Ozturkkal, BelmaWahlstrom, Ranik Raaen2025-01-152025-01-15202400927-70991572-9974https://doi.org/10.1007/s10614-024-10763-6https://hdl.handle.net/20.500.12469/7114We 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.eninfo:eu-repo/semantics/openAccessMortgage LoanDefault RiskTree-Based MethodsLassoShapEmerging MarketC40C52C65G21ArticleWOS:00138344940000110.1007/s10614-024-10763-62-s2.0-85213048609Q2Q2