Students Create Interactive Natural-Hazard Risk Dashboard for Mortgages

Graduate students at the University of Maryland's Robert H. Smith School of Business have developed an interactive, online tool to assess natural hazard-related risks to residential mortgage borrowers across the United States.

The Mortgage Natural Hazard Analyzer is produced and facilitated by Master of Quantitative Finance students led by Professor of the Practice and Smith Enterprise Risk Consortium (SERC) Director Clifford Rossi. The Tableau-based dashboard is designed to be a resource to help policymakers, credit investors, insurance companies and others to interactively examine the impact of different hazards on homeowners, including drill downs on financially vulnerable borrowers.

“The home often is the most valuable asset an individual will have, and with the number and intensity of extreme weather events on the rise, the availability and cost associated with homeowners’ insurance is moving toward becoming a major crisis in this country,” said Rossi, who developed the mortgage industry’s first statistically-based automated underwriting scorecards for FHA and VA loans during a previous tenure at Freddie Mac.

Earlier this year, climate risk financial modeling firm First Street projected $5.4 billion in lender losses from mortgage foreclosures by 2035. And Federal Reserve Chairman Jerome Powell recently told Congress, “If you fast-forward 10 or 15 years, there are going to be regions of the country where you can’t get a mortgage.”

Rossi and his students created the new dashboard based on 13 million single-family mortgage loans and merged this with FEMA's National Risk Index tool for all 78,000 U.S. Census tracts across 18 different climate hazards, including earthquakes, wildfires and hurricanes. They then randomly selected 1 million mortgage loans and used different machine learning models and performance statistics to analyze the data.

The resulting dashboard allows the user to 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 and income. 

“Lenders, insurance companies and policymakers all could use this information during the underwriting process and for figuring out which areas need more government resources and/or intervention,” Rossi said.