Labour productivity plays an important role in the successful delivery of engineering, procurement and construction projects. This paper aims to present a field study that determines the effects of a set of variables on daily and/or short‐term jobsite labour productivity, using artificial neural network model.
The data used in this paper were collected over a period of ten months, directly from the job sites of two building construction projects in Montreal. A neural network model was used to study a number of factors considered to impact labour productivity on daily basis. These included temperature, relative‐humidity, wind speed, precipitation, gang size, crew composition, height of work, type of work and construction method employed. The data were then analyzed to determine the influence of these parameters on site labour productivity.
Among the nine parameters studied, temperature was found to have the most significant impact on productivity, closely followed by the height then by the type of work. Given the range of the collected data available on the variables considered, temperature, humidity and crew composition were found each to have a similar trend, with an optimum value that corresponds to the normalized maximum productivity.
The findings of this paper will provide awareness and better understanding of parameters that impact labour productivity in building construction.
