An Ensemble Machine Learning-Based Decision-Support Framework for Predicting Construction Labour Productivity

Yasser Aboelmagd; Remon Eskander

doi:10.31081/dmame8120251676

Authors

Yasser Aboelmagd Vice Dean, College of Engineering, University of Business & Technology (UBT), Jeddah, Saudi Arabia & Mathematics and Physics Engineering Department, Faculty of Engineering, Alexandria University, Egypt
Remon Eskander Engineering Programs Director, Field of Engineering, Alamein International University (AIU), New Al-Alamein City, Matrouh - Egypt & Structural Engineering Department, Faculty of Engineering, Alexandria University, Egypt

DOI:

https://doi.org/10.31081/dmame8120251676

Keywords:

Labour Productivity, Construction Productivity, RII (Relative Importance Index), Columns Formwork, Machine Learning, Ensemble Model, Productivity Prediction, Deep Learning, and Regression

Abstract

The construction sector is currently recognised as a highly innovative industry, where sustained monitoring of labour efficiency has accelerated project expansion. Nevertheless, addressing performance constraints requires optimising workforce productivity, accurately estimating task durations, and improving output rates to minimise labour expenses and project timelines. This study examines enhancements to conventional site practices, where professionals such as contractors, engineers, and managers typically rely on theoretical productivity approximations that often result in time and cost inefficiencies. Within the Egyptian context, standardised benchmarks for forecasting construction labour productivity remain absent. Accordingly, this research identifies the principal determinants affecting column formwork productivity through a structured questionnaire. Variables demonstrating high relative importance index (RII) values were selected as independent predictors influencing the dependent variable, labour productivity, within the proposed model. Empirical productivity observations were recorded at two-hour intervals across three sites, Smouha, Beheira, and Moharam-Bek, enabling the assessment of time and cost loss ratios and the establishment of baseline metrics for each location. Furthermore, an artificial intelligence model was implemented using the Python programming language within Visual Studio Code to estimate short-term productivity, thereby supporting improved scheduling and managerial decision-making for enhanced efficiency and cost reduction. The findings indicate that the developed ensemble machine learning approach achieved a performance accuracy of 97.66% with a validation error of 0.015. A web-based platform was also created as a baseline system, offering practitioners and planners a dependable and precise tool for forecasting column formwork labour productivity at two-hour intervals prior to project execution.

Downloads

Download data is not yet available.

References

[1] Abdel-Hamid, M., & Abdelhaleem, H. M. (2022). Impact of poor labor productivity on construction project cost. International Journal of Construction Management, 22(12), 2356-2363. https://doi.org/10.1080/15623599.2021.1877243

[2] Ahmad, S. B. S., Mazhar, M. U., Bruland, A., Andersen, B. S., Langlo, J. A., & Torp, O. (2020). Labour productivity statistics: a reality check for the Norwegian construction industry. International Journal of Construction Management, 20(1), 39-52. https://doi.org/10.1080/15623599.2018.1484859

[3] Alinaitwe, H., Mwakali, J., & Hansson, B. (2006). Labor productivity in the building construction. https://itc.scix.net/pdfs/w65-2006-85.pdf

[4] Almamlook, R., Bzizi, M., Al-Kbisbeh, M., Ali, T., & Almajiri, E. (2020). Factors affecting labor productivity in the construction industry. American Journal of Environmental Science and Engineering, 4(2), 24-30. https://doi.org/10.11648/j.ajese.20200402.11

[5] Aswed, G. K. (2016). Productivity estimation model for bricklayer in construction projects using neural network. Al-Qadisiyah Journal for Engineering Sciences, 9(2), 183-199. https://journal.qu.edu.iq/index.php/engineering/article/view/283

[6] Breiman, L. (2001). Statistical modeling: The two cultures. Statistical Science, 16(3), 199-231. https://doi.org/10.1214/ss/1009213726

[7] Budak, A., & Karataş, İ. (2022). Impact of the BIM system in construction management services in developing countries; Case of Turkey. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 28(6), 828-839. https://doi.org/10.5505/pajes.2022.12352

[8] Dozzi, S. P., & AbouRizk, S. M. (1993). Productivity in construction. https://nrc-publications.canada.ca/eng/view/object/?id=8b3c3a61-6d06-4c58-b5a2-0c0b7e5b8e1c

[9] El-Gohary, K. M., & Aziz, R. F. (2014). Factors influencing construction labor productivity in Egypt. Journal of management in engineering, 30(1), 1-9. https://doi.org/10.1061/(ASCE)ME.1943-5479.0000168

[10] El-Gohary, K. M., Aziz, R. F., & Abdel-Khalek, H. A. (2017). Engineering approach using ANN to improve and predict construction labor productivity under different influences. Journal of Construction Engineering and Management, 143(8), 04017045. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001342

[11] Golnaraghi, S., Moselhi, O., Alkass, S., & Zangenehmadar, Z. (2020). Modelling construction labour productivity using evolutionary polynomial regression. International Journal of Productivity and Quality Management, 31(2), 207-226. https://doi.org/10.1504/IJPQM.2020.110418

[12] Golnaraghi, S., Zangenehmadar, Z., Moselhi, O., & Alkass, S. (2019). Application of artificial neural networks in predicting formwork labour productivity. Advances in Civil Engineering, 2019, 5972620. https://doi.org/10.1155/2019/5972620

[13] Heravi, G., & Eslamdoost, E. (2015). Applying artificial neural networks for measuring and predicting construction-labor productivity. Journal of Construction Engineering and Management, 141(10), 04015032. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001006

[14] Jarkas, A. M. (2010). Buildability factors influencing formwork labour productivity of walls. International Journal of Construction Management, 10(4), 101-117. https://doi.org/10.3763/ijcm.2010.0342

[15] Juszczyk, M. (2020). Analysis of labour efficiency supported by the ensembles of neural networks on the example of steel reinforcement works. Archives of Civil Engineering, 66(1), 97-111. https://doi.org/10.24425/ace.2020.131789

[16] Kediya, S., Bhorkar, M., Deshpande, P., Jain, R., Puri, C., & Gudadhe, A. A. (2023). Review on the Significance of Artificial Intelligence in Construction Engineering and Management. https://doi.org/10.1109/ICCSAI58935.2023.10291173

[17] Mohapatra, A., Mohammed, A. R., & Panda, S. (2023). Role of Artificial Intelligence in the Construction Industry—A Systematic Review. https://ijarcce.com/wp-content/uploads/2023/01/IJARCCE.2023.120105.pdf

[18] Ospitia, N., Jaramani, R., Remy, O., & Aggelis, D. G. (2022). Determination of concrete formwork removal time based on ultrasound reflection. Applied Sciences, 12(3), 1221. https://doi.org/10.3390/app12031221

[19] Rojas, E. M., & Aramvareekul, P. (2003). Labor productivity drivers and opportunities in the construction industry. Journal of Management in Engineering, 19(2), 78-82. https://doi.org/10.1061/(ASCE)0742-597X(2003)19:2(78)

[20] Sana, S. S. (2011). A production-inventory model of imperfect quality products in a three-layer supply chain. Decision Support Systems, 50(2), 539-547. https://doi.org/10.1016/j.dss.2010.09.012

[21] Sonmez, R., & Rowings, J. E. (1998). Construction labor productivity modeling with neural networks. Journal of Construction Engineering and Management, 124(6), 498-504. https://doi.org/10.1061/(ASCE)0733-9364(1998)124:6(498)

[22] Tayalati, F., Boukrouh, I., Azmani, A., & Azmani, M. (2024). Deep Learning-Based Intelligent X-Bar Control Chart for Monitoring Manufacturing Process. https://doi.org/ 10.1109/IICAIET60512.2024.10420465

[23] Tsehayae, A. A., & Fayek, A. R. (2016). Developing and optimizing context-specific fuzzy inference system-based construction labor productivity models. Journal of Construction Engineering and Management, 142(7), 04016017. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001128

[24] Waters Ii, W. (2007). Productivity measurement. In Handbook of Transport Modelling (pp. 395-415). https://doi.org/10.1108/9781847200201-022

[25] Woldetsadik, E. T. (2025). A Predictive Model for Estimating Formwork and Shoring Removal Time The George Washington University]. https://hsrc.himmelfarb.gwu.edu/etd/