Startups use satellite imaging, public databases and algorithms to map out threats of natural disasters for specific towns—and even buildings—that back bonds
For centuries, bond investing has boiled down to forecasting two things: which way interest rates are going to move and how likely a borrower is to repay its debts. A handful of startups are betting that to predict repayments in the future, bond analysts will need better data on something they’ve long overlooked—climate risk.
The new firms are competing to design algorithms that can predict the likelihood of natural disasters hitting specific towns, industrial parks, even individual buildings, and how much damage they will do. That could become more relevant as wildfires, floods, storms and drought strike more frequently, creating potential losses for holders of municipal, corporate and mortgage-backed debt.
One company marketing such geospatial data to Wall Street is risQ, a Boston-based firm launched in 2016 by a handful of academics. The firm created a digital grid that divides the U.S. into 100-meter by 100-meter patches of dirt, forecasts the probability of climate events in each square and assigns associated risk scores to the bonds that would be affected.
THE WALL STREET JOURNAL
by MATT WIRZ
JULY 10, 2022