Construction projects with long time spans often suffer from cost overruns. Adequate cost estimation at the planning phase is an integral part of a projectâ€™s success. Many uncertainties disturb the plannersâ€™ initial estimations and lead to cost overruns. Changes in the economic conditions are often considered as risks that parties have little control over their impacts. Many research efforts have targeted quantifying the impact of the economic conditions changes on the construction costs. Although many researchers highlighted the correlation between economic indicators and construction costs, a reliable tool for accurate quantification of the impact of this correlation has not yet been reached. An essential part of construction costs is the materials costs. Each country has its unique economic conditions and the relevant leading economic indicators for each countryâ€™s construction market may be different. In Egypt, material costs are the predominant components of construction costs. This research proposes three models that utilize Artificial Neural Networks (ANN) to predict the prices of major construction materials, namely steel reinforcement bars, and Portland cement in the context of the Egyptian construction industry 6 months ahead. The three models are developed using Microsoft Excel spreadsheet that also utilizes Genetic Algorithm (GA) to minimize the error between the actual and predicted prices, Excel Add-in called Neural Tools, and Python programing language in Spyder software. Historical data of Steel and Cement prices as well as macroeconomic indicators in Egypt from May 2008 to June 2018 are used for training, testing, and validation of the proposed models. The inputs to the proposed ANN models are the identified leading economic indicators such as Gross Domestic Product, Unemployment rate, US. Dollar to Egyptian pound exchange rate, and Consumer Price Index (C.P.I). For prediction of Steel prices, the ANN model developed using Python programing language had the superior performance over other models with its ability to predict the month-to-month variations in Steel prices while having mean-absolute-percentage error of 9.0% and 10.1% for training and testing sets respectively. For prediction of Cement prices, the ANN-Excel model is more favorable with its mean-absolute-percentage error of 6.0% and 8.74% respectively. The proposed model can potentially be a useful tool for construction contractors as well as developers for predicting and quantifying the fluctuations of major construction materials prices, specifically in projects containing reinforced concrete structures, enough time ahead to prepare mitigation measures that will reduce the extra costs incurred.
Construction Engineering Department
MS in Construction Engineering
Nassar, Khaled; Dorra, El Khayam
Committee Member 1
Dorra, El Khayam
Committee Member 2
[committee member name not provided]
The author retains all rights with regard to copyright. The author certifies that written permission from the owner(s) of third-party copyrighted matter included in the thesis, dissertation, paper, or record of study has been obtained. The author further certifies that IRB approval has been obtained for this thesis, or that IRB approval is not necessary for this thesis. Insofar as this thesis, dissertation, paper, or record of study is an educational record as defined in the Family Educational Rights and Privacy Act (FERPA) (20 USC 1232g), the author has granted consent to disclosure of it to anyone who requests a copy. The author has granted the American University in Cairo or its agents a non-exclusive license to archive this thesis, dissertation, paper, or record of study, and to make it accessible, in whole or in part, in all forms of media, now or hereafter known.
Institutional Review Board (IRB) Approval
Approval has been obtained for this item
(2019).Prediction of construction material prices using macroeconomic indicators: A neural networks model [Master's Thesis, the American University in Cairo]. AUC Knowledge Fountain.
Shiha, Ahmed. Prediction of construction material prices using macroeconomic indicators: A neural networks model. 2019. American University in Cairo, Master's Thesis. AUC Knowledge Fountain.