Title: Modelling construction labour productivity using evolutionary polynomial regression

Authors: Sasan Golnaraghi; Osama Moselhi; Sabah Alkass; Zahra Zangenehmadar

Addresses: Department of Building, Civil and Environmental Engineering, Concordia University, Sir George Williams Campus, 1455 De Maisonneuve Blvd. W., Montreal, Quebec H3G 1M8, Canada ' Department of Building, Civil and Environmental Engineering, Concordia University, Sir George Williams Campus, 1455 De Maisonneuve Blvd. W., Montreal, Quebec H3G 1M8, Canada ' Department of Building, Civil and Environmental Engineering, Concordia University, Sir George Williams Campus, 1455 De Maisonneuve Blvd. W., Montreal, Quebec H3G 1M8, Canada ' Department of Building, Civil and Environmental Engineering, Concordia University, Sir George Williams Campus, 1455 De Maisonneuve Blvd. W., Montreal, Quebec H3G 1M8, Canada

Abstract: Construction projects are labour-intensive and labour costs are a substantial percentage of total budget. Impaired labour productivity causes an increase in construction project schedule. Labour productivity is one of the most frequently discussed topics in the construction industry, and modelling labour productivity by utilising different techniques has been getting more attention. It is a challenging task as it requires identifying the influencing factors as well as considering the associated interdependencies. This paper investigates the application of evolutionary polynomial regression (EPR) for modelling labour productivity in formwork installation. EPR is a data-driven hybrid modelling technique based on evolutionary computing and has been successfully applied to solving civil engineering problems. Results obtained from the EPR model were compared with the outcomes of three other methods: best subset, stepwise, and general regression neural network (GRNN). Results demonstrate the predictive superiority of the developed EPR model for nonlinear problems based on statistical performance indicators.

Keywords: construction industry; labour productivity; loss of productivity; evolutionary polynomial regression; EPR; modelling; regression.

DOI: 10.1504/IJPQM.2020.110024

International Journal of Productivity and Quality Management, 2020 Vol.31 No.2, pp.207 - 226

Received: 12 Dec 2018
Accepted: 09 Jun 2019

Published online: 22 Sep 2020 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article