How Tractable is training AI to assess property damage

InsurTech-Tractable-AI-artificial-intelligence-property-damage

InsurTech Tractable’s AI technology has expanded from assessing auto damage, to property. For the technology, this is a big step, but one in which the InsurTech is tackling.

According to Tractable, homes are harder for AI to assess than cars. This is partly due to the fact that parts of cars are more standardised. For example, most cars will have two or four doors, whereas properties do not have a standard number. There is also more variation within a property than within a car.

It is commonly assumed that if AI can assess damage to a car, this is transferrable to assessing damage to a property. However, Tractable stresses that in reality it is actually very challenging for AI.

How does Tractable get around this?

Breaking down complex tasks into simply, digestible steps is key. This simplification is done by consulting with insurance experts who are experienced in assessing properties and the specifics of property damage.

The result, Tractable said, is that this complex picture becomes a series of narrow, circumscribed tasks that current AI technology can deal with. On top of these AI tasks are sets of rules and traditional software which act as the glue that holds it together.

Although the step from assessing auto damage to property damage is a big leap for AI technology, Tractable argue that it is still very much within reach and can be trained.

In a basic sense, the process of extracting and assessing information is the same. A photo is taken of the damage, uploaded using an app, Tractable’s technology then breaks down the item into component parts, which are then assessed individual. The technology looks at each part to determine whether the damage is due to the storm or normal wear and tear and subsequently asks whether each part can be repaired or needs to be replaced.

AI is continuously learning

At the moment, Tractable said AI deals with relatively modest tasks, like broken windows. But in future it should be able to deal with more comprehensive damage, including homes flattened by a typhoon.

Applied AI is trained on historic cases that have been assessed by humans – but it learns continuously and, where necessary, receives input, oversight and correction from human experts.

This means that over time, the AI will get better at the narrow tasks it’s been assigned and will also expand its capabilities within those tasks.

The benefits are far-reaching. Especially in a world where natural disaters and extreme weather are on the rise, it is more important than ever to be able to help people recover their homes and lives faster.

Read more here.

In an exclusive with FinTech Global, Sakina Najmi, VP marketing at Tractable explained how Tractable is exploring the real-world opportunities of applied AI.

Copyright © 2022 FinTech Global

Enjoying the stories?

Subscribe to our weekly InsurTech newsletter and get the latest industry news & research

Investors

The following investor(s) were tagged in this article.