Range estimation of construction costs using neural networks with bootstrap prediction intervals


EXPERT SYSTEMS WITH APPLICATIONS, vol.38, no.8, pp.9913-9917, 2011 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 38 Issue: 8
  • Publication Date: 2011
  • Doi Number: 10.1016/j.eswa.2011.02.042
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.9913-9917
  • Keywords: Neural networks, Cost estimation, Bayesian regularization, Bootstrap method, Construction projects, MODEL, BUILDINGS, PROJECTS, REGULARIZATION, SYSTEMS
  • Middle East Technical University Affiliated: Yes


Modeling of construction costs is a challenging task, as it requires representation of complex relations between factors and project costs with sparse and noisy data. In this paper, neural networks with bootstrap prediction intervals are presented for range estimation of construction costs. In the integrated approach, neural networks are used for modeling the mapping function between the factors and costs, and bootstrap method is used to quantify the level of variability included in the estimated costs. The integrated method is applied to range estimation of building projects. Two techniques; elimination of the input variables, and Bayesian regularization were implemented to improve generalization capabilities of the neural network models. The proposed modeling approach enables identification of parsimonious mapping function between the factors and cost and, provides a tool to quantify the prediction variability of the neural network models. Hence, the integrated approach presents a robust and pragmatic alternative for conceptual estimation of costs. (C) 2011 Elsevier Ltd. All rights reserved.