Abstract
Abstract The construction industry in Yemen is currently facing challenges associated with rapid development of technology; thus, cost estimation is considered a key factor that should align with this technological advancement. The main problem in the area of preliminary estimate in Yemen is how to make estimate accurately. The aim of this study is to analyse a modern method of preliminary cost estimation in Yemen to prove its efficiency over the traditional method. Therefore, a wide range of literature sources regarding the preliminary estimates using Artificial Neural Network (ANN) as a modern technique is considered. Both qualitative and quantitative approaches were adopted in this study depending on the theoretical premises discussed in literature and the ANN technique, respectively. The independent variables were chosen in the course of literature review. The collected data were classified and processed regarding the ANN constraints and encoded for building and analysis of the ANN model. NeuroSolution 6 software was used to build, train, and test the network as well as to perform sensitivity analysis. In addition, the results of training, testing, and sensitivity analysis were obtained and discussed showing high effectiveness of accurate estimates with less than 1 % error. The ANN model is a more powerful technique for estimating costs in the preliminary stage that should be used in the developing countries instead of the traditional methods.
Highlights
Many factors affect the success of a construction project, such as time, quality and cost (Finch, Yu, Shen, Kelly, & Hunter, 2005); cost estimation is the most important activity during various project stages
This study investigates the preliminary estimate made using Artificial Neural Network (ANN)
In the network test process, the data from twenty projects were used to compare the actual costs with the estimated costs, which were obtained by the ANN model (Table 5)
Summary
Many factors affect the success of a construction project, such as time, quality and cost (Finch, Yu, Shen, Kelly, & Hunter, 2005); cost estimation is the most important activity during various project stages. Cost estimation may be a challenging task in conditions of limited availability of information. Lack of time and information, as well as the complexity of the building project considered for cost estimation often lead to poor performance in estimates (Brook, 2011). Samphaongoen (2010) states that the accuracy of the preliminary estimate is often ±10 to 20 %. In Yemen, engineers estimate their projects in the preliminary stage using traditional methods, i.e. unit price of square meter and analogous methods, which often leads to inaccurate estimates. In order to overcome this problem, a modern preliminary estimate (modern technique) to be adopted in Yemen is investigated to prove its efficiency over the traditional methods. This study investigates the preliminary estimate made using Artificial Neural Network (ANN)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Baltic Journal of Real Estate Economics and Construction Management
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
