Articles - The ADAS Data Challenge


Having studied immense amounts of data, at LexisNexis Risk Solutions we believe that by 2025 all new cars rolling off the production line will be ‘connected’, and the connected car data marketplace will be worth $5 billion. This is a huge opportunity, and something we’re extremely excited about. But there is already connected car data piling up and underutilised. Forward collision warning, adaptive cruise control, parking assist, lane departure warnings, blind spot monitoring.

 By Paul Stacy, R&D Director and Director of Automotive Development EMEA, LexisNexis Risk Solutions 

 These features are in many cars already, but the safety benefits they bring are not yet used in insurance risk assessment and pricing because insurers can’t access the data at point of quote.

 The potential of ADAS data
 A recent US study of 12 million vehicles assessed the impact of ADAS features on claims. The study found these features are preventing accidents and reducing the severity when collisions do occur. Of course, this reduces the frequency and cost of claims. There is something very exciting here, with huge potential to save lives and cut insurance costs.

 Most new vehicles have at least two ADAS features. 60% of the UK car parc now has ADAS, and that figure is growing all the time. But how can insurance providers price accurately for the reduced risk these vehicles represent?

 When it comes to any vehicle, there are three levels of data.
 1. The most basic: model-level data, e.g. engine size, body type, transmission. This is the easiest to access but is the least informative as it is too generic.
 2. One-up is trim-level data, e.g., wheel size, interior fabric, optional technology available. Available from 3rd parties, this gives insurance providers a better idea of cost-to-repair. However, it doesn’t list specific features each customer adds when they order a brand-new vehicle, so the value is limited.
 3. The ideal is VIN-level data. Essentially the DNA of the car, this comes direct from the manufacturer, detailing every feature installed on individual vehicles, every one of which is different.

 Only VIN-level data confirms which ADAS options are installed on an individual car. This is extremely useful in risk assessment and pricing, although future developments will add further value as driving information such as the frequency with which each safety feature is triggered will feed into usage-based insurance..

 The data difficulty
 In Europe alone there are hundreds of insurance providers, more than 15 OEMs which have hundreds of different brands and models. Data therefore comes in a multitude of formats, with different names for similar features. Before this mass of data can produce consistent results, for building attributes and creating scores that can be useful to insurance providers in pricing and underwriting, it must be normalised, cleansed and analysed.

 This sort of industry challenge lends itself very nicely to a third party, neutral server which provides an exchange service. LexisNexis Risk Solutions is not the only provider, but we have what we believe to be a unique aspiration to solve the many-to-many problem. We have already learnt a huge amount through our relationships with OEMs and are therefore well-placed to build a solution that works for them as well as for insurance providers.

 OEMs are large complex companies usually comprising three separate entities – the manufacturer builds the vehicles and handles procurement and distribution; another entity manages the aftermarket servicing and repairs; a third handles leasing and insurance. These three silos are typically separate companies with independent digital and connected car teams. The challenge facing the exchange service provider is to bring together every silo and satisfy their individual requirements.

 The road ahead
 Clearly, we are still some way off reaping the full insurance benefits of ADAS, with several ongoing issues to resolve. One significant difficulty is that ADAS features, still being relatively new and built by many different manufacturers, do not perform uniformly across makes and models. Some manufacturers are simply doing a better job than others.

 While we wait for the market to mature further and deliver more uniform data in a way which can be utilised by insurance providers, we have created a range of products to utilise and multiply the value of data currently and soon-to-be available. The solutions will provide insurance providers with individual vehicle scores based on build data, which ADAS are fitted, and estimated claims outcomes.

 These are exciting times for the motor insurance industry, on the brink of a risk, pricing and underwriting revolution based on accurate, individual, instant vehicle and driving data. Bringing the industry together – OEMs and insurance providers – is the only way in which all parties can benefit and pass on the benefits to consumer customers via reduced premiums and safer roads.
  

Back to Index


Similar News to this Story

Actuarial Post Magazine Awards Winners Edition December 2024
Welcome to the Actuarial Post Awards 2024 winner’s edition and we hope you enjoy reading about their responses on having won their award. The awards
Guide to setting expense reserves under the new Funding Code
The new defined benefit (DB) funding code of practice (new Funding Code) requires all schemes to achieve funding levels that ensure low dependency on
Smooth(ing) Operator
Private equity can be a great asset. It’s generally the most significant way to have any real world impact as an investor (eg infrastructure assets li

Site Search

Exact   Any  

Latest Actuarial Jobs

Actuarial Login

Email
Password
 Jobseeker    Client
Reminder Logon

APA Sponsors

Actuarial Jobs & News Feeds

Jobs RSS News RSS

WikiActuary

Be the first to contribute to our definitive actuarial reference forum. Built by actuaries for actuaries.