Explaining Mortgage Defaults Using Shap and Lasso

dc.authorscopusid 55512229700
dc.authorscopusid 57223099751
dc.contributor.author Öztürkkal, Ayşe Belma
dc.contributor.author Wahlstrom, Ranik Raaen
dc.contributor.other International Trade and Finance
dc.date.accessioned 2025-01-15T21:37:53Z
dc.date.available 2025-01-15T21:37:53Z
dc.date.issued 2024
dc.department Kadir Has University en_US
dc.department-temp [Ozturkkal, Belma] Kadir Has Univ, Fac Econ Adm & Social Sci, Dept Int Trade & Finance, Istanbul, Turkiye; [Wahlstrom, Ranik Raaen] Norwegian Univ Sci & Technol, NTNU Business Sch, N-7491 Trondheim, Norway en_US
dc.description.abstract We utilize machine learning methods to model the credit risk of mortgages in a significant emerging market. For this purpose, we investigate a multitude of variables that explain the characteristics of the loans, the demographics of the borrowers, and macroeconomic factors. We employ SHapley Additive exPlanations (SHAP) values in conjunction with five different tree-based machine learning methods, as well as the least absolute shrinkage and selection operator (LASSO) in conjunction with logistic regressions. Our findings, which are robust across two sampling schemes, reveal that while demographic variables are significant and important, loan-specific and macroeconomic variables are the most crucial in explaining mortgage defaults. As existing literature on mortgage default has primarily focused on advanced markets, we aim to bridge this gap by concentrating on emerging market data. We also share our code, which we hope will encourage others to utilize the methods we have applied. en_US
dc.description.sponsorship NTNU Norwegian University of Science and Technology (St. Olavs Hospital-Trondheim University Hospital); EU COST Action "Fintech and Artificial Intelligence in Finance- Towards a transparent financial industry" (FinAI) [CA19130] en_US
dc.description.sponsorship Open access funding provided by NTNU Norwegian University of Science and Technology (incl St. Olavs Hospital-Trondheim University Hospital). This work acknowledges research support by EU COST Action "Fintech and Artificial Intelligence in Finance- Towards a transparent financial industry" (FinAI) CA19130. en_US
dc.description.woscitationindex Science Citation Index Expanded - Social Science Citation Index
dc.identifier.citationcount 0
dc.identifier.doi 10.1007/s10614-024-10763-6
dc.identifier.issn 0927-7099
dc.identifier.issn 1572-9974
dc.identifier.scopus 2-s2.0-85213048609
dc.identifier.scopusquality Q2
dc.identifier.uri https://doi.org/10.1007/s10614-024-10763-6
dc.identifier.uri https://hdl.handle.net/20.500.12469/7114
dc.identifier.wos WOS:001383449400001
dc.identifier.wosquality Q2
dc.language.iso en en_US
dc.publisher Springer en_US
dc.relation.publicationcategory Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı en_US
dc.rights info:eu-repo/semantics/openAccess en_US
dc.scopus.citedbyCount 0
dc.subject Mortgage Loan en_US
dc.subject Default Risk en_US
dc.subject Tree-Based Methods en_US
dc.subject Lasso en_US
dc.subject Shap en_US
dc.subject Emerging Market en_US
dc.subject C40 en_US
dc.subject C52 en_US
dc.subject C65 en_US
dc.subject G21 en_US
dc.title Explaining Mortgage Defaults Using Shap and Lasso en_US
dc.type Article en_US
dc.wos.citedbyCount 0
dspace.entity.type Publication
relation.isAuthorOfPublication 4305087b-4178-478d-8846-9b1a77e8bfbe
relation.isAuthorOfPublication.latestForDiscovery 4305087b-4178-478d-8846-9b1a77e8bfbe
relation.isOrgUnitOfPublication 16202dfd-a149-4884-98fb-ada5f8c12918
relation.isOrgUnitOfPublication.latestForDiscovery 16202dfd-a149-4884-98fb-ada5f8c12918

Files