Smith Professor, Students Take On Mortgage Climate Risk

A recent NOAA National Centers for Environmental Information report confirms rising costs from weather extremes in the United States: From 2016-22, 122 disasters killed at least 5,000 people and inflicted more than $1 trillion in damage.

Much of that destruction occurs to housing, ultimately exposing mortgage providers to increased risk. Now a risk expert and his students at the University of Maryland’s Robert H. Smith School of Business have developed a new way to quantify the liability.

“Climate risk is complicated because it’s a global risk,” said Professor of the Practice Clifford Rossi, who spent 25 years in risk management at banks and government agencies. “This is not just about managing risk, it’s also about managing uncertainty—a much harder game.”

A lot of the problem stems from a dearth of good data and models for analyzing the risks, said Rossi. That’s where his students came in. He led of 11 of them in Smith’s Master of Quantitative Finance program in a project with government-sponsored mortgage enterprise (GSE) Freddie Mac to build a model that leverages machine learning to pinpoint the regions in the U.S. with the highest climate risk.

The students created an interactive dashboard of all 13 million single-family mortgage loans originated in 2021 and merged it with the Federal Emergency Management Agency's National Risk Index tool for all 78,000 census tracts across 18 different climate hazards, including earthquakes, wildfires, hurricanes, coastal and river flooding, tornadoes and drought. Then they randomly selected 1 million mortgage loans and used a battery of different machine learning models and performance statistics to analyze the data, looking for such effects as adverse selection against Freddie Mac and and fellow GSE Fannie Mae, impact on low- and moderate-income borrowers and minorities, and other key effects.

“Anyone can point and click on any county in the U.S., for any climate hazard type and get figures on borrower characteristics such as race, age, income,” said Rossi. “It is quite amazing.”

Rossi and his students are also conducting some machine learning analysis on that data to differentiate high-hazard risk areas from others based on borrower, tract and other characteristics. The Smith School plans to make the tool available online.

Freddie Mac, Fannie Mae, banks, insurance companies and policymakers could all use this information for underwriting mortgages and insurance policies; policymakers could also use it to determine which areas need more government resources. Rossi’s students presented their findings to executives on Freddie Mac’s Climate Risk team.

Rossi called the project “the finest student presentation on a highly technical subject I have ever been involved with.” He said senior leaders at Freddie Mac were also impressed with the extent and complexity of the students’ analysis, and their ability to explain difficult concepts, calling the presentation better than some by employees and consultants.

Right now, another group of his students is working with Fannie Mae on modelling flood risk, building on a student project from last year.

He’ll continue leading projects on climate risk, eventually as part of the Smith School’s new master’s degree track in climate finance in the Master of Finance and Master of Quantitative Finance programs, starting in Spring 2024.

“This is a growing area,” said Rossi. “Many governments around the world are involved in trying to get their arms around this, and these students would need those tools adapted from our standard finance concepts but focusing specifically on solving climate-related financial issues.”