[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119682-en":3,"doc-seo-119682-105":30,"detail-sidebar-cat-0-en-105":95},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119682,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","Modelling Failure Rates with Machine-Learning Models - Evidence from a Panel of UK Firms","This study investigates whether machine-learning techniques can predict firm failures more effectively than established alternatives. Using panel data on UK firms’ business and financial risks from 1994–2019, it shows that machine-learning models deliver systematically higher accuracy than a discrete hazard benchmark. The random forest model achieves the strongest failure-prediction performance, and its advantage remains under extreme economic events as well as firm and industry heterogeneity. Financial factors further explain failure probabilities.","DOI: 10.1111/eufm.12369  \nORIGINAL ARTICLE  \nEUROPEAN FINANCIAL MANAGEMENT  \nModellingfailurerateswithmachine‐learning models: Evidence from a panel of UK firms  \nGeorgios Sermpinis1 | Serafeim Tsoukas1 | Yiqun Zhang2  \n1Adam Smith Business School, University of Glasgow, Glasgow, UK 2School of Insurance, Central University of Finance and Economics, Beijing, China  \nCorrespondence  \nGeorgios Sermpinis, Adam Smith Business School, University of Glasgow, Glasgow G12 8QQ, UK.  \nEmail: [georgios.sermpinis@glasgow.ac.uk](georgios.sermpinis@glasgow.ac.uk)  \nAbstract  \nIn this study, we investigate the ability of machine‐ learning techniques to predict firm failures and we compare them against alternatives. Using data on business and financial risks of UK firms over 1994–2019, we document that machine‐learning models are systematically more accurate than a discrete hazard benchmark. We conclude that the random forest model outperforms other models in failure prediction. In addition, we show that the improved predictive power of the random forest model relative to its counterparts persists when we consider extreme economic events as well as firm and industry heterogeneity. Finally, we find that financial factors affect failure probabilities.  \nKEYWORD S  \nbusiness closures, finance, financial ratios, machine‐learning models, random forest  \nJ E L C LASS IF ICA T I O N  \nG17, G33, C25, E37  \n\n| We are grateful to the editor (John Doukas) and one anonymous reviewer for insightful comments and suggestions. We acknowledge the participants at the 2021 International Conference of the French Finance Association and the 2022 International Conference on Macroeconomic Analysis and International Finance for their useful comments. Any remaining errors are our own. |\n| --- |\n| This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.\u003Cbr>© 2022 The Authors. European Financial Management published by John Wiley & Sons Ltd. |\n\n[734](734 | wileyonlinelibrary.com/journal/eufm)[ |](734 | wileyonlinelibrary.com/journal/eufm)[ wileyonlinelibrary.com/journal/eufm](734 | wileyonlinelibrary.com/journal/eufm) Eur Financ Manag. 2023;29:734–763.  \nSERMPINIS ET AL. EUROPEAN | 735  \nFINANCIAL MANAGEMENT  \n1 | INTRODUCTION  \nIt is well accepted that timely detection and accurate prediction of firm failures are essential to firm managers, market participants and policymakers. Managers, as insiders, can incorporate reliable and efficient failure predictions into their internal performance evaluations to check management performance and construct early warning mechanisms so they can implement remedial actions (Geng et al., 2015) . Moreover, accurate failure prediction can lower the probability that a firm's outsiders (e.g., investors and creditors) become exposed to default risksand losses. Failure prediction can also encourage policymakers to create regulations or policies that can stabilize the financial markets.  \nImprovement of prediction techniques has become a pressing issue for academics and practitioners in light of extreme economic events such as the most recent global financial crisis (GFC) or the United Kingdom's decision to leave the European Union in the 23 June 2016 referendum (Brexit) . Both events are characterized by heightened economic and policy uncertainty with implications for firms' real activities, as well as for trade, immigration and regulation (Bloom et al., 2019; van Reenen, 2016) . The empirical literature confirms that uncertainty affects firms due to declines in demand and supply or in the extreme, corporate bankruptcy. Surprisingly, however, there is limited empirical evidence regarding the most appropriate modelling strategy and the characteristics that affect firm closures during the recent global financial crisis and Brexit.  \nThe purpose of this paper is to take a deeper look at firms' failur","cbCaimUMgWOYgJ7B","https://ap.wps.com/l/cbCaimUMgWOYgJ7B","pdf",1500921,1,30,"English","en",105,"# Introduction\n## Motivation for firm-failure prediction\n## Limits of conventional modelling approaches\n## Contributions and research purpose","[{\"question\":\"What is the main goal of the study?\",\"answer\":\"The study evaluates machine-learning techniques for predicting firm failures and compares them with alternative modelling approaches in both tranquil and crisis periods.\"},{\"question\":\"What dataset and time span are used?\",\"answer\":\"The analysis uses panel data covering business and financial risks of UK firms from 1994 to 2019.\"},{\"question\":\"Which model performs best in predicting failures?\",\"answer\":\"The random forest model outperforms other tested models in failure prediction.\"},{\"question\":\"Do the results hold during extreme economic events and across different firm types?\",\"answer\":\"Yes. The relative improvement of the random forest model persists when considering extreme economic events and when accounting for firm and industry heterogeneity.\"}]","Modelling Failure Rates with Machine-Learning Models - Evidence from a Panel of UK Firms | PDF",1785725727,76,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":90,"head_meta":92,"extra_data":94,"updated_unix":28},"modelling-failure-rates-with-machine-learning-models-evidence-from-a-panel-of-uk-firms","",{"@graph":36,"@context":89},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/modelling-failure-rates-with-machine-learning-models-evidence-from-a-panel-of-uk-firms/119682/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main goal of the study?","Question",{"text":75,"@type":76},"The study evaluates machine-learning techniques for predicting firm failures and compares them with alternative modelling approaches in both tranquil and crisis periods.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What dataset and time span are used?",{"text":80,"@type":76},"The analysis uses panel data covering business and financial risks of UK firms from 1994 to 2019.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model performs best in predicting failures?",{"text":84,"@type":76},"The random forest model outperforms other tested models in failure prediction.",{"name":86,"@type":73,"acceptedAnswer":87},"Do the results hold during extreme economic events and across different firm types?",{"text":88,"@type":76},"Yes. The relative improvement of the random forest model persists when considering extreme economic events and when accounting for firm and industry heterogeneity.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,126,131,134,138],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":21,"slug":125},"research-report",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":129,"slug":130},9,"Religion & Spirituality",20,"religion-spirituality",{"id":129,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":129,"slug":133},"World Cup","world-cup",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":135,"slug":137},10,"Lifestyle","lifestyle",{"id":139,"doc_module":4,"doc_module_name":46,"category_name":140,"show_sort_weight":110,"slug":141},19,"General","general"]