Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Assessing collusion risks in managing construction projects using artificial neural network
Being an insidious risk to construction projects, collusion has attracted extensive attention from numerous researchers around the world. However, little effort has ever been made to assess collusion, which is important and necessary for curbing collusion in construction projects. Specific to the context of China, this paper developed an artificial neural network model to assess collusion risk in construction projects. Based on a comprehensive literature review, a total of 22 specific collusive practices were identified first, and then refined by a two-round Delphi interview with 15 experienced experts. Subsequently, using the consolidated framework of collusive practices, a questionnaire was further developed and disseminated, which received 97 valid replies. The questionnaire data were then utilized to develop and validate the collusion risk assessment model with the facilitation of artificial neural network approach. The developed model was finally applied in a real-life metro project in which its reliability and applicability were both verified. Although the model was developed under the context of Chinese construction projects, its developing strategy can be applied in other countries, especially for those emerging economies that have a significant concern of collusion in their construction sectors, and thus contributing to the global body of knowledge of collusion.
Assessing collusion risks in managing construction projects using artificial neural network
Being an insidious risk to construction projects, collusion has attracted extensive attention from numerous researchers around the world. However, little effort has ever been made to assess collusion, which is important and necessary for curbing collusion in construction projects. Specific to the context of China, this paper developed an artificial neural network model to assess collusion risk in construction projects. Based on a comprehensive literature review, a total of 22 specific collusive practices were identified first, and then refined by a two-round Delphi interview with 15 experienced experts. Subsequently, using the consolidated framework of collusive practices, a questionnaire was further developed and disseminated, which received 97 valid replies. The questionnaire data were then utilized to develop and validate the collusion risk assessment model with the facilitation of artificial neural network approach. The developed model was finally applied in a real-life metro project in which its reliability and applicability were both verified. Although the model was developed under the context of Chinese construction projects, its developing strategy can be applied in other countries, especially for those emerging economies that have a significant concern of collusion in their construction sectors, and thus contributing to the global body of knowledge of collusion.
Assessing collusion risks in managing construction projects using artificial neural network
Shan, Ming (Autor:in) / Le, Yun (Autor:in) / Yiu, Kenneth T. W. (Autor:in) / Chan, Albert P. C. (Autor:in) / Hu, Yi (Autor:in) / Zhou, You (Autor:in)
12.10.2018
doi:10.3846/20294913.2017.1303648
Technological and Economic Development of Economy; Vol 24 No 5 (2018); 2003-2025 ; 2029-4921 ; 2029-4913
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
DDC:
690
Assessing collusion risks in managing construction projects using artificial neural network
| BASE | 2018
Assessing and Managing the Potential Environmental Risks of Construction Projects
| British Library Online Contents | 2005
Assessing and Managing the Potential Environmental Risks of Construction Projects
| Online Contents | 2005
Managing risks in design & construction projects
| TIBKAT | 2006
Risks assessment in the construction of infrastructure projects using artificial neural networks
| Taylor & Francis Verlag | 2024