Articles producció científica> Gestió d'Empreses

Can the SOM analysis predict business failure using capital structure theory? Evidence from the subprime crisis in Spain

  • Identification data

    Identifier: imarina:6406067
    Authors:
    Pedro Lucanera, JuanFabregat-Aibar, LauraScherger, ValeriaVigier, Hernan
    Abstract:
    © 2020 by the authors. The paper aims to identify which variables related to capital structure theory predict business failure in the Spanish construction sector during the subprime crisis. An artificial neural network (ANN) approach based on Self-Organizing Maps (SOM) is proposed, which allows one to cluster between default and active firms' groups. The similarities and differences between the main features in each group determine the variables that explain the capacities of failure of the analyzed firms. The network tests whether the factors that explain leverage, such as profitability, growth opportunities, size of the company, risk, asset structure, and age of the firm, can be suitable to predict business failure. The sample is formed by 152 construction firms (76 default and 76 active) in the Spanish market. The results show that the SOM correctly predicts 97.4% of firms in the construction sector and classifies the firms in five groups with clear similarities inside the clusters. The study proves the suitability of the SOM for predicting business bankruptcy situations using variables related to capital structure theory and financial crises.
  • Others:

    Author, as appears in the article.: Pedro Lucanera, Juan; Fabregat-Aibar, Laura; Scherger, Valeria; Vigier, Hernan
    Department: Gestió d'Empreses
    URV's Author/s: Fabregat Aibar, Laura
    Keywords: Som Neural network Investment Insolvency Impact Firms Financial ratios Decisions Corporate failure Capital structure Business failure Behavior Bankruptcy prediction Bankruptcy
    Abstract: © 2020 by the authors. The paper aims to identify which variables related to capital structure theory predict business failure in the Spanish construction sector during the subprime crisis. An artificial neural network (ANN) approach based on Self-Organizing Maps (SOM) is proposed, which allows one to cluster between default and active firms' groups. The similarities and differences between the main features in each group determine the variables that explain the capacities of failure of the analyzed firms. The network tests whether the factors that explain leverage, such as profitability, growth opportunities, size of the company, risk, asset structure, and age of the firm, can be suitable to predict business failure. The sample is formed by 152 construction firms (76 default and 76 active) in the Spanish market. The results show that the SOM correctly predicts 97.4% of firms in the construction sector and classifies the firms in five groups with clear similarities inside the clusters. The study proves the suitability of the SOM for predicting business bankruptcy situations using variables related to capital structure theory and financial crises.
    Thematic Areas: Mathematics, applied Mathematical physics Matemática / probabilidade e estatística Logic Interdisciplinar Geometry and topology Ciencias sociales Astronomia / física Analysis Algebra and number theory
    licence for use: https://creativecommons.org/licenses/by/3.0/es/
    ISSN: 20751680
    Author's mail: laura.fabregat@urv.cat
    Author identifier: 0000-0002-0077-161X
    Record's date: 2024-09-28
    Papper version: info:eu-repo/semantics/publishedVersion
    Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
    Papper original source: Axioms: Mathematical Logic And Mathematical Physics. 9 (2): 46-
    APA: Pedro Lucanera, Juan; Fabregat-Aibar, Laura; Scherger, Valeria; Vigier, Hernan (2020). Can the SOM analysis predict business failure using capital structure theory? Evidence from the subprime crisis in Spain. Axioms: Mathematical Logic And Mathematical Physics, 9(2), 46-. DOI: 10.3390/AXIOMS9020046
    Entity: Universitat Rovira i Virgili
    Journal publication year: 2020
    Publication Type: Journal Publications
  • Keywords:

    Algebra and Number Theory,Analysis,Geometry and Topology,Logic,Mathematical Physics,Mathematics, Applied
    Som
    Neural network
    Investment
    Insolvency
    Impact
    Firms
    Financial ratios
    Decisions
    Corporate failure
    Capital structure
    Business failure
    Behavior
    Bankruptcy prediction
    Bankruptcy
    Mathematics, applied
    Mathematical physics
    Matemática / probabilidade e estatística
    Logic
    Interdisciplinar
    Geometry and topology
    Ciencias sociales
    Astronomia / física
    Analysis
    Algebra and number theory
  • Documents:

  • Cerca a google

    Search to google scholar