[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-290498-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-290498-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","sustainability-related-risks-in-credit-risk-modeling-evidence-limitations-and-the-role-of-machine-learning","Sustainability-Related Risks in Credit Risk Modeling - Evidence, Limitations, and the Role of Machine Learning","","Climate change and sustainability pressures affect firms’ solvency, asset values, and credit loss distributions, yet their incorporation into credit risk modeling remains fragmented. This paper reviews how sustainability-related factors enter credit risk assessment and whether machine learning can support the integration. Two systematic literature reviews under PRISMA synthesize evidence on ESG, transition, and physical climate risks, and survey machine learning methods, inputs, and limitations. Results link sustainability factors to credit outcomes with heterogeneous effects across channels, sectors, time horizons, and measures, highlighting four structural gaps and assessing mitigation via machine learning.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/sustainability-related-risks-in-credit-risk-modeling-evidence-limitations-and-the-role-of-machine-learning/290498/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/sustainability-related-risks-in-credit-risk-modeling-evidence-limitations-and-the-role-of-machine-learning/290498.png","ImageObject",300,407,{"name":42,"@type":43},"Noah","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-01","2026-09-17",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",15,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"How does the paper evaluate sustainability-related risks in credit risk modeling?","Question",{"text":63,"@type":64},"It conducts two parallel systematic literature reviews following PRISMA guidelines: one synthesizing empirical ESG and climate-risk evidence on credit risk metrics, and another reviewing machine learning applications in credit risk with focus on inputs, modeling approaches, and limitations.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What does the paper find about the relationship between sustainability factors and credit risk outcomes?",{"text":68,"@type":64},"Across sustainability-oriented literature, sustainability factors are empirically associated with credit risk outcomes, but effects are heterogeneous across risk channels, sectors, time horizons, and measurement choices.",{"name":70,"@type":61,"acceptedAnswer":71},"Why are traditional credit models challenged by transition and physical climate risks?",{"text":72,"@type":64},"The paper highlights strong scenario dependence, spatial concentration, and forward-looking dynamics in transition and physical climate risks, which challenge models calibrated mainly on historically stable relationships.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},290498,1789641847,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":80,"read_time":145,"preview_page_count":4},8796095462418,"https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780","Title Manuscript:  \nSustainability-Related Risks in Credit Risk Modeling: Evidence, Limitations, and the Role  \nof Machine Learning  \nAuthors:  \nManuele Masseia, Wouter van Heeswijka, Xiaohong Huanga, Laura Spierdijka  \nAffiliations:  \na University of Twente, Faculty of Behavioral, Management and Social Sciences, The Netherlands  \n1  \nThis preprint research paper has not been peer reviewed. Electronic copy available at: [https://ssrn.com/abstract=6292484](https://ssrn.com/abstract=6292484)  \nSustainability-Related Risks in Credit Risk Modeling: Evidence, Limitations, and the Role of Machine Learning  \nAbstract  \nClimate change and broader sustainability pressures increasingly affect firms’ solvency, asset values, and credit loss distributions, yet their integration into credit risk modeling remains fragmented. This paper examines how sustainability-related factors are incorporated into credit risk assessment and evaluates whether machine learning methods can meaningfully support this integration. We conduct two parallel systematic literature reviews following PRISMA guidelines. The first synthesizes empirical evidence on the effects of environmental, social and governance information, transition risk, and physical climate risk on credit risk metrics. The second reviews machine learning applications in credit risk, focusing on data inputs, modeling approaches and reported limitations. Across the sustainability-oriented literature, sustainability factors are empirically associated with credit risk outcomes, but effects are heterogeneous across risk channels, sectors, time horizons, and measurement choices.  \nSocial and governance indicators show the most consistent relationships with credit risk, while environmental indicators exhibit timing-and sector-dependent effects.  \nTransition and physical climate risks introduce strong scenario dependence, spatial concentration, and forward-looking dynamics that challenge historically calibrated credit models. In parallel, the machine learning literature demonstrates substantial advances in modeling non-linearities, relational dependencies, and unstructured data, but largely abstracts from sustainability and climate-related exposures and remains  \nPreprint submitted to International Review of Financial Analysis December 31, 2025  \nThis preprint research paper has not been peer reviewed. Electronic copy available at: [https://ssrn.com/abstract=6292484](https://ssrn.com/abstract=6292484)  \npredominantly backward-looking. By jointly interpreting both literatures, the paper identifies four structural gaps limiting sustainable credit risk modeling and assesses the extent to which machine learning can mitigate them. The findings suggest that machine learning can enhance data integration and relational modeling, while relying on strong data foundations, explicit scenario design, and robust model governance. Keywords: Credit Risk, Sustainability, Climate Risk, Machine Learning, Systematic Review  \n1. Introduction  \nClimate change and broader sustainability pressures increasingly affect firms’solvency, collateral values, and long term financial resilience. Rising temperatures, more frequent extreme events, and intensified regulatory and social scrutiny modify firms’operating environments and alter the distribution of credit losses across borrowers and portfolios.s. Supervisory authorities now explicitly recognize these links. The Basel Committee on Banking Supervision requires banks to identify and manage climate related drivers within their credit risk frameworks (Basel Committee on Banking Supervision, 2022) . The European Banking Authority calls for the incorporation of environmental, social and governance risks beyond standard planning horizons (European Banking Authority, 2021b), while the European Central Bank documents persistent shortcomings in banks’ability to quantify physical and transition risks due to data and modeling limitations (European Central Bank, 2020) . These developments es","cbCailleDnNkmD18","https://ap.wps.com/l/cbCailleDnNkmD18","pdf",4780606,88,"English","# Abstract\n# Introduction\n## Regulatory recognition of sustainability and climate risks\n## Methodological challenges in integrating sustainability into credit models\n## Availability of data and machine learning opportunities\n# Systematic literature reviews (PRISMA)\n## Evidence on ESG and climate risks in credit risk metrics\n## Machine learning applications and limitations in credit risk","[{\"question\":\"How does the paper evaluate sustainability-related risks in credit risk modeling?\",\"answer\":\"It conducts two parallel systematic literature reviews following PRISMA guidelines: one synthesizing empirical ESG and climate-risk evidence on credit risk metrics, and another reviewing machine learning applications in credit risk with focus on inputs, modeling approaches, and limitations.\"},{\"question\":\"What does the paper find about the relationship between sustainability factors and credit risk outcomes?\",\"answer\":\"Across sustainability-oriented literature, sustainability factors are empirically associated with credit risk outcomes, but effects are heterogeneous across risk channels, sectors, time horizons, and measurement choices.\"},{\"question\":\"Why are traditional credit models challenged by transition and physical climate risks?\",\"answer\":\"The paper highlights strong scenario dependence, spatial concentration, and forward-looking dynamics in transition and physical climate risks, which challenge models calibrated mainly on historically stable relationships.\"}]","Sustainability-Related Risks in Credit Risk Modeling - Evidence, Limitations, and the Role of Machine Learning | PDF",222]