TY - JOUR
T1 - A machine learning approach for predicting critical factors determining adoption of off-site construction in Nigeria
AU - Wusu, Godoyon
AU - Alaka, Hafiz
AU - Yusuf, Wasiu
AU - Mporas, Iofis
AU - Toriola-Coker, Luqman
AU - Oseghale, Raphael
N1 - © 2022, Emerald Publishing Limited. This is the accepted manuscript version of an article which has been published in final form at https://doi.org/10.1108/SASBE-06-2022-0113
PY - 2022/12/12
Y1 - 2022/12/12
N2 - Purpose: Several factors influence OSC adoption, but extant literature did not articulate the dominant barriers or drivers influencing adoption. Therefore, this research has not only ventured into analyzing the core influencing factors but has also employed one of the best-known predictive means, Machine Learning, to identify the most influencing OSC adoption factors. Design/methodology/approach: The research approach is deductive in nature, focusing on finding out the most critical factors through literature review and reinforcing — the factors through a 5- point Likert scale survey questionnaire. The responses received were tested for reliability before being run through Machine Learning algorithms to determine the most influencing OSC factors within the Nigerian Construction Industry (NCI). Findings: The research outcome identifies seven (7) best-performing algorithms for predicting OSC adoption: Decision Tree, Random Forest, K-Nearest Neighbour, Extra-Trees, AdaBoost, Support Vector Machine and Artificial Neural Network. It also reported finance, awareness, use of Building Information Modeling (BIM) and belief in OSC as the main influencing factors. Research limitations/implications: Data were primarily collected among the NCI professionals/workers and the whole exercise was Nigeria region-based. The research outcome, however, provides a foundation for OSC adoption potential within Nigeria, Africa and beyond. Practical implications: The research concluded that with detailed attention paid to the identified factors, OSC usage could find its footing in Nigeria and, consequently, Africa. The models can also serve as a template for other regions where OSC adoption is being considered. Originality/value: The research establishes the most effective algorithms for the prediction of OSC adoption possibilities as well as critical influencing factors to successfully adopting OSC within the NCI as a means to surmount its housing shortage.
AB - Purpose: Several factors influence OSC adoption, but extant literature did not articulate the dominant barriers or drivers influencing adoption. Therefore, this research has not only ventured into analyzing the core influencing factors but has also employed one of the best-known predictive means, Machine Learning, to identify the most influencing OSC adoption factors. Design/methodology/approach: The research approach is deductive in nature, focusing on finding out the most critical factors through literature review and reinforcing — the factors through a 5- point Likert scale survey questionnaire. The responses received were tested for reliability before being run through Machine Learning algorithms to determine the most influencing OSC factors within the Nigerian Construction Industry (NCI). Findings: The research outcome identifies seven (7) best-performing algorithms for predicting OSC adoption: Decision Tree, Random Forest, K-Nearest Neighbour, Extra-Trees, AdaBoost, Support Vector Machine and Artificial Neural Network. It also reported finance, awareness, use of Building Information Modeling (BIM) and belief in OSC as the main influencing factors. Research limitations/implications: Data were primarily collected among the NCI professionals/workers and the whole exercise was Nigeria region-based. The research outcome, however, provides a foundation for OSC adoption potential within Nigeria, Africa and beyond. Practical implications: The research concluded that with detailed attention paid to the identified factors, OSC usage could find its footing in Nigeria and, consequently, Africa. The models can also serve as a template for other regions where OSC adoption is being considered. Originality/value: The research establishes the most effective algorithms for the prediction of OSC adoption possibilities as well as critical influencing factors to successfully adopting OSC within the NCI as a means to surmount its housing shortage.
KW - Original Research Paper
KW - Construction
KW - Construction Industry
KW - Nigeria
KW - Off-site Construction
KW - Machine Learning
KW - Housing
KW - Machine learning
KW - Offsite construction
KW - Construction industry
UR - http://www.scopus.com/inward/record.url?scp=85144006535&partnerID=8YFLogxK
U2 - 10.1108/sasbe-06-2022-0113
DO - 10.1108/sasbe-06-2022-0113
M3 - Article
SN - 2046-6099
JO - Smart and Sustainable Built Environment
JF - Smart and Sustainable Built Environment
ER -