Please use this identifier to cite or link to this item: https://doi.org/10.1061/(ASCE)0733-9364(2005)131:4(391)
Title: Modeling a contractor's markup estimation
Authors: Liu, M.
Ling, Y.Y. 
Keywords: Bids
Construction management
Contractors
Fuzzy sets
Neural networks
Issue Date: 2005
Source: Liu, M., Ling, Y.Y. (2005). Modeling a contractor's markup estimation. Journal of Construction Engineering and Management 131 (4) : 391-399. ScholarBank@NUS Repository. https://doi.org/10.1061/(ASCE)0733-9364(2005)131:4(391)
Abstract: The estimation of markup is a difficult process for contractors in a changeable and uncertain construction environment. In this study, a fuzzy logic-based artificial neural network (ANN) model, called the fuzzy neural network (FNN) model, is constructed to assist contractors in making markup decisions. With the fuzzy logic inference system integrated inside, the FNN model provides users with a clear explanation to justify the rationality of the estimated markup output. Meanwhile, with the self-learning ability of ANN, the accuracy of the estimation results is improved. From a survey and interview with local contractors, the factors that affect markup estimation and the rules applied in the markup decision are identified. Based on the finding, both ANN and FNN models were constructed and trained in different project scenarios. The comparison of the two models shows that FNN will assist contractors with markup estimation with more accurate results and convincing user-defined linguistic rules inside. © ASCE,.
Source Title: Journal of Construction Engineering and Management
URI: http://scholarbank.nus.edu.sg/handle/10635/46018
ISSN: 07339364
DOI: 10.1061/(ASCE)0733-9364(2005)131:4(391)
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

45
checked on Dec 6, 2017

WEB OF SCIENCETM
Citations

33
checked on Nov 21, 2017

Page view(s)

86
checked on Dec 10, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.