and over 25 years of experience spanning academia, national security, and global tech leaders.
Throughout his career, from heading AI research at Spotify and Peltarion to serving as Director of AI & Data for the Swedish Security Service and GlobalConnect, Anders has focused on building AI solutions and a culture that enables AI to thrive at scale.
Read more about our AI - and the difference it makes
Get in touch for more information
Ready to see what independently validated crash prediction can do for your organization? Our team can walk you through the benefits of a simple AI integration.
Fill in the form to contact us and we’ll get back to you promptly.