3 min read

Share on:

New AI solution to help homeowners recover faster from natural disasters

  • AI Property, from Tractable, uses artificial intelligence to assess the amount of external damage to buildings caused by wind, hail and hurricanes
  • Applying AI to property can accelerate damage assessment from several months to a single day
  • The solution is now being used by a major Japanese insurer, MS&AD Insurance Group, to help homeowners in Japan recover faster after natural disasters, such as Oct 2021’s Typhoon Mindulle
  • AI Property is now available in North America

Tractable, the company developing artificial intelligence (AI) for visual assessment and disaster recovery, today launches AI Property, a new solution that assesses damage to buildings caused by hurricanes, floods and other natural disasters.

AI Property allows anyone with a smartphone to quickly and easily assess the external condition of a damaged property through a mobile-friendly web-based app, by taking photos and submitting them to Tractable’s artificial intelligence platform, which mitigates the challenge of having appraisers onsite to assess damage in the wake of disaster. 

The AI, which has been trained on a large database of claims and damaged property, makes an immediate assessment of the amount of damage it sees and relays this to the homeowner’s insurer. Whereas in a major natural disaster that process can take several months, now it can happen as quickly as in a single day. 

Alex Dalyac, Co-founder and CEO of Tractable, said: “Climate change is leading to more frequent and severe natural disasters. Hurricanes leave households without a proper home to live in. By allowing homeowners to immediately self-assess their homes via AI augmented damage appraisal, insurers can intervene faster and at greater scale, to help their customers at their time of greatest need.“

Tractable has been working in Japan with one of the world’s leading insurers, MS&AD Insurance Group Holdings Inc., to use AI Property to help homeowners in Japan during the country’s 2021 typhoon season. The technology has already been used to process real claims from October’s Typhoon Mindulle, resolving them as quickly as in a single day.

After a typhoon, MS&AD policyholders can use the AI to take pictures of high frequency, wind-related damage to a fence, wall or other outdoor area with their smartphone and send them to their insurer for assessment. In the future, MS&AD and Tractable expect to expand AI coverage to include indoor damage, such as water leakage and smoke. 

For now, MS&AD will use the AI only for wide-area disasters such as typhoons, and the estimates calculated by AI will be verified by humans. Insurers deploying the AI first and over the largest number of cases will see it learn and attain full automation the fastest. 

Ikuo Kudayama, Senior GM, Claims Division at Mitsui Sumitomo Insurance, subsidiary of MS&AD Insurance Group Holdings Inc., said: “We are proud to be the first major insurer in Japan to be using AI to help homeowners after a natural disaster. When a typhoon occurs, the devastation is such that assessing everyone’s homes quickly is not always immediately possible. With AI, we use tomorrow’s technology to help our policyholders today, ensuring we help them as much as possible at their greatest moment of need.”

Akira Yano, GM in charge of Natural Disaster Measures, Claims Service Division at Aioi Nissay Dowa Insurance, subsidiary of MS&AD Insurance Group Holdings Inc., said: “We will continue to expand our services to meet various customer needs, and realize true Customer Orientation.” Since 2014, Tractable has developed AI to accelerate accident and disaster recovery, and over 25 of the world’s 100 leading insurers already use its technology to understand damage to vehicles. The company is now applying what it has learned from auto appraisal to understanding property, and has worked extensively with property experts to prioritize the elements of the home where AI can add most value – from standalone external objects, to elements like fences and walls.