In the highly competitive worldwide construction industry, a slight inaccuracy of estimation can easily cause the loss of a project. Erroneous experience‐based cost estimates or allocations of onsite supervisory manpower often offset the profit gained from the project and may even jeopardize the management processes. To counter these types of problems, we develop a model using mathematical analysis and case‐based reasoning to automate the allocation of onsite supervisory manpower and its costs. The method is founded upon laborious data collection processes and analysis by matching statistical assumptions, and is applicable to construction projects for residential buildings, industrial office buildings, commercial buildings and industrial construction. In the modelling the costs and allocation of onsite supervisory manpower are quantified for both owners and contractors before initiating or bidding on the projects. The findings confirm that the degree of variation of the model predictions has an accuracy rate at 88.47%. Single‐site construction projects with the following characteristics: a non‐crashing schedule, a floor area of less than 35 000 m2, a height of less than 50m, can be accurately predicted and the assignment of supervisory manpower feasibly automated.
Construction Management and Economics 26(8), pp.805-814