A Predictive Model for Scaffolding Man-hours in Heavy Industrial Construction Projects

In typical heavy industrial construction projects, scaffolding can account for 30% to 40% of the total direct manhours. However, most industrial contractors estimate scaffolding manpower based on a certain percentage of the direct work, which leads to cost increase and schedule delay due to inaccurate estimation. In order to aid industrial companies to plan and allocate the resources for scaffolding activities before construction, this paper proposes a methodology which combines the classification tree and multiple linear regression to estimate scaffolding manhours based on available project features. The evaluation matrix involves R Squared value (R2), Adjusted R Squared value (Adj. R2), mean absolute error (MAE), root mean squared error (RMSE), and relative absolute error (RAE). The proposed methodology has been tested on the historical scaffolding data in a heavy industrial project and the results showed its effectiveness.