A startup uses machine learning to process aerial imagery and remotely analyze insurance risks for real estate across the country.
Why it matters: The combination of AI and aerial imagery from satellites and even balloons can help insurers quickly assess property risks without a face-to-face visit, saving money and time.
How it works: Arturo’s AI model can identify potentially risky features of a property – such as roof tiles in need of repair or a pool without a fence – and estimate the likelihood of an insurable accident in the future.
- “We create high-fidelity information about the property in seconds so that insurers can understand what is actually there today, and probably tomorrow, lenders,” said John-Isaac Clark, CEO of Arturo.
Background: Arturo’s business model is a combination of two major technological trends: the ever-growing growth of aerial imagery, which can be used to capture detailed images of the ground, and the power of machine learning.
- Prior to becoming CEO of Arturo, Clark was Product Director at DigitalGlobe, a major commercial provider of space imagery and geospatial content.
- “It has fundamentally changed how we understand the location as consumers,” says Clark. “Whether from space, from satellites, from airplanes – these images gave us a way to understand where things were and where we were going.”
The big picture: Insurance may seem like the most boring of companies, but since its inception hundreds of years ago, the field has focused on using available data to predict the future – that’s exactly what machine learning is good at.
- A recent report by Porch Research found that “InsurTech” companies like Arturo raised $ 5.4 billion in venture finance last year.
- As both the data sources – Arturo recently partnered with Urban Sky to use the company’s low-cost “microballoon” images – and the computing power of AI systems increase, the InsurTech field is also growing.
The catch: Given that insurance essentially exists as a collective hedge against uncertainty, the better insurance companies can predict the future, the more difficult it may be for some properties or those with a higher risk profile to obtain protection.