Brussels-headquartered multinational insurer Ageas is using an artificial intelligence (AI) solution developed by technology company Tractable to create car damage assessments and repair estimates.
The AI-powered technology is able to support some of the complex tasks usually carried out by human assessors, such as identifying which parts of a vehicle have been affected and to what extent.
Ageas is then able to generate a full estimate including recommended repair, paint, and blend operations, as well as costs and labour hours.
The AI is also able to accelerate how quickly tasks are completed, as policyholders can submit photos using their smartphone even while initially reporting an incident.
“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,” said Robin Challand, Claims Director at Ageas.
“We realised that Tractable’s cutting-edge technology could make a real difference to our customers in the aftermath of an accident and by using Tractable’s AI we have improved our claims experience by supporting customers when they report claims and assisting our repairers in the early assessment of what’s required.”
Adrien Cohen, co-founder at Tractable, also commented: “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,” Cohen continued.
“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, and has processed over $1 billion in auto claims worldwide.
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.
