A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Contractor Prequalification Using Support Vector Machines
https://orcid.org/http://orcid.org/0000-0002-4266-1355
Contractors frequently experience financial difficulties, which has a substantial negative impact on the economy and causes large disruptions and losses to project stakeholders. This paper demonstrates a method for predicting financial distress using support vector machines (SVM). The objective of this work is to increase the forecasting accuracy and examine how macroeconomic factors and financial ratios affect the financial status of the contractor. Eight financial ratios and six macroeconomic factors were chosen as the input variables to this model. Macroeconomic variables and financial ratios are both present in the first dataset, but financial ratios alone are present in the second dataset. Both datasets are compared to determine the significance of macroeconomic variables. In this work, three kernel SVM function techniques—linear, polynomial, and radial basis (RBF)—were employed on both datasets. In comparison with the other techniques, the linear kernel function generated the highest accuracy (87.27%). Additionally, the dataset that included macroeconomic factors and financial ratios produced improved performance measures in comparison with the dataset containing financial ratios only. As a result, this framework is a useful tool for forecasting the financial health of building companies.
Contractor Prequalification Using Support Vector Machines
https://orcid.org/http://orcid.org/0000-0002-4266-1355
Contractors frequently experience financial difficulties, which has a substantial negative impact on the economy and causes large disruptions and losses to project stakeholders. This paper demonstrates a method for predicting financial distress using support vector machines (SVM). The objective of this work is to increase the forecasting accuracy and examine how macroeconomic factors and financial ratios affect the financial status of the contractor. Eight financial ratios and six macroeconomic factors were chosen as the input variables to this model. Macroeconomic variables and financial ratios are both present in the first dataset, but financial ratios alone are present in the second dataset. Both datasets are compared to determine the significance of macroeconomic variables. In this work, three kernel SVM function techniques—linear, polynomial, and radial basis (RBF)—were employed on both datasets. In comparison with the other techniques, the linear kernel function generated the highest accuracy (87.27%). Additionally, the dataset that included macroeconomic factors and financial ratios produced improved performance measures in comparison with the dataset containing financial ratios only. As a result, this framework is a useful tool for forecasting the financial health of building companies.
Contractor Prequalification Using Support Vector Machines
https://orcid.org/http://orcid.org/0000-0002-4266-1355
Contractors frequently experience financial difficulties, which has a substantial negative impact on the economy and causes large disruptions and losses to project stakeholders. This paper demonstrates a method for predicting financial distress using support vector machines (SVM). The objective of this work is to increase the forecasting accuracy and examine how macroeconomic factors and financial ratios affect the financial status of the contractor. Eight financial ratios and six macroeconomic factors were chosen as the input variables to this model. Macroeconomic variables and financial ratios are both present in the first dataset, but financial ratios alone are present in the second dataset. Both datasets are compared to determine the significance of macroeconomic variables. In this work, three kernel SVM function techniques—linear, polynomial, and radial basis (RBF)—were employed on both datasets. In comparison with the other techniques, the linear kernel function generated the highest accuracy (87.27%). Additionally, the dataset that included macroeconomic factors and financial ratios produced improved performance measures in comparison with the dataset containing financial ratios only. As a result, this framework is a useful tool for forecasting the financial health of building companies.
Contractor Prequalification Using Support Vector Machines
Lecture Notes in Civil Engineering
Desjardins, Serge (editor) / Poitras, Gérard J. (editor) / Nik-Bakht, Mazdak (editor) / Elgamal, Salah (author) / Hosny, Ossama (author)
Canadian Society of Civil Engineering Annual Conference ; 2023 ; Moncton, NB, Canada
Proceedings of the Canadian Society for Civil Engineering Annual Conference 2023, Volume 4 ; Chapter: 19 ; 251-260
2024-09-18
10 pages
Article/Chapter (Book)
Electronic Resource
English
CPP - contractor prequalification
| British Library Conference Proceedings | 1999
A support vector machine model for contractor prequalification
| Elsevier | 2008
A support vector machine model for contractor prequalification
| Online Contents | 2009
A support vector machine model for contractor prequalification
| Online Contents | 2009