A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Hybrid machine learning approach for construction cost estimation: an evaluation of extreme gradient boosting model
Estimating the project cost is an important process in the early stage of the construction project. Accurate cost estimation prevents major issues like cost deficiency and disputes in the project. Identifying the affected parameters to project cost leads to accurate results and enhances cost estimation accuracy. In this paper, extreme gradient boosting (XGBoost) was applied to select the most correlated variables to the project cost. XGBoost model was used to estimate construction cost and compared with two common artificial intelligence algorithms: extreme learning machine and multivariate adaptive regression spline model. Statistical indicators showed that XGBoost algorithm achieved the best performance with a coefficient of determination (R2 = 0.952) and root mean square error (RMSE = 590,609.782). Due to the reliability of XGBoost model, the presented approach can assist project managers in abstracting the influencing variables and estimating the cost of building projects. The findings of this study are helpful for the project's stockholder to decrease the errors of the estimated cost and take the appropriate decision in the early stage of the construction process.
Hybrid machine learning approach for construction cost estimation: an evaluation of extreme gradient boosting model
Estimating the project cost is an important process in the early stage of the construction project. Accurate cost estimation prevents major issues like cost deficiency and disputes in the project. Identifying the affected parameters to project cost leads to accurate results and enhances cost estimation accuracy. In this paper, extreme gradient boosting (XGBoost) was applied to select the most correlated variables to the project cost. XGBoost model was used to estimate construction cost and compared with two common artificial intelligence algorithms: extreme learning machine and multivariate adaptive regression spline model. Statistical indicators showed that XGBoost algorithm achieved the best performance with a coefficient of determination (R2 = 0.952) and root mean square error (RMSE = 590,609.782). Due to the reliability of XGBoost model, the presented approach can assist project managers in abstracting the influencing variables and estimating the cost of building projects. The findings of this study are helpful for the project's stockholder to decrease the errors of the estimated cost and take the appropriate decision in the early stage of the construction process.
Hybrid machine learning approach for construction cost estimation: an evaluation of extreme gradient boosting model
Asian J Civ Eng
Ali, Zainab Hasan (author) / Burhan, Abbas M. (author)
Asian Journal of Civil Engineering ; 24 ; 2427-2442
2023-11-01
16 pages
Article (Journal)
Electronic Resource
English
Using extreme gradient boosting (XGBoost) machine learning to predict construction cost overruns
| Taylor & Francis Verlag | 2024
Extreme Gradient Boosting-Based Machine Learning Approach for Green Building Cost Prediction
| DOAJ | 2022