[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125888-en":3,"doc-seo-125888-105":31,"detail-sidebar-cat-0-en-105":93},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},125888,1099523885336,"Violet","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Predicting Mortgage Loan Defaults Using Machine Learning Techniques - read online free","Mortgage default prediction supports banks’ credit-risk management and regulators’ monitoring of systemic risk. This study predicts one-year mortgage default outcomes using data from the Ukrainian credit registry and applies machine-learning methods with two balancing strategies. Results show that random forests and extreme gradient-boosted decision trees deliver stronger accuracy and precision than alternatives, offering effective trade-offs between capturing true defaults and limiting false alarms. The analysis highlights real GDP growth and the DSTI ratio as particularly informative predictors.","Contents lists available at Vilnius University Press  \nEkonomika ISSN 1392-1258 eISSN 2424-6166  \n2024, vol. 103(2), pp. 140–160 DOI: [https://doi.org/10.15388/Ekon.2024.103.2.8](https://doi.org/10.15388/Ekon.2024.103.2.8)  \n\n| Predicting Mortgage Loan Defaults Using Machine Learning Techniques\u003Cbr>Danylo Krasovytskyi*\u003Cbr>Taras Shevchenko National University of Kyiv; Lead Economist, National Bank of Ukraine, Kyiv, Ukraine Email: [dkrasovytskyi@kse.org.ua](dkrasovytskyi@kse.org.ua)\u003Cbr>ORCID: [https://orcid.org/0009-0008-7017-0175](https://orcid.org/0009-0008-7017-0175)\u003Cbr>Andriy Stavytskyy\u003Cbr>Taras Shevchenko National University of Kyiv, Ukraine\u003Cbr>Email: [a.stavytskyy@gmail.com](a.stavytskyy@gmail.com)\u003Cbr>ORCID: [https://orcid.org/0000-0002-5645-6758](https://orcid.org/0000-0002-5645-6758) |\n| --- |\n| Abstract. Mortgage default prediction is always on the table for financial institutions. Banks are interested in provision planning, while regulators monitor systemic risk, which this sector may possess. This research is focused on predicting defaults on a one-year horizon using data from the Ukrainian credit registry applying machine-learning methods. This research is useful for not only academia but also policymakers since it helps to assess the need for implementation of macroprudential instruments. We tested two data balancing techniques: weighting the original sample and synthetic minority oversampling technique and compared the results. It was found that random forest and extreme gradient-boosting decision trees are better classifiers regarding both accuracy and precision. These models provided an essential balance between actual default precision and minimizing false defaults. We also tested neural networks, linear discriminant analysis, support vector machines with linear kernels, and decision trees, but they showed similar results to logistic regression. The result suggested that real gross domestic product (GDP) growth and debt-service-to-income ratio (DSTI) were good predictors of default. This means that a realistic GDP forecast as well as a proper assessment of the borrower’s DSTI through the loan history can predict default on a one-year horizon. Adding other variables such as the borrower’s age and loan interest rate can also be beneficial. However, the residual maturity of mortgage loans does not contribute to default probability, which means that banks should treat both new borrowers equally and those who nearly repaid the loan.\u003Cbr>Keywords: machine learning, classification, default prediction, mortgage lending, random forest, extreme gradient-boosting decision tree |\n\n1. Introduction  \nLoan default prediction remains a critical area of research for financial institutions. Accurate prediction of borrower insolvency lowers credit risk and enables correct shortand medium-term provisioning planning. Default rate shocks cannot be prevented, and some borrowers default anyway, but banks should do everything to lower their losses.  \n* Correspondent author.  \nReceived: 08/03/2024 . Revised: 17/04/2024 . Accepted: 07/05/2024  \nCopyright © 2024 Danylo Krasovytskyi, Andriy Stavytskyy. Published by Vilnius University Press  \nThis is an Open Access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.  \nDanylo Krasovytskyi, Andriy Stavytskyy. Predicting Mortgage Loan Defaults Using Machine Learning Techniques  \nOne of the key segments of financial markets, especially in developed countries, is mortgage lending. Mortgages possess special interest because they have two features: significant loan sums and long terms. In case of default, these features correspond to significant financial losses. That is why it is crucial for banks to predict borrowers’ default in this segment.  \nMachine learning (ML) methods open new horizons for default prediction. According to the recent B","cbCaijih4R7t9Cif","https://ap.wps.com/l/cbCaijih4R7t9Cif","pdf",2076410,7,1,21,"English","en",105,"# Abstract\n# Introduction\n## Research goals and questions","[{\"question\":\"How is mortgage default predicted in this research?\",\"answer\":\"The study predicts one-year mortgage default using Ukrainian credit registry data and multiple machine-learning models trained on macroeconomic, borrower, and loan-specific factors.\"},{\"question\":\"Which models perform best for default prediction?\",\"answer\":\"Random forest and extreme gradient-boosting decision trees outperform other tested approaches in both accuracy and precision.\"},{\"question\":\"What factors are found to be strong predictors of mortgage default?\",\"answer\":\"Real GDP growth and the debt-service-to-income (DSTI) ratio are identified as good predictors, while the residual maturity of mortgage loans does not significantly contribute to default probability.\"}]","Predicting Mortgage Loan Defaults Using Machine Learning Techniques - read online free | PDF",1785901850,53,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"predicting-mortgage-loan-defaults-using-machine-learning-techniques-read-online-free","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/predicting-mortgage-loan-defaults-using-machine-learning-techniques-read-online-free/125888/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"How is mortgage default predicted in this research?","Question",{"text":77,"@type":78},"The study predicts one-year mortgage default using Ukrainian credit registry data and multiple machine-learning models trained on macroeconomic, borrower, and loan-specific factors.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"Which models perform best for default prediction?",{"text":82,"@type":78},"Random forest and extreme gradient-boosting decision trees outperform other tested approaches in both accuracy and precision.",{"name":84,"@type":75,"acceptedAnswer":85},"What factors are found to be strong predictors of mortgage default?",{"text":86,"@type":78},"Real GDP growth and the debt-service-to-income (DSTI) ratio are identified as good predictors, while the residual maturity of mortgage loans does not significantly contribute to default probability.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,117,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":113,"doc_module":4,"doc_module_name":47,"category_name":114,"show_sort_weight":115,"slug":116},6,"Technology",50,"technology",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":108,"slug":139},19,"General","general"]