Case Study: Kettle achieves more accurate wildfire risk prediction with Tribe AI

Kettle uses machine learning to balance risk in a changing climate

Kettle, a reinsurance company, was challenged by the increasing frequency and severity of wildfires due to climate change. Their industry's legacy models, which relied on outdated historical data, failed to accurately predict risk, causing market instability and skyrocketing premiums. To reinsure properties effectively, they needed a vastly improved predictive model and turned to vendor Tribe AI for expertise in machine learning and computer vision.

Tribe AI assembled a team of specialists to build a novel machine learning solution that split the problem into modeling fire ignition and contagion. By using satellite imagery and data on past fires, their model could predict the probability of a specific location burning, moving beyond the industry's simplistic methods. Tribe AI's work more than doubled the performance of Kettle's existing model, bringing unprecedented accuracy to wildfire risk prediction and the potential to stabilize the reinsurance market.

Kettle

Nat Manning

Chief Operation Officer