Publicação

New Early Warning Tools for Insolvency Prevention in the European Context

Ver documento

Detalhes bibliográficos
Resumo:Abstract Directive 2019/1023 of the European Union represents an important step in ensuring that companies in financial distress can achieve continuity. To this end, Member States are adopting various restructuring mechanisms for debtors, with early warning tools being particularly significant. These tools help companies detect risk situations and correct them before insolvency becomes imminent. There is a growing demand for new models that allow for a more robust verification of companies' exposure to financial risk and potential insolvency within the European context. This study addresses this gap by developing models with high predictive accuracy for European countries. Using a sample of 8,400 European companies from 2017-2022 and advanced computational techniques, the study achieves a prediction accuracy exceeding 98%, providing alerts up to three years in advance. These results surpass those obtained by current early warning systems and present important implications for regulators, professionals and academics, who can promote the efficiency of early warning systems through more robust and reliable models.
Autores principais:Hidalgo-Díaz,Ana Elena
Outros Autores:Alaminos-Aguilera,David; Delgado-Gómez,Enrique
Assunto:Insolvency Early Warning Insolvency Prediction Machine Learning Europe
Ano:2025
País:Portugal
Tipo de documento:artigo
Tipo de acesso:acesso aberto
Instituição associada:Fundação para a Ciência e Tecnologia
Idioma:inglês
Origem:SciELO Portugal
Descrição
Resumo:Abstract Directive 2019/1023 of the European Union represents an important step in ensuring that companies in financial distress can achieve continuity. To this end, Member States are adopting various restructuring mechanisms for debtors, with early warning tools being particularly significant. These tools help companies detect risk situations and correct them before insolvency becomes imminent. There is a growing demand for new models that allow for a more robust verification of companies' exposure to financial risk and potential insolvency within the European context. This study addresses this gap by developing models with high predictive accuracy for European countries. Using a sample of 8,400 European companies from 2017-2022 and advanced computational techniques, the study achieves a prediction accuracy exceeding 98%, providing alerts up to three years in advance. These results surpass those obtained by current early warning systems and present important implications for regulators, professionals and academics, who can promote the efficiency of early warning systems through more robust and reliable models.