Construction Unit Rate Factor Modelling Using Neural Networks

Authors: Balimu Mwiya, Mundia Muya, Chabota Kaliba, Peter Mukalula

Abstract:

Factors affecting construction unit cost vary depending on a country’s political, economic, social and technological inclinations. Factors affecting construction costs have been studied from various perspectives. Analysis of cost factors requires an appreciation of a country’s practices. Identified cost factors provide an indication of a country’s construction economic strata. The purpose of this paper is to identify the essential factors that affect unit cost estimation and their breakdown using artificial neural networks. Twenty five (25) identified cost factors in road construction were subjected to a questionnaire survey and employing SPSS factor analysis the factors were reduced to eight. The 8 factors were analysed using neural network (NN) to determine the proportionate breakdown of the cost factors in a given construction unit rate. NN predicted that political environment accounted 44% of the unit rate followed by contractor capacity at 22% and financial delays, project feasibility and overhead & profit each at 11%. Project location, material availability and corruption perception index had minimal impact on the unit cost from the training data provided. Quantified cost factors can be incorporated in unit cost estimation models (UCEM) to produce more accurate estimates. This can create improvements in the cost estimation of infrastructure projects and establish a benchmark standard to assist the process of alignment of work practises and training of new staff, permitting the on-going development of best practises in cost estimation to become more effective.

Keywords: Construction cost factors, neural networks, roadworks, Zambian Construction Industry.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1097999

References:

[1] G. Raballand and A. Whitworth “The Crisis in the Zambian Road Sector”, Working Paper No. 5, Zambia Institute for Policy Analysis and Research (ZIPAR), 2012, Lusaka.
[2] C. Hendrickson, Project Management for Construction, Fundamental Concepts for Owners, Engineers, Architects and Builders, 2008, (available online: http://pmbook.ce.cmu.edu/ (accessed 05/11/20139))
[3] Zambia Public Procurement Authority, Consulting services to undertake an assessment of the prevailing market rates in the construction industry, Request for proposals, ZPPA, Zambia, 2014.
[4] J. De la Garza and K. Rouhana, Neural Network versus parameter-based application. Cost Engineering, 37(2) 1995, pp.14-18.
[5] A. K. Mason and A. E. Smith, Cost Estimation Predictive Modeling: Regression versus Neural Network. Engineering Economist 42, (2) 1997, pp. 137-161.
[6] AACE International, Cost Engineering Terminology, Recommended Practice No. 10S-90, TCM Framework: General Reference, Association for the Advancement of Cost Engineering (AACE),2013
[7] Langdon, D., Spon's Civil Engineering and Highway Works Price Book 2009, Spon Press, 2009
[8] J. Mashilipa, An investigation on the effects and their implications of using British outputs in Estimating in the Zambian Construction Industry, BSc (Building) Unpublished thesis, Copperbelt University, Zambia, 2004.
[9] Ibid
[10] E. J Blocher, E. David, G. C. Stout and K. H. Chen, Cost management; A strategic emphasis 4th ed., McGraw Hill, 2008.
[11] A. Enshassi, S. Mohamed, and I. Madi, Contractors’ Perspectives towards Factors Affecting Cost Estimation in Palestine. Jordan Journal of Civil Engineering, 1 (2) 2007, pp. 186-193.
[12] A. Trombka and S. Downey, A Study of County Road Project Cost and Schedule Estimates, Office of Legislative Oversight, Montgomery County, Maryland Report Number 2008-04, 2008, (available online https://www.montgomerycountymd.gov/olo/resources/files/2008-4.pdf (accessed 05/07/2014))
[13] A.H. Memon, I.A. Rahman, M.R. Abdullah, and A.A.A. Azis, Factors Affecting Construction Cost Performance in Project Management Projects: Case of Mara Large Projects. Proceedings of Post Graduate seminar on Engineering, Technology and Social Science. 29-30 November 2010, Universiti Tun Hussein Onn Malaysia, 2010
[14] A.U. Elinwa and S.A. Buba, Construction cost factors in Nigeria, Journal of Construction Engineering and Management. 119 (4), 1993, pp. 698-713.
[15] J. Bode, Neural Networks for Cost Estimation, Cost Engineering Journal 40 (1) 1998, pp.25-30
[16] I. Peško, M. Trivunić, G. Cirović and V. Mučenski, A preliminary estimate of time and cost in urban road construction using neural networks Technical Gazette 20 (3), 2013, pp. 563-570 (accessed 16/01/2014)
[17] A. J. Hasan, Parametric Cost Estimation of Road Projects Using Artificial Neural Networks, M.Sc. Unpublished thesis, The Islamic University, Gaza, 2013
[18] S. Muqeem, A. Idrus, F. M. Khamidi, J.B. Ahmad, and S.B. Zakaria, Construction labor production rates modeling using artificial neural network, Journal of Information Technology in Construction (ITcon), Vol. 16, 2011, pp. 713-726, (available online http://www.itcon.org/2011/42 (accessed on 09/04/2014))
[19] A. Hashem, P.A. Alex, and M. Tantash, Preliminary Cost Estimation of Highway Construction Using Neural Networks, Cost Engineering 41, (3) 1999, pp. 19-24
[20] D. R. Cooper and P.S. Schindler, Business research methods 11th ed., McGraw Hill, 2011, pp.390-397
[21] Creative Research Systems, Sample Size Formula, (available online: http://www.surveysystem.com/sample-size-formula.htm (accessed on 09/04/2014))
[22] J. C. F. de Winter, D. Dodou, and P. A. Wieringa, Exploratory Factor Analysis with Small Sample Sizes, Multivariate Behavioral Research, 44, 2009, pp147–181