The seismic shock that the insurance sector has undergone in the last few weeks will lead to big changes, most of which involve the use of automated systems, data science, remote working and AI decision making. In a few years’ time it will become the norm for typical fender-bender car collisions, where there are no injuries, to be settled by smartphone photos and video clips – at the scene. Interesting news then from Ageas and Tractable;
For the first time, one of the UK’s insurers is employing artificial intelligence to create end-to-end assessments and estimates of vehicle damage.
Ageas is using an AI solution, developed by technology company Tractable, to support some of the complex tasks that a human assessor would normally carry out when evaluating vehicle damage. For example, the AI identifies which parts of the vehicle have been affected and to what extent, and generates a full estimate including recommended repair, paint, and blend operations, as well as costs and labour hours.
After successful UK trials in 2019, Ageas and Tractable will now scale the use of the technology to resolve thousands of claims every month.
Robin Challand, claims director at Ageas, said: “At Ageas, we work to make insurance easy for our customers by delivering a best-in-class service. We look to digital innovation to help us deliver this.
Adrien Cohen, co-founder at Tractable, said: “Ageas using Tractable’s AI to generate end-to-end estimates is a breakthrough for the insurance sector worldwide. By harnessing AI at the beginning of the claims process to assess damage and generate estimates, we accelerate every part of it, creating efficiencies for the insurer and greater clarity for the policy holder. With this partnership with Ageas, computer vision is today making a positive difference for people in the real world, by helping them recover from accidents faster.
“It’s the first time that a UK insurer is using AI to generate end-to-end estimates, and is a breakthrough in how computer vision – using computers to see and analyse images and pictures – is applied on a commercial basis at scale.”
Tractable’s AI uses deep learning for computer vision, along with machine learning techniques. The AI is trained on many millions of photos of car damage, and the algorithms learn from experience by analysing a large variety of different examples.
The AI allows insurers to evaluate the damage to a vehicle, based on photos provided by repairers, appraisers or policyholders. Via a platform, Tractable’s AI shares damage estimates and guides the claim process to ensure each claim is processed and settled as quickly as possible.
Tractable’s AI has processed over $1 billion in auto claims for the world’s top insurers, including Covéa, the largest auto insurer in the French market, Tokio Marine, the largest insurer in Japan, and Talanx-Warta, the second-largest auto insurer in Poland.