Tokio Marine is using AI technology from the insurtech Tractable to study damage to car accidents in Japan.
Using computer vision to look at photos of car damage and making sense of accidents as humans would in near-real time, Tractable’s platform enables a range of repair decisions, including recommended repair, paint, and blend operations, as well as the labor hours required.
“In Japan, after an accident it can take two to three weeks to determine the amount that should be paid,” shared Hidenori Kobayashi, Tokio Marine Group Deputy General Manager. “We expect to shorten that time considerably.”
Along with allowing insurers to evaluate the damage to a vehicle, based on photos provided by repairers, appraisers or policyholders, Tokio Marine is also using a new product developed by Tractable, Loss Adjuster Application, which enables the insurer to set their own QA checks for repairers, ensuring repairs are carried out to set standards. Tokio Marine and Tractable have been working together since 2018 with the goal to improve appraisal operations using computer technology and vision. After AI training on millions of photos of car damage as well as human appraiser decisions, the algorithms learn from experience by analysing a large variety of different examples.
“Computer vision is accelerating accident recovery; the technology is here, it’s on the ground and it’s making a difference,” shared Alex Dalyac, co-founder and CEO, Tractable.