0
  • DE
  • EN
  • FR
  • Internationale Datenbank und Galerie für Ingenieurbauwerke

Anzeige

Comparison of Machine Learning Approaches for Medium-to-Long-Term Financial Distress Predictions in the Construction Industry

Autor(en):

Medium: Fachartikel
Sprache(n): Englisch
Veröffentlicht in: Buildings, , n. 10, v. 12
Seite(n): 1759
DOI: 10.3390/buildings12101759
Abstrakt:

A method for predicting the financial status of construction companies after a medium-to-long-term period can help stakeholders in large construction projects make decisions to select an appropriate company for the project. This study compares the performances of various prediction models. It proposes an appropriate model for predicting the financial distress of construction companies considering three, five, and seven years ahead of the prediction point. To establish the prediction model, a financial ratio was selected, which was adopted in existing studies on medium-to-long-term predictions in other industries, as an additional input variable. To compare the performances of the prediction models, single-machine learning and ensemble models’ performances were compared. The comprehensive performance comparison of these models was based on the average value of the prediction performance and the results of the Friedman test. The comparison result determined that the random subspace (RS) model exhibited the best performance in predicting the financial status of construction companies after a medium-to-long-term period. The proposed model can be effectively employed to help large-scale project stakeholders avoid damage caused by the financial distress of construction companies during the project implementation process.

Copyright: © 2022 by the authors; licensee MDPI, Basel, Switzerland.
Lizenz:

Dieses Werk wurde unter der Creative-Commons-Lizenz Namensnennung 4.0 International (CC-BY 4.0) veröffentlicht und darf unter den Lizenzbedinungen vervielfältigt, verbreitet, öffentlich zugänglich gemacht, sowie abgewandelt und bearbeitet werden. Dabei muss der Urheber bzw. Rechteinhaber genannt und die Lizenzbedingungen eingehalten werden.

  • Über diese
    Datenseite
  • Reference-ID
    10700027
  • Veröffentlicht am:
    11.12.2022
  • Geändert am:
    10.05.2023
 
Structurae kooperiert mit
International Association for Bridge and Structural Engineering (IABSE)
e-mosty Magazine
e-BrIM Magazine