Predina develops AI-based predictive crash warning platform


London-based technology developer Predina, which has been supported by the UK’s Intelligent Mobility (IM) Accelerator program, has created a system for dynamically predicting and reducing the contextual/spatial risk of crashes using artificial intelligence (AI).

Developed for the automotive technology and insurance telematics sector, Predina has built a cloud-based spatial risk platform that learns from historical crashes and contextual/spatial variables to predict ‘where’ and ‘when’ a crash is likely to happen; dynamically and in real-time. The company’s STARI (Spatio-Temporal Accident Risk Intelligence) platform has been validated through a project with UK’s Digital Catapult and an enterprise fleet. In early results, the project demonstrated over 80% accuracy of crash predictions, reduced crashes by over 25%, and increased awareness of spatial risk among drivers by 100%. The company was also one of very few deep tech companies supported by Google through its ‘Machine Learning for Good’ program.

STARI provides dynamic hotspots, the real-time and historic risk of crashes for a specific route, the safest route from A to B, and driver risk alerts/warnings. The cloud-based STARI platform works dynamically, without hardware, installations or cameras, but rather it learns from a history of crashes and the external conditions, such as weather, traffic, time of day, road layout, and visibility, to make a future prediction on ‘where’ (spatio) and ‘when’ (temporal) it is likely to happen again. The system is easily integrated either via an API (Application Programing Interface) into any digital application or via a white labelled navigation mobile application. Currently, Predina is developing an app that will help drivers plan their journey to minimize crash ‘hot-spots’ or to warn them as they enter higher risk areas.

In the long term, the platform can be integrated with the decision-making engine of an automated/autonomous vehicle (AV) to dynamically alert the driver to a high-risk area and automatically reduce its speed within these areas in real-time. The system can also be enhanced and customized through a history of AV incidents to provide a spatial understanding of risk on the roads and identify the lowest risk route. In addition to the technology, Predina is also an innovator in the user experience of safety and has developed the STARI platform to easily communicate the information in a user-friendly and accessible way via audio, satnav, mobile applications, web and pdf.

“The next stages of development are integrations and partnerships with vehicle OEMs, ADAS and AV mapping providers, telematics insurers and navigation providers. We are already in advanced conversations with leaders across this category and will announce partnerships shortly,” said Bola Adegbulu, co-founder of Predina. “We are really excited to be meeting some of the biggest automotive, telematics and mobility companies on earth, and will be sharing our vision on the future of safety and risk at two forthcoming summits in California.”

Adegbulu will be speaking at: Automotive World M:bility California in San Jose on September 17-18, and TU Automotive West Coast, also in San Jose on October 2-3.

Share this story:

About Author


James joined the Traffic Technology International team in 2017. Previously he was Assistant Editor on an engineering title for several years and has worked for various other trade magazines before that. James is happily married and has a young daughter and son who keep him busy.