Construction Cost Estimation Using Machine Learning
DOI:
https://doi.org/10.29284/bjgkes87Keywords:
Construction Cost Estimation, Machine Learning, Multi-Output Regression, XGBoost, Ensemble Learning, Predictive Modeling, Civil Engineering Applications.Abstract
The estimation of construction costs is a very important subject in the project planning, budgeting, and financial decision making of a civil engineering project. The conventional methods of estimation, however, are mainly based on the information of the historical cost, manual calculation and intuition, which tend to create inaccuracies as construction activity is very dynamic and complicated. To overcome this obstacle, this research paper suggests a machine learning-based architecture of automated and precise building cost forecasting. A detailed dataset as a compilation of 10 000 records of construction projects was gathered using various sources such as records of contractors, government rate schedules as well as estimates of real-estate projects. Data cleaning, data imputation, feature scaling, and correlation-based feature selection were the techniques used to preprocess the dataset to enhance the quality of data and the performance of the model. Several regression models were run such as Linear regression, Decision tree, Random forest, Gradient Boosting and XGBoost as a MultiOutputRegressor to predict at once the quantity of materials, costs of materials and the total cost of construction. Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and coefficient of determination (R 2 ) were used to estimate the performance of the model. The outcome of the experiment showed that XGBoost, had the highest predictive power with a corresponding R 2 of approximately 0.9999, compared to the random forest (0.9998), among others. Also, the trained model was implemented in the form of a web application written in Flask with the help of which one can enter the parameters of the project and predict the costs in real time. These results indicate that ensemble machine learning models can also significantly increase accuracy and efficiency of construction cost estimation and offer a viable decision-support tool to engineers, contractors, and project planners.
References
[1] Zheng, Z., Zhou, L., Zhou, L. “Construction Cost Prediction System Based on Random Forest Optimized by the Bird Swarm Algorithm,” Mathematical Biosciences and Engineering, 20(8), pp. 15044–15074, 2023. https://doi.org/10.3934/mbe.2023674
[2] Magdum, S. K., Adamuthe, A. C. “Construction Cost Prediction Using Neural Networks,” ICTACT Journal on Soft Computing, 8(1), pp. 1549–1556, 2017.
[3] Xu, Y., Cao, S. “Building Engineering Cost Prediction Model Based on TSNE and Improved Grey Correlation Algorithm,” Procedia Computer Science, 228, pp. 957–965, 2023. https://doi.org/[Insert DOI if available]
[4] Ye, D. “An Algorithm for Construction Project Cost Forecast Based on Particle Swarm Optimization Guided BP Neural Network,” Scientific Programming, 2021, Article ID 4309495. https://doi.org/[Insert DOI if available]
[5] Hashemi, S. T., Ebadati, O. M., Kaur, H. “Cost Estimation and Prediction in Construction Projects: A Systematic Review on Machine Learning Techniques,” SN Applied Sciences, 2, Art. 1703, 2020. https://doi.org/[Insert DOI if available]
[6] Zhang, Y., Mo, H. “Intelligent Building Construction Cost Optimization and Prediction by Integrating BIM and Elman Neural Network,” Heliyon, 10(5), p. e37525, 2024. https://doi.org/[Insert DOI if available]
[7] Jirait, S., Rede, S. “House Construction Cost Prediction,” International Journal of Novel Research and Development, 9(5), pp. h311–h314, 2024.
[8] Park, D., Yun, S. “Construction Cost Prediction Using Deep Learning with BIM Properties in the Schematic Design Phase,” Applied Sciences, 13(12), Art. 7207, 2023. https://doi.org/[Insert DOI if available]
[9] Yaseen, M., Shaker, A., Altaee, S. “Hybrid GA ANN SVM Model for Construction Cost and Time Estimation,” International Journal of Engineering and Technology, 7(3.20), pp. 1142–1147, 2018.
[10] Liu, C., Li, Q., Wang, C. “Engineering Cost Estimation Model Based on GA Optimized BP Neural Network,” SHS Web of Conferences, 170, p. 02009, 2023. https://doi.org/[Insert DOI if available]
[11] Aung, Theingi, Sui Reng Liana, Arkar Htet, and Amiya Bhaumik. "Using machine learning to predict cost overruns in construction projects." Journal of Technology Innovations and Energy 2, no. 2 (2023): 1-7.
[12] Das, Pobithra, Abul Kashem, Imrul Hasan, and Mominul Islam. "A comparative study of machine learning models for construction costs prediction with natural gradient boosting algorithm and SHAP analysis." Asian Journal of Civil Engineering 25, no. 4 (2024): 3301-3316.
[13] Lee, Haneul, and Seokheon Yun. "Strategies for imputing missing values and removing outliers in the dataset for machine learning-based construction cost prediction." Buildings 14, no. 4 (2024): 933.
[14] Draz, Moatasem M., Osama Emam, and Safaa M. Azzam. "Software cost estimation predication using a convolutional neural network and particle swarm optimization algorithm." Scientific Reports 14, no. 1 (2024): 13129.
[15] Zhang, X., Song, J. “A Whole Process Cost Prediction System for Construction Projects Based on Improved Support Vector Machines,” 2022. https://doi.org/10.46300/9106.2022.16.34
[16] Wang, X. “Forecasting Construction Project Cost Based on BP Neural Network,” 2018. https://doi.org/10.1109/ICMTMA.2018.00109
[17] Zhang, Y., Mo, H. “Intelligent Building Construction Cost Prediction Based on BIM and Elman Neural Network,” 2023. https://doi.org/10.21203/rs.3.rs 3226303/v1
[18] Zheng, Z., Zhou, L., Zhou, L. “Construction Cost Prediction System Based on Random Forest Optimized by the Bird Swarm Algorithm,” Mathematical Biosciences and Engineering, [online] Available at: https://doi.org/10.3934/mbe.2023674 [Accessed: 14 July 2025].
[19] “Research on Intelligent Prediction of Engineering Cost Based on Artificial Intelligence,” 2023. https://doi.org/10.25236/ijndes.2023.070110
[20] Lakshana, J., Madhumitha, L., Dharshini, S. L. P., Kumar, T. R. “Cost Prediction for Home Construction Using Quantum Computing,” 2024. https://doi.org/10.4018/979 8 3693 3601 4.ch006
[21] Rayabharapu, V. K., Rao, K. D., Punitha, S., Abbas, S. H., Sivaranjani, L. “Enhancing Construction Project Cost Predictions using Machine Learning,” 2025. https://doi.org/10.2139/ssrn.5080704
[22] Shi, H., Li, W. “A Web Based Integrated System for Construction Project Cost Prediction,” 2010. https://doi.org/10.1007/978 3 642 05173 9_5
[23] Ali, Z. H., Burhan, A. M., Kassim, M., Al Khafaji, Z. H. K. “Developing an Integrative Data Intelligence Model for Construction Cost Estimation,” 2022. https://doi.org/10.1155/2022/4285328
[24] Ameya, F. M. “Evaluation of the Ongoing Use of Approximate Construction Cost Estimation,” 2025. https://doi.org/10.20944/preprints202501.1900.v1
[25] Sarode, G. C., E. C. S. “To Study Cost Prediction Analysis of Construction Project Using ANN Model and SVM by MATLAB,” 2020.
[26] Chandra, A., Yuliana, C. “Estimation of Cost Budget Using BIM in School Construction,” 2024. https://doi.org/10.20527/crc.v8i5.13421
[27] Yang, S.-W., Moon, S., Jang, H., Choo, S. Y., Kim, S.-A. “Parametric and BIM Based Cost Estimation for Construction Projects,” 2022. https://doi.org/10.3390/app12199553
[28] Yalçın, G., Bayram, S., Çıtakoğlu, H. “Evaluation of Earned Value Management Based Cost Estimation,” Buildings, 14(12), 372, 2024. https://doi.org/10.3390/buildings14123772
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
