Abstract
AbstractWe use a dataset of 12 million residential mortgages to investigate the loan default behavior in several European countries. We model the default occurrence as a function of borrower characteristics, loan-specific variables, and local economic conditions. We compare the performance of a set of machine learning algorithms relative to the logistic regression, finding that they perform significantly better in providing predictions. The most important variables in explaining loan default are the interest rate and the local economic characteristics. The existence of relevant geographical heterogeneity in the variable importance points at the need for regionally tailored risk-assessment policies in Europe.
Highlights
LiteratureThere is a substantial empirical literature on the determinants of mortgage delinquency and default, mainly focused on the United States
Our results indicate that the current interest rate and LTV have a significant impact on default occurrence and that they are highly nonlinear, explaining the better performance of boosting models related to the logistic regression
A better understanding of the default drivers is of primary importance for policymakers in order to reduce the societal costs associated with a default and avoid the inefficient allocation of resources
Summary
There is a substantial empirical literature on the determinants of mortgage delinquency and default, mainly focused on the United States. Bajari, Chu, and Park (2008) study the relative importance of the various drivers behind subprime borrowers decision to default. They point at the role of the nationwide decrease in home prices and increase in borrowers with high payment to income ratios as main drivers of default. Campbell and Cocco (2015) propose a model of mortgage default for the United States in the presence of labor income, house price, inflation, and interest rate risk to show how different shocks contribute to the default decision. One important result from this study is that negative home equity tends to occur when house prices decline in a low-inflation environment and for moderate levels of negative home equity, default is more likely as borrowing constraints bind more tightly on households. Babii, Chen, and Ghysels (2019) analyze the spatial dependence among commercial and residential default using Generalized Autoregressive Score(GAS) models
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
