.png){kind=icon}
返回
Calculating cost contingency for residential construction projects in Egypt using a machine learning algorithm
.png){kind=icon}
PRE
AI
DOI：10.1080/15623599.2025.2567747.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Cost contingency (CC) is a critical factor in residential construction projects, as it has several negative consequences for project owners if underestimated. If the cost contingency (CC) is too high, it might cause the construction project to be uneconomical; if it is too low, it may result in unacceptable performance consequences. This research presents an Artificial Neural Network (ANN) machine learning model that allows owners to accurately predict the project’s cost contingency (CC) for residential construction projects in Egypt. The main factors have been identified and defined as data input variables for the model. Furthermore, the model layers are identified, with the output being the cost contingency as a percentage of the project. Two scenarios are mentioned to develop the most accurate prediction for the contingency using 20 sets of actual residential project data. Based on the best model prediction, testing and validation were completed. The model was tested and validated with an acceptable Symmetric Mean Absolute Percentage Error (sMAPE) of 19.5% for residential projects’ cost contingency (CC).
Keyword:
Cost contingency
artificial neural networks
symmetric mean absolute percentage error
期刊
I
IF:
3.4
论文数:
329
被引数:
0
机构
引用论文
.png){kind=icon}
分享收藏Invariant Signatures of Architecture, Engineering, and Construction Objects to Support BIM Interoperability between Architectural Design and Structural Analysis建筑、工程和施工对象的不变签名，以支持建筑设计和结构分析之间的BIM互操作性
PREAI
分享收藏Application of ANN technique to predict the thermal conductivity of nanofluids: a review应用人工神经网络技术预测纳米流体热导率的研究进展
PREAI
分享收藏
查看更多内容