Developing a stacked ensemble model for construction labor productivity prediction with metaheuristic-optimized random forest

Abdirisak Mohamed Abdillahi; Savaş Bayram; Abdirisak Mohamed Abdillahi; Savaş Bayram

doi:10.3934/jimo.2026071

Journal of Industrial and Management Optimization

2026, Volume 22, Issue 4: 1928-1955. doi: 10.3934/jimo.2026071

Previous Article Next Article

Research article

Developing a stacked ensemble model for construction labor productivity prediction with metaheuristic-optimized random forest

Abdirisak Mohamed Abdillahi ^1,2,
Savaş Bayram ^{3
,
,}

1.
Graduate School of Natural and Applied Sciences, Erciyes University, Kayseri 38039, Türkiye
2.
African Institute for Multidisciplinary Studies, Mogadishu, Somalia
3.
Department of Civil Engineering, Faculty of Engineering, Erciyes University, Kayseri 38039, Türkiye

Received: 27 May 2025 Revised: 23 February 2026 Accepted: 11 March 2026 Published: 20 March 2026
Primary: 90B30; Secondary: 68T05, 68T20, 90C59

Accurately predicting construction labor productivity is essential for effective project management, particularly in resource‐constrained settings like Somaliland. However, existing studies primarily rely on single-model structures, which often struggle to generalize across varying site conditions and activity types. Moreover, while metaheuristic optimization has been used to tune individual models, its integration into ensemble architectures remains limited, leaving a gap in methods capable of combining complementary learning behaviors. To address this, this study developed a stacked ensemble model designed to improve prediction stability and robustness. The proposed approach integrates two metaheuristically optimized Random Forest models, tuned using Particle Swarm Optimization and Artificial Bee Colony, with an Extreme Gradient Boosting (XGBoost) meta-learner. The model was evaluated on 1422 real-world productivity records from 52 construction projects involving concrete, formwork, and bricklaying tasks. The stacked ensemble achieved competitive and more stable performance, particularly for high-variance activities, demonstrating improved robustness, stability, and generalization. Feature selection results emphasized the importance of safety-related disruptions, weather conditions, and communication efficiency in determining labor productivity. The proposed model offers a practical and scalable tool for more reliable construction labor productivity (CLP) prediction and provides decision-making support for construction management, particularly in resource-limited environments.
- construction productivity,
- metaheuristic optimization,
- random forest,
- ensemble learning,
- XGBoost
Citation: Abdirisak Mohamed Abdillahi, Savaş Bayram. Developing a stacked ensemble model for construction labor productivity prediction with metaheuristic-optimized random forest[J]. Journal of Industrial and Management Optimization, 2026, 22(4): 1928-1955. doi: 10.3934/jimo.2026071

Related Papers:

Abstract

Accurately predicting construction labor productivity is essential for effective project management, particularly in resource‐constrained settings like Somaliland. However, existing studies primarily rely on single-model structures, which often struggle to generalize across varying site conditions and activity types. Moreover, while metaheuristic optimization has been used to tune individual models, its integration into ensemble architectures remains limited, leaving a gap in methods capable of combining complementary learning behaviors. To address this, this study developed a stacked ensemble model designed to improve prediction stability and robustness. The proposed approach integrates two metaheuristically optimized Random Forest models, tuned using Particle Swarm Optimization and Artificial Bee Colony, with an Extreme Gradient Boosting (XGBoost) meta-learner. The model was evaluated on 1422 real-world productivity records from 52 construction projects involving concrete, formwork, and bricklaying tasks. The stacked ensemble achieved competitive and more stable performance, particularly for high-variance activities, demonstrating improved robustness, stability, and generalization. Feature selection results emphasized the importance of safety-related disruptions, weather conditions, and communication efficiency in determining labor productivity. The proposed model offers a practical and scalable tool for more reliable construction labor productivity (CLP) prediction and provides decision-making support for construction management, particularly in resource-limited environments.

References

[1]	D. Przywara, A. Rak, Analysis construction industry on the basis of price trends of labor cost, MATEC Web Conf., 146 (2018), 04005. https://doi.org/10.1051/matecconf/201817404005 doi: 10.1051/matecconf/201817404005
[2]	A. M. Abdillahi, A. Kazaz, Evaluating Factors Effecting Building Construction Labor Productivity in Somaliland, J. Constr. Eng. Technol. Manag., 11 (2021), 19–28.
[3]	O. Moselhi, Z. Khan, Significance ranking of parameters impacting construction labour productivity, Constr. Innov., 12 (2012), 272–296. https://doi.org/10.1108/14714171211244541 doi: 10.1108/14714171211244541
[4]	T. Mahfouz, A productivity decision support system for construction projects through machine learning (ML), Proc. CIB W78, 2012
[5]	K. P. Kisi, N. Mani, E. M. Rojas, E. Terence Foster, Estimation of Optimal Productivity in Labor-Intensive Construction Operations: Advanced Study, J. Constr. Eng. Manage., 144 (2018), 04018097. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001551 doi: 10.1061/(ASCE)CO.1943-7862.0001551
[6]	Y. T. Lim, W. Yi, H. Wang, Application of Machine Learning in Construction Productivity at Activity Level: A Critical Review, Appl. Sci., 14 (2024), 10605. https://doi.org/10.3390/app142210605 doi: 10.3390/app142210605
[7]	L. Florez-Perez, Z. Song, J. C. Cortissoz, Predicting construction productivity with machine learning approaches, Proc. Int. Symp. Autom. Robot. Constr., 2022. https://doi.org/10.22260/ISARC2022/0017 doi: 10.22260/ISARC2022/0017
[8]	P. Joshi, S. K. Shrestha, Analysis of Labor Productivity during concreting operation in building construction of Kathmandu Valley, J. Adv. Res. Constr. Urban Archit., 4 (2019), 1–7.
[9]	M. H. Momade, S. Shahid, M. R. bin Hainin, et al., Modelling labour productivity using SVM and RF: a comparative study on classifiers performance, Int. J. Constr. Manag., 22 (2022), 1924–1934. https://doi.org/10.1080/15623599.2020.1744799 doi: 10.1080/15623599.2020.1744799
[10]	S. Golnaraghi, Z. Zangenehmadar, O. Moselhi, S. Alkass, Application of Artificial Neural Network(s) in Predicting Formwork Labour Productivity, Adv. Civ. Eng., 2019 (2019). https://doi.org/10.1155/2019/5972620 doi: 10.1155/2019/5972620
[11]	P. Goodarzizad, E. Mohammadi Golafshani, M. Arashpour, Predicting the construction labour productivity using artificial neural network and grasshopper optimisation algorithm, Int. J. Constr. Manag., 23 (2023), 763–779. https://doi.org/10.1080/15623599.2021.1927363 doi: 10.1080/15623599.2021.1927363
[12]	S. Ebrahimi, Developing hybrid artificial intelligence model for construction labour productivity prediction and optimization, MSc Thesis, University of Alberta, Canada, 2021.
[13]	S. Ebrahimi, A. R. Fayek, V. Sumati, Hybrid artificial intelligence hfs-rf-pso model for construction labor productivity prediction and optimization, Algorithms, 14 (2021). https://doi.org/10.3390/a14070214 doi: 10.3390/a14070214
[14]	B. P. Kaur, H. Singh, R. Hans, S. K. Sharma, C. Sharma, M. M. Hassan, A Genetic algorithm aided hyper parameter optimization based ensemble model for respiratory disease prediction with Explainable AI, PLoS One, 19 (2024), e0308015. https://doi.org/10.1371/journal.pone.0308015 doi: 10.1371/journal.pone.0308015
[15]	G. Feng, Feature selection algorithm based on optimized genetic algorithm and the application in high-dimensional data processing, PLoS One, 19 (2024), e0303088. https://doi.org/10.1371/journal.pone.0303088 doi: 10.1371/journal.pone.0303088
[16]	D. Yilmaz Eroglu, U. Akcan, An Adapted Ant Colony Optimization for Feature Selection, Appl. Artif. Intell., 38 (2024), 2335098. https://doi.org/10.1080/08839514.2024.2335098 doi: 10.1080/08839514.2024.2335098
[17]	E. Saraç, S. A. Özel, An Ant Colony Optimization Based Feature Selection for Web Page Classification, Sci. World J., 2014 (2014), 1–16. https://doi.org/10.1155/2014/649260 doi: 10.1155/2014/649260
[18]	H. Abubakar, S. Boukari, A. Y. Gital, F. U. Zambuk, A hyper-parameter tuned Random Forest algorithm-based on Artificial Bee Colony for improving accuracy, precision and interpretability of crime prediction, Dutse J. Pure Appl. Sci., 10 (2024), 371–381. https://doi.org/10.4314/dujopas.v10i4a.34 doi: 10.4314/dujopas.v10i4a.34
[19]	M. Kaya Keles, U. Kilic, A. E. Keles, Proposed artificial bee colony algorithm as feature selector to predict the leadership perception of site managers, Comput. J., 64 (2021), 408–417. https://doi.org/10.1093/comjnl/bxaa163 doi: 10.1093/comjnl/bxaa163
[20]	A. Brodzicki, M. Piekarski, J. Jaworek-Korjakowska, The whale optimization algorithm approach for deep neural networks, Sensors, 21 (2021), 8003. https://doi.org/10.3390/s21238003 doi: 10.3390/s21238003
[21]	M. A. Kahya, S. A. Altamir, Z. Y. Algamal, Improving whale optimization algorithm for feature selection with a time-varying transfer function, Numer. Algebra Control Optim., 11 (2020), 87–98. https://doi.org/10.3934/naco.2020017 doi: 10.3934/naco.2020017
[22]	A. T. Maadapoosi, V. Balamurugan, V. Vedanarayanan, S. A. Nisha, R. Narmadha, Grey Wolf Optimization-Based Artificial Neural Network in the Development of an Automated Heart Disease Prediction Model, Int. J. Fuzzy Log. Intell. Syst., 24 (2024), 231–241. http://doi.org/10.5391/IJFIS.2024.24.3.231 doi: 10.5391/IJFIS.2024.24.3.231
[23]	Y. C. Kuyu, N. Ozekmekci, Grey wolf optimizer to the hyperparameters optimization of convolutional neural network with several activation functions, 2022 Int. Symp. Multidiscip. Stud. Innov. Technol. (ISMSIT), IEEE, 2022, 13–17.
[24]	Z. Chen, W. Fan, Freeway Travel Time Prediction Based on Ensemble Learning Approaches, Int. Conf. Transp. Dev. 2023, Austin, Texas, American Society of Civil Engineers, 2023,410–423. https://doi.org/10.1061/9780784484876.036
[25]	B. Ozturk, A. Kodsy, M. Iskander, Forecasting the Bearing Capacity of Open-Ended Pipe Piles Using Machine Learning Ensemble Methods, IFCEE 2024, Dallas, Texas, American Society of Civil Engineers, 2024,146–156. https://doi.org/10.1061/9780784485408.016
[26]	U. Park, Y. Kang, H. Lee, S. Yun, A stacking heterogeneous ensemble learning method for the prediction of building construction project costs, Appl. Sci., 12 (2022), 9729. https://doi.org/10.3390/app12199729 doi: 10.3390/app12199729
[27]	I. Karatas, A. Budak, Development and comparative of a new meta-ensemble machine learning model in predicting construction labor productivity, Eng. Constr. Archit. Manag., 31 (2024), 1123–1144. https://doi.org/10.1108/ECAM-08-2021-0692 doi: 10.1108/ECAM-08-2021-0692
[28]	N. Lawaju, N. Parajuli, S. K. Shrestha, Analysis of Labor Productivity of Brick Masonry Work in Building Construction in Kathmandu Valley, J. Adv. Coll. Engin. Mgt., 6 (2021), 159–175. https://doi.org/10.3126/jacem.v6i0.38356 doi: 10.3126/jacem.v6i0.38356
[29]	F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirio, O. Grisel, et al., Scikit-learn: Machine learning in Python, J. Mach. Learn. Res., 12 (2011), 2825–2830.
[30]	S. Shoar, N. Chileshe, J. D. Edwards, Machine learning-aided engineering services' cost overruns prediction in high-rise residential building projects: Application of random forest regression, J. Build. Eng., 50 (2022), 104102. https://doi.org/10.1016/j.jobe.2022.104102 doi: 10.1016/j.jobe.2022.104102
[31]	M. Čeh, M. Kilibarda, A. Lisec, B. Bajat, Estimating the performance of random forest versus multiple regression for predicting prices of the apartments, ISPRS Int. J. Geo-Inf., 7 (2018), 168. https://doi.org/10.3390/ijgi7050168 doi: 10.3390/ijgi7050168
[32]	H. Sun, D. Gui, B. Yan, Y. Liu, W. Liao, Y. Zhu, et al., Assessing the potential of random forest method for estimating solar radiation using air pollution index, Energy Convers. Manag., 119 (2016), 121–129. https://doi.org/10.1016/j.enconman.2016.04.051 doi: 10.1016/j.enconman.2016.04.051
[33]	T. O. Hodson, Root mean square error (RMSE) or mean absolute error (MAE): When to use them or not, Geosci. Model Dev. Discuss., 2022 (2022), 1–10. https://doi.org/10.5194/gmd-15-5481-2022 doi: 10.5194/gmd-15-5481-2022
[34]	K. Deb, Multiobjective optimization using evolutionary algorithms, New York: Wiley, 2001.
[35]	M. Dorigo, V. Maniezzo, A. Colorni, Ant system: optimization by a colony of cooperating agents, IEEE Trans. Syst. Man Cybern. B Cybern., 26 (1996), 29–41. https://doi.org/10.1109/3477.484436 doi: 10.1109/3477.484436
[36]	S. T. Ng, Y. Zhang, Optimizing Construction Time and Cost Using Ant Colony Optimization Approach, J. Constr. Eng. Manage., 134 (2008), 721–728. https://doi.org/10.1061/(ASCE)0733-9364(2008)134:9(721) doi: 10.1061/(ASCE)0733-9364(2008)134:9(721)
[37]	D. Karaboga, An idea based on honey bee swarm for numerical optimization, Technical Report TR06, Computer Engineering Department, Engineering Faculty, Erciyes University, Kayseri, Türkiye, 2005.
[38]	M. Yahya, M. P. Saka, Construction site layout planning using multi-objective artificial bee colony algorithm with Lévy flights, Autom. Constr., 38 (2014), 14–29. https://doi.org/10.1016/j.autcon.2013.11.001 doi: 10.1016/j.autcon.2013.11.001
[39]	D. H. Tran, M. Y. Cheng, M. T. Cao, Hybrid multiple objective artificial bee colony with differential evolution for the time–cost–quality tradeoff problem, Knowl.-Based Syst., 74 (2015), 176–186. http://dx.doi.org/10.1016/j.knosys.2014.11.018 doi: 10.1016/j.knosys.2014.11.018
[40]	A. Sharma, A. Sharma, S. Choudhary, R. K. Pachauri, A. Shrivastava, D. Kumar, A review on artificial bee colony and it's engineering applications, J. Crit. Rev., 7 (2020), 4097–4107.
[41]	S. Mirjalili, S. M. Mirjalili, A. Lewis, Grey wolf optimizer, Adv. Eng. Softw., 69 (2014), 46–61. https://doi.org/10.1016/j.advengsoft.2013.12.007 doi: 10.1016/j.advengsoft.2013.12.007
[42]	E. Dada, S. Joseph, D. Oyewola, A. A. Fadele, H. Chiroma, S. I. M. Abdulhamid, Application of grey wolf optimization algorithm: recent trends, issues, and possible horizons, Gazi Univ. J. Sci., 35 (2022), 485–504. https://doi.org/10.35378/gujs.820885 doi: 10.35378/gujs.820885
[43]	S. Katoch, S. S. Chauhan, V. Kumar, A review on genetic algorithm: past, present, and future, Multimed. Tools Appl., 80 (2021), 8091–8126. https://doi.org/10.1007/s11042-020-10139-6 doi: 10.1007/s11042-020-10139-6
[44]	S. N. Sivanandam, S. N. Deepa, Genetic Algorithms, in: Introduction to Genetic Algorithms, Berlin, Heidelberg: Springer Berlin Heidelberg, 2008, 15–37. https://doi.org/10.1007/978-3-540-73190-0_2
[45]	J. Kennedy, R. Eberhart, Particle swarm optimization, Proc. ICNN'95-Int. Conf. Neural Netw., IEEE, 1995, 1942–1948. https://doi.org/10.1109/ICNN.1995.488968
[46]	H. Yiğit, S. Ürgün, S. Mirjalili, Comparison of recent metaheuristic optimization algorithms to solve the SHE optimization problem in MLI, Neural Comput. Appl., 35 (2023), 7369–7388. https://doi.org/10.1007/s00521-022-07980-1 doi: 10.1007/s00521-022-07980-1
[47]	M. Lu, Q. Hou, S. Qin, L. Zhou, D. Hua, X. Wang, et al., A stacking ensemble model of various machine learning models for daily runoff forecasting, Water, 15 (2023), 1265. https://doi.org/10.3390/w15071265 doi: 10.3390/w15071265
[48]	D. R. I. M. Setiadi, K. Nugroho, A. R. Muslikh, S. W. Iriananda, A. A. Ojugo, Integrating SMOTE-Tomek and Fusion Learning with XGBoost Meta-Learner for Robust Diabetes Recognition, J. Future Artif. Intell. Technol., 1 (2024), 23–38. https://doi.org/10.62411/faith.2024-11 doi: 10.62411/faith.2024-11

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)