Predicting Cost Deviation in Reconstruction Projects: Artificial Neural Networks versus Regression
Publication: Journal of Construction Engineering and Management
Volume 129, Issue 4
Abstract
This paper investigates the challenging environment of reconstruction projects and describes the development of a predictive model of cost deviation in such high-risk projects. Based on a survey of construction professionals, information was obtained on the reasons behind cost overruns and poor quality from 50 reconstruction projects. For each project, the specific techniques used for project control were reported along with the actual cost deviation from planned values. Two indicators of cost deviation are used in this study: cost overrun to the owner, and the cost of rework to the contractor. Based on the information obtained, 36 factors were identified as having direct impact on the cost performance of reconstruction projects. Two techniques were then used to develop models for predicting cost deviation: statistical analysis, and artificial neural networks (ANNs). While both models had similar accuracy, the ANN model is more sensitive to a larger number of variables. Overall, this study contributes to a better understanding of the reasons for cost deviation in reconstruction projects and provides a decision support tool to quantify that deviation.
Get full access to this article
View all available purchase options and get full access to this article.
References
Ashley, D. B., Lurie, C. S., and Jaselskis, E. J.(1987). “Determinants of construction project success.” Proj. Manage. J., XVIII(2), 69–77.
Attalla, M. (1996). “Reconstruction of occupied buildings, project control techniques.” Master of Applied Science thesis, Univ. of Waterloo, Waterloo, Canada.
Attalla, M., Hegazy, T., McKim, R., and Coppinger, F. (1999). “Success factors in reconstruction projects: A case study.” Proc., 27th Annual Conf. of the Canadian Society of Civil Engineering, Ottawa, 319–328.
Hegazy, T., Moselhi, O., and Fazio, P.(1994). “A neural network approach for representing implicit knowledge in construction.” Int. J. Constr. Inf. Technol., 1(3), 73–86.
Kaminetzky, D., and Lavon, B.(1996). “Success or failure: A tale of two projects.” Civ. Eng. (N.Y.), 66(46), 62–63.
Kerr, W. C., Tamaro, G. J., and Hahn, D. M.(1992). “Exchange Place Station subsurface reconstruction and improvements.” J. Constr. Eng. Manage., 118(1), 166–178.
Kritzek, R., Lo, W., and Hadavi, A.(1996). “Lessons learned from multiphase reconstruction project.” J. Constr. Eng. Manage., 122(1), 44–54.
Krug, T.(1997). “Everything old is new again.” Civ. Eng. (N.Y.), 67(4), 58–60.
Lee, J. (1996). “Statistical deterioration models for condition assessment of older buildings.” PhD thesis, Wayne State Univ., Detroit, Mich.
McKim, R., and Attalla, M. (1998). “Reconstruction of occupied buildings, project control techniques—A Canadian study.” Proc., 1st Int. Conf. on Civil Engineering, Helwan Univ., Cairo, Egypt, 439–453.
McKim, R., Hegazy, T., and Attalla, M.(2000). “Project performance control in reconstruction projects.” J. Constr. Eng. Manage., 126(2), 137–141.
Montgomery, D. C. (1990). Design and analysis of experiments, Wiley, New York.
Rasmussen, E.(1997). “The Rebirth of a station.” Civ. Eng. (N.Y.), 67(10), 54–57.
Rumelhort, D., Hinton, G., and Williams, R. (1986). Parallel distributed processing, Vol. 1, Foundations, MIT Press, Cambridge, Mass.
Sanvido, V., Grobler, F., Parfitt, K., Guvenis, M., and Coyle, M.(1992). “Critical success factors for construction projects.” J. Constr. Eng. Manage., 118(1), 94–111.
Sanvido, V., and Riggs, L. (1991). “Managing retrofit projects.” Technical Rep. 25, Computer Integrated Construction Research Program, Pennsylvania State Univ., University Park, Pa.
Sanvido, V., and Riggs, L. S.(1993). “Managing successful retrofit projects.” Cost Eng., 35(12), 25–31.
Statistics Canada. (1998). “Gross domestic product.” 〈http://www.statcan.ca〉.
U.S. Census Bureau. (1998). “Construction business.” 〈http://www.census.gov〉.
Information & Authors
Information
Published In
Copyright
Copyright © 2003 American Society of Civil Engineers.
History
Received: Sep 7, 2001
Accepted: May 21, 2002
Published online: Jul 15, 2003
Published in print: Aug 2003
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.