Car insurance is evolving and data is in the driving seat. As an insurer, if you know more about the driver’s behaviour, fave routes, parking places, the local weather conditions etc the better. It’s all about personalising the risk, consumer or fleet. More here;
UK-based deep tech enabled MGA, Humn.ai, has announced the launch of pioneering new fleet insurance proposition, Rideshur. Powered by real-time risk platform, riskOS, the new programme works to allow Humn.ai to create tailored, fair, data driven policies.
Rideshur is able to process hundreds of data points every second to generate a real-time risk score for individual drivers. The ability to generate premiums tailored to each and every driver within a fleet takes traditional insurance into the future. The product also boasts a range of reporting capabilities. Every client will gain access to the Rideshur user platform where they can review live trips and exposure data, live premiums and perform instant analysis to enhance and improve risk management policies.
Initial product trials have seen accident frequency reductions of up to 65%. The reduction in vehicle downtime alone generates additional revenues for Humn.ai’s initial fleets.
What data powers Rideshur?
Rideshur gathers more than just driver data. To create a comprehensive risk picture, its algorithms assess thousands of real-time data points including weather feeds, traffic patterns and density, roadworks, human movement and social feeds.
Using machine learning, the programme swiftly completes driver profiling while calculating unseen road risk rating, near-miss detection models and risk points of interest.
These highly sophisticated data points empower accurate rating and allow for the deployment and swapping of live models in real time, it also reduces the likelihood of under-pricing frequency and severity. It’s the use of technology for instant and fair fleet insurance.
Humn.ai Founder and CEO, Mark Musson, comments: ‘The overarching problem with the traditional insurance framework is that insurers often have to price fleets on a limited set of static risk factors. Despite the fact that commercial fleets aggregate huge quantities of data, insurers have been unable to use the data effectively.
‘We have built Rideshur to combat this problem with the application of data science, enabling better risk selection. Our algorithms detect events in real time, taking numerous data sources to calculate risk as it happens, allowing future planning to anticipate and prevent potential incidents as more insurers move away from personal motor insurance to commercial and product liability.’