Financial institutions use a scoring model to predict if a borrower will repay or not a loan. Banks usually ignore risks associated to climate change, such as extreme weather and sea level rise, in their scoring models. As this could be problematic for financial stability, central banks are starting to stress the importance for banks to include climate change in their scoring models. In this paper we suggest a scoring model for mortgages in Florida that takes into account flooding risk. We obtain that climate change variables are significant to predict if a borrower will not pay back the mortgage but not if the borrower will prepay the mortgage.
Raffaella is Associate Professor in Data Science at the University of Edinburgh Business School. She is Director of the Fintech PhD programme, member of the Credit Research Centre and of the Global Open Finance Centre of Excellence. She is an academic fellow at the Scottish Parliament. Her research and collaborations with the industry are focused on developing new models for analysing credit risk and Fintech. The former includes scoring models, modelling of loss given default, stress testing and interpretability. For Fintech, she has proposed novel solutions to assess risk using Open Banking data such as affordability test and credit scoring.