Cost Estimation of Metro Construction Projects Using Interpretable Machine Learning
Publication: Journal of Computing in Civil Engineering
Volume 38, Issue 6
Abstract
The metro, renowned as an environmentally friendly mode of transportation due to its low energy consumption and minimal pollution, plays a crucial role in achieving sustainable urban growth. Due to the scarcity of information in the early stages of metro construction projects and the subjectivity of cost estimation (which relies heavily on the estimator’s experience), it is always difficult to guarantee the accuracy of metro construction project cost estimation. Furthermore, the existing methodological models commonly used for cost estimation do not adequately consider the interpretability of the estimation results, making it difficult to promote their application in real-world scenarios. In this paper, an interpretable machine learning method is introduced into the study of cost estimation of metro construction projects, and a maximum relevance and minimum redundancy (mRMR)–light gradient boosting machine (LightGBM)–Shapley additive explanations (SHAP) interpretable assisted investment decision-making framework is proposed. The results show that the negative impact of variable multicollinearity on model prediction is avoided by quantitatively identifying the key driving variables of costing through mRMR based on the historical data of metro construction projects and macroeconomic data. LightGBM is employed to predict the cost of metro construction projects with a mean absolute percentage error of 13.00%, surpassing the accuracy of the five baseline models. The SHAP method’s introduction explains the influence of key driving variables on the model prediction response at both global and local levels, which improves the decision trust of the cost estimation of metro construction projects. The study takes into account the impact of key driving variables on the model’s prediction response in a real-world context and balances the needs for estimation accuracy and variable interpretability in real-world scenarios.
Practical Applications
In this study, we propose a new interpretable machine learning method that helps improve the decision trust of cost estimation for metro construction projects. We use the mRMR module to identify the key driving variables for cost. Based on the LightGBM module, we accurately fit the nonlinear relationship between the cost of metro construction projects and the key variables. The SHAP algorithm is introduced to analyze the effects of the key driving variables on the prediction of the model at both global and local levels. The combined mRMR-LightGBM-SHAP model is proven to have better prediction accuracy than the traditional prediction model under the same conditions, and the SHAP response results prove the reliability of the model prediction. The study also found that the inclusion of economic environment variables plays a positive role in improving the accuracy of cost estimation for metro construction projects. The research results can be mainly used by metro investment units to quickly confirm or review the cost of metro construction projects, and they can also help government departments pay close attention to the impact of the external economic environment on the cost of metro construction.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
All data, models, or codes that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
This study was supported by the National Natural Science Foundation of China (Grant No. 72071133) and the Funding Program for Cultivating Innovative Abilities of Graduate Students Studying in the Department of Education of Hebei Province (Grant No. CXZZBS2024147).
References
Adeli, H., and A. Karim. 1997. “Scheduling/cost optimization and neural dynamics model for construction.” J. Constr. Eng. Manage. 123 (4): 450–458. https://doi.org/10.1061/(ASCE)0733-9364(1997)123:4(450).
Anderson, S. D., K. R. Molenaar, and C. Schexnayder. 2007. Guidance for cost estimation and management for highway projects during planning, programming, and preconstruction. Washington, DC: Transportation Research Board.
Antoniou, F., G. N. Aretoulis, D. Giannoulakis, and D. Konstantinidis. 2023. “Cost and material quantities prediction models for the construction of underground metro stations.” Buildings 13 (2): 382. https://doi.org/10.3390/buildings13020382.
Arrieta, A. B., et al. 2020. “Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible.” AI Inf. Fusion 58 (Jun): 82–115. https://doi.org/10.1016/j.inffus.2019.12.012.
Baye, M. R., and R. O. Beil. 2006. Managerial economics and business strategy. New York: McGraw-Hill.
Breiman, L. 2001. “Statistical modeling: The two cultures (with comments and a rejoinder by the author).” Stat. Sci. 16 (3): 199–231. https://doi.org/10.1214/ss/1009213726.
Chan, S. L., and M. Park. 2005. “Project cost estimation using principal component regression.” Construct. Manage. Econ. 23 (3): 295–304. https://doi.org/10.1080/01446190500039812.
Duan, X. C., Y. X. Chen, Z. D. Shi, and K. L. Huang. 2021. “Research on the intelligent estimation method of metro construction investment.” J. Railway Eng. Soc. 38 (11): 109–114. https://doi.org/10.3969/j.issn.1006-2106.2021.11.018.
Efron, B. 1979. “Bootstrap methods: Another look at the jackknife.” Annal Stat. 7 (1): 1–26. https://doi.org/10.1214/aos/1176344552.
Fan, S.-L., I.-C. Yeh, and W.-S. Chi. 2021. “Improvement in estimating durations for building projects using artificial neural network and sensitivity analysis.” J. Constr. Eng. Manage. 147 (7): 04021050. https://doi.org/10.1061/(ASCE)CO.1943-7862.0002036.
Flyvbjerg, B., M. S. Holm, and S. Buhl. 2002. “Underestimating costs in public works projects: Error or lie?” J. Am. Plann. Assoc. 68 (3): 279–295. https://doi.org/10.1080/01944360208976273.
Gao, H., and X. Q. Zhang. 2013. “A Markov-based road maintenance optimization model considering user costs.” Comput.-Aided Civ. Infrastruct. Eng. 28 (6): 451–464. https://doi.org/10.1111/mice.12009.
Ghimire, P., S. Pokhare, K. Kim, and P. Barutha. 2023. “Machine learning-based prediction models for budget forecast in capital construction.” In Proc., 2nd Int. Conf. on Construction, Energy, Environment & Sustainability (CEES 2023). Funchal, Portugal: Itecons.
Gunduz, M., L. O. Ugur, and E. Ozturk. 2011. “Parametric cost estimation system for light rail transit and metro trackworks.” Expert Syst. Appl. 38 (3): 2873–2877. https://doi.org/10.1016/j.eswa.2010.08.080.
Hashemi, S. T., E. O. M. Ebadati, and H. Kaur. 2019. “A hybrid conceptual cost estimating model using ANN and GA for power plant projects.” Neural Comput. Appl. 31 (7): 2143–2154. https://doi.org/10.1007/s00521-017-3175-5.
He, Z., and N. E. Khorasani. 2022. “Identification and hierarchical structure of cause factors for fire following earthquake using data mining and interpretive structural modeling.” Nat. Hazards 112 (1): 947–976. https://doi.org/10.1007/s11069-022-05214-0.
Hollar, D. A., W. Rasdorf, M. Liu, J. E. Hummer, I. Arocho, and S. M. Hsiang. 2012. “Preliminary engineering cost estimation model for bridge projects.” J. Constr. Eng. Manage. 139 (9): 1943–7862. https://doi.org/10.1061/(ASCE)CO.1943-7862.0000668.
Hsiao, F. Y., S. H. Wang, W. C. Wang, C. P. Wen, and W. D. Yu. 2012. “Neuro-fuzzy cost estimation model enhanced by fast messy genetic algorithms for semiconductor hookup construction.” Comput.-Aided Civ. Infrastruct. Eng. 27 (10): 764–781. https://doi.org/10.1111/j.1467-8667.2012.00786.x.
Jafarzadeh, R., J. M. Ingham, S. Wilkinson, V. González, and A. A. Aghakouchak. 2013. “Application of artificial neural network methodology for predicting seismic retrofit construction costs.” J. Constr. Eng. Manage. 140 (2): 04013044. https://doi.org/10.1061/(ASCE)CO.1943-7862.0000725.
Jiang, Q. H. 2019. “Estimation of construction project building cost by back-propagation neural network.” J. Eng. Des. Technol. 18 (3): 601–609. https://doi.org/10.1108/JEDT-08-2019-0195.
Karaca, I., D. D. Gransberg, and H. D. Jeong. 2020. “Improving the accuracy of early cost estimates on transportation infrastructure projects.” J. Manage. Eng. 36 (5): 04020063. https://doi.org/10.1061/(ASCE)ME.1943-5479.0000819.
Karim, A., and H. Adeli. 1999. “CONSCOM: An OO construction scheduling and change management system.” J. Constr. Eng. Manage. 125 (5): 368–376. https://doi.org/10.1061/(ASCE)0733-9364(1999)125:5(368).
Ke, G., Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, and T. Y. Liu. 2017. “LightGBM: A highly efficient gradient boosting decision tree.” In Proc., 2017 Advances in Neural Information Processing Systems, 3149–3157. New York: Curran Associates.
Kim, G. H., S. H. An, and K. I. Kang. 2004a. “Comparison of construction cost estimating models based on regression analysis, neural networks, and case-based reasoning.” Build. Environ. 39 (10): 1235–1242. https://doi.org/10.1016/j.buildenv.2004.02.013.
Kim, G. H., J. E. Yoon, S. H. An, H. H. Cho, and K. I. Kang. 2004b. “Neural network model incorporating a genetic algorithm in estimating construction costs.” Build. Environ. 39 (11): 1333–1340. https://doi.org/10.1016/j.buildenv.2004.03.009.
Lundberg, S. M., and S. I. Lee. 2017. “A unified approach to interpreting model predictions.” In Proc., 31st Int. Conf. on Neural Information Processing Systems, 4768–4777. New York: Curran Associates Inc.
Mahamid, I., and A. Bruland. 2010. “Preliminary cost estimating models for road construction activities.” In Proc., FIG Congress. Sydney, NSW, Australia: Leica.
Mou, Q., and G. Jia. 2018. “Reference class forecasting (RCF) for estimates and approval of governmental construction projects: A case study of Shenzhen's transportation infrastructure projects.” Stat. Inf. For. 33 (5): 85–92.
Ogungbile, A. J., A. E. Oke, and K. Rasak. 2018. “Developing cost model for preliminary estimate of road projects in Nigeria.” Int. J. Sustainable Real Estate Constr. Econ. 1 (2): 182–199. https://doi.org/10.1504/IJSRECE.2018.092277.
Peng, H., F. Long, and C. Ding. 2005. “Feature selection based on mutual information: Criteria of max-dependency, max-relevance, and min-redundancy.” IEEE Trans. Pattern Anal. Mach. Intell. 27 (8): 1226–1238. https://doi.org/10.1109/TPAMI.2005.159.
Petroutsatou, C., S. Lambropoulos, and J. P. Pantouvakis. 2006. “Road tunnel early cost estimates using multiple regression analysis.” Oper. Res. 6 (3): 311–322. https://doi.org/10.1007/BF02941259.
Pokharel, S., and P. Ghimire. 2023. “Data-driven ML models for accurate prediction of energy consumption in a low-energy house: A comparative study of XGBoost, random forest, decision tree, and support vector machine.” J. Innovations Eng. Educ. 6 (1): 12–20. https://doi.org/10.3126/jiee.v6i1.54965.
Rafiei, M. H., and H. Adeli. 2015. “A novel machine learning model for estimation of sale prices of real estate units.” J. Constr. Eng. Manage. 142 (2): 04015066. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001047.
Rafiei, M. H., and H. Adeli. 2016. “Sustainability in highrise building design and construction.” Struct. Des. Tall Special Build. 25 (13): 643–658. https://doi.org/10.1002/tal.1276.
Rafiei, M. H., and H. Adeli. 2018. “Novel machine-learning model for estimating construction costs considering economic variables and indexes.” J. Constr. Eng. Manage. 144 (12): 04018106. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001570.
Shmueli, G. 2009. “To explain or to predict?” Stat. Sci. 25 (3): 289–310. https://doi.org/10.1214/10-STS330.
Smith, R., E. Ferrebee, Y. Ouyang, and J. Roesler. 2014. “Optimal staging area locations and material recycling strategies for sustainable highway reconstruction.” Comput.-Aided Civ. Infrastruct. Eng. 29 (8): 559–571. https://doi.org/10.1111/mice.12089.
Sonmez, R. 2004. “Conceptual cost estimation of building projects with regression analysis and neural networks.” Can. J. Civ. Eng. 31 (4): 677–683. https://doi.org/10.1139/l04-029.
Tong, B., J. Guo, and S. Fang. 2021. “Predicting budgetary estimate of highway construction projects in China based on GRA-LASSO.” J. Manage. Eng. 37 (3): 04021012. https://doi.org/10.1061/(ASCE)ME.1943-5479.0000890.
Wang, F. Y. 2012. “Analysis of metro engineering comprehensive cost index.” Railway Eng. Cost Manage. 27 (5): 33–36. https://doi.org/10.3969/j.issn.1007-9890.2012.05.011.
Wang, R., V. Asghari, C. M. Cheung, S. C. Hsu, and C. J. Lee. 2022. “Assessing effects of economic factors on construction cost estimation using deep neural networks.” Autom. Constr. 134 (Feb): 104080. https://doi.org/10.1016/j.autcon.2021.104080.
Wen, X., Y. C. Xie, L. T. Wu, and L. M. Jiang. 2021. “Quantifying and comparing the effects of key risk factors on various types of roadway segment crashes with LightGBM and SHAP.” Accid. Anal. Prev. 159 (1): 106261. https://doi.org/10.1016/j.aap.2021.106261.
Wilmot, C. G., and B. Mei. 2005. “Neural network modeling of highway construction costs.” J. Constr. Eng. Manage. 131 (7): 765–771. https://doi.org/10.1061/(ASCE)0733-9364(2005)131:7(765).
Yan, H. Y., Z. He, C. Gao, M. J. Xie, H. Y. Sheng, and H. H. Chen. 2022. “Investment estimation of prefabricated concrete buildings based on XGBoost machine learning algorithm.” Adv. Eng. Inf. 54 (Oct): 101789. https://doi.org/10.1016/j.aei.2022.101789.
Zhang, Y., R. E. Minchin Jr., and D. Agdas. 2017. “Forecasting completed cost of highway construction projects using LASSO regularized regression.” J. Constr. Eng. Manage. 143 (10): 04017071. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001378.
Zhang, Y., R. E. Minchin Jr., I. Flood, and R. J. Ries. 2023. “Preliminary cost estimation of highway projects using statistical learning methods.” J. Constr. Eng. Manage. 149 (5): 04023026. https://doi.org/10.1061/JCEMD4.COENG-12773.
Zhou, G., A. Etemadi, and A. Mardon. 2022. “Machine learning-based cost predictive model for better operating expenditure estimations of US light rail transit projects.” J. Public Transp. 24 (1): 10003. https://doi.org/10.1016/j.jpubtr.2022.100031.
Information & Authors
Information
Published In
Journal of Computing in Civil Engineering
Volume 38 • Issue 6 • November 2024
Copyright
© 2024 American Society of Civil Engineers.
History
Received: Feb 22, 2024
Accepted: Jun 14, 2024
Published online: Aug 27, 2024
Published in print: Nov 1, 2024
Discussion open until: Jan 27, 2025
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.