How risk modelers like Fathom and Verisk are using AI and diffusion models to bypass the limits of physics-based "cat" models to predict natural disasters (Financial Times)

▤ Summary

The article looks at how risk modelers such as Fathom and Verisk are using AI and diffusion models to improve natural disaster prediction. It contrasts these approaches with traditional physics-based cat models, which have limits in speed, flexibility, and scenario coverage. The piece shows how insurers and risk analytics vendors are adopting machine learning to refine catastrophe modeling. This points to a broader shift in insurance software toward AI-driven forecasting and decision support.

▦ Linked Companies

Verisk

$1B+