Predicting Safety Accident Costs in Construction Projects Using Ensemble Data-Driven Models
Publication: Journal of Construction Engineering and Management
Volume 150, Issue 7
Abstract
The construction industry suffers from frequent and expensive safety accidents, significantly affecting construction project performance. Numerous data-driven classification models have been developed to categorize construction accident outcomes. While critical influencing factors provide insights for safety prevention, existing models have given less attention to the cost of accidents—an important indicator influencing management decisions. This study aims to develop accident cost prediction models that examine crucial precursors of safety accidents, offering guidance for construction safety prevention from a financial perspective. This study collected 1,606 accident reports from the Chinese construction industry between 2005 and 2022 to address this gap. Three ensemble data-driven methods, namely random forest, extreme gradient boosting regressor (XGBoost), and natural gradient boosting regressor (NGBoost) were employed to develop accident cost prediction models. Based on the performance comparison, the random forest regression model for accident cost was determined to be the best prediction model. To extract the critical attributes affecting safety accident costs, this study utilized shapely additive explanations (SHAP) value to analyze the sensitivity and influence of input variables of data-driven models. The findings showed that collapse has the greatest impact on accident costs, as indicated by the highest mean SHAP value, followed by falling from height. Furthermore, factors such as year, safety supervision, drawing, and construction plan are noteworthy in affecting accident cost prediction. Safety department, protection, and work conditions hold a slightly higher degree of influence compared to contracting arrangement, safety culture, safety supervision, training and examination, and mechanical equipment on the model output. This study provides a dimension that might be overlooked in the investigation of safety accidents in the construction industry and the insights provided by findings will contribute to the development of targeted safety accident prevention strategies.
Get full access to this article
View all available purchase options and get full access to this article.
Acknowledgments
This work was supported by the Key Project of National Social Science Foundation of China (21AGL033); Major Project of Late-stage Funding for Philosophy and Social Science Research of the Ministry of Education (22JHQ022); Major Project of Philosophy and Social Science Planning of Sichuan Province (SC22ZDYC05); Special Funds for Basic Research Operating Expenses of the Central Universities (No. 2022CDJSKPT25); and Chongqing Social Science Planning Key Project (No. 2022ZTZD06). Moreover, this work was supported by the China Scholarship Council (No. 202206050076). The authors also acknowledge the contributions of the members of the ASCII Lab at Monash University for critiquing the manuscript and providing constructive feedback.
References
Alkaissy, M., M. Arashpour, E. M. Golafshani, M. R. Hosseini, S. Khanmohammadi, Y. Bai, and H. Feng. 2023. “Enhancing construction safety: Machine learning-based classification of injury types.” Saf. Sci. 162 (Jun): 106102. https://doi.org/10.1016/j.ssci.2023.106102.
Alkaissy, M., M. Arashpour, R. Wakefield, R. Hosseini, and P. Gill. 2022. “The cost burden of safety risk incidents on construction: A probabilistic quantification method.” Risk Anal. 42 (10): 2312–2326. https://doi.org/10.1111/risa.13865.
Allison, R. W., C. K. H. Hon, and B. Xia. 2019. “Construction accidents in Australia: Evaluating the true costs.” Saf. Sci. 120 (Dec): 886–896. https://doi.org/10.1016/j.ssci.2019.07.037.
Ayhan, B. U., and O. B. Tokdemir. 2020. “Accident analysis for construction safety using latent class clustering and artificial neural networks.” J. Constr. Eng. Manage. 146 (3): 04019114. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001762.
Baker, H., M. R. Hallowell, and A. J. P. Tixier. 2020. “AI-based prediction of independent construction safety outcomes from universal attributes.” Autom. Constr. 118 (Oct): 103146. https://doi.org/10.1016/j.autcon.2020.103146.
Chakraborty, D., H. Elhegazy, H. Elzarka, and L. Gutierrez. 2020. “A novel construction cost prediction model using hybrid natural and light gradient boosting.” Adv. Eng. Inf. 46 (Oct): 101201. https://doi.org/10.1016/j.aei.2020.101201.
Chen, T., and C. Guestrin. 2016. “XGBoost: A scalable tree boosting system.” In Proc., 22nd ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, 785–794. San Francisco: Association for Computing Machinery. https://doi.org/10.1145/2939672.2939785.
Choi, J., B. Gu, S. Chin, and J.-S. Lee. 2020. “Machine learning predictive model based on national data for fatal accidents of construction workers.” Autom. Constr. 110 (Feb): 102974. https://doi.org/10.1016/j.autcon.2019.102974.
Dong, W., Y. Huang, B. Lehane, and G. Ma. 2020. “XGBoost algorithm-based prediction of concrete electrical resistivity for structural health monitoring.” Autom. Constr. 114 (Jun): 103155. https://doi.org/10.1016/j.autcon.2020.103155.
Duan, T., A. Avati, D. Y. Ding, S. Basu, A. Y. Ng, and A. Schuler. 2019. “NGBoost: Natural gradient boosting for probabilistic prediction.” Preprint, submitted October 8, 2019. https://arxiv.org/abs/1910.03225.
Eurostat. 2020. “Accidents at work statistics.” Accessed December 5, 2022. http://ec.europa.eu/eurostat/statistics-explained/index.php/Accidents_at_work_statistics.
Gavious, A., S. Mizrahi, Y. Shani, and Y. Minchuk. 2009. “The costs of industrial accidents for the organization: Developing methods and tools for evaluation and cost–benefit analysis of investment in safety.” J. Loss Prevent. Proc. 22 (4): 434–438. https://doi.org/10.1016/j.jlp.2009.02.008.
Ge, S., W. Gao, S. Cui, X. Chen, and S. Wang. 2022. “Safety prediction of shield tunnel construction using deep belief network and whale optimization algorithm.” Autom. Constr. 142 (Oct): 104488. https://doi.org/10.1016/j.autcon.2022.104488.
Goh, Y. M., and M. J. Askar Ali. 2016. “A hybrid simulation approach for integrating safety behavior into construction planning: An earthmoving case study.” Accid. Anal. Prev. 93 (Aug): 310–318. https://doi.org/10.1016/j.aap.2015.09.015.
Guo, J., P. Xiang, X. Wang, and Y. Lee. 2022. “Predicting and managing megaproject gray rhino risks with IF-ANP and DEMATEL based on panel data.” Expert Syst. Appl. 208 (Dec): 118243. https://doi.org/10.1016/j.eswa.2022.118243.
Gurcanli, G. E., S. Bilir, and M. Sevim. 2015. “Activity based risk assessment and safety cost estimation for residential building construction projects.” Saf. Sci. 80 (Dec): 1–12. https://doi.org/10.1016/j.ssci.2015.07.002.
He, S., L. Su, H. Fan, and R. Ren. 2019. “Methane explosion accidents of tunnels in SW China.” Geomatics Nat. Hazards Risk 10 (Jan): 667–677. https://doi.org/10.1080/19475705.2018.1541826.
Heinrich, H. W. 1941. Industrial accident prevention. A scientific approach. New York: McGraw-Hill.
HSE (Health and Safety Executive). 2020. “Construction statistics in Great Britain.” Accessed January 20, 2023. https://www.hse.gov.uk/statistics/overall/hssh1920.pdf.
ILO (International Labour Organization). 2014. Safety and health in the construction sector-overcoming the challenges. Geneva: ILO.
Jabbari, M., and R. Ghorbani. 2016. “Developing techniques for cause-responsibility analysis of occupational accidents.” Accid. Anal. Prev. 96 (Nov): 101–107. https://doi.org/10.1016/j.aap.2016.07.039.
Kang, K., and H. Ryu. 2019. “Predicting types of occupational accidents at construction sites in Korea using random forest model.” Saf. Sci. 120 (Dec): 226–236. https://doi.org/10.1016/j.ssci.2019.06.034.
Kang, K.-S., C. Koo, and H.-G. Ryu. 2022. “An interpretable machine learning approach for evaluating the feature importance affecting lost workdays at construction sites.” J. Build. Eng. 53 (Aug): 104534. https://doi.org/10.1016/j.jobe.2022.104534.
Khanmohammadi, S., M. Arashpour, E. M. Golafshani, M. G. Cruz, A. Rajabifard, and Y. Bai. 2022. “Prediction of wildfire rate of spread in grasslands using machine learning methods.” Environ. Modell. Software 156 (Oct): 105507. https://doi.org/10.1016/j.envsoft.2022.105507.
Khodakarami, V., and A. Abdi. 2014. “Project cost risk analysis: A Bayesian networks approach for modeling dependencies between cost items.” Int. J. Project Manage. 32 (7): 1233–1245. https://doi.org/10.1016/j.ijproman.2014.01.001.
Kim, S., S. Chang, and D. Castro-Lacouture. 2020. “Dynamic modeling for analyzing impacts of skilled labor shortage on construction project management.” J. Manage. Eng. 36 (1): 04019035. https://doi.org/10.1061/(asce)me.1943-5479.0000720.
Koc, K., Ö. Ekmekcioğlu, and A. P. Gurgun. 2021. “Integrating feature engineering, genetic algorithm and tree-based machine learning methods to predict the post-accident disability status of construction workers.” Autom. Constr. 131 (Nov): 103896. https://doi.org/10.1016/j.autcon.2021.103896.
Koc, K., Ö. Ekmekcioğlu, and A. P. Gurgun. 2022a. “Accident prediction in construction using hybrid wavelet-machine learning.” Autom. Constr. 133 (Jan): 103987. https://doi.org/10.1016/j.autcon.2021.103987.
Koc, K., Ö. Ekmekcioğlu, and A. P. Gurgun. 2022b. “Prediction of construction accident outcomes based on an imbalanced dataset through integrated resampling techniques and machine learning methods.” Eng. Constr. Archit. Manage. 30 (9): 4486–4517. https://doi.org/10.1108/ecam-04-2022-0305.
Koc, K., Ö. Ekmekcioğlu, and A. P. Gurgun. 2023. “Developing a national data-driven construction safety management framework with interpretable fatal accident prediction.” J. Constr. Eng. Manage. 149 (4): 04023010. https://doi.org/10.1061/jcemd4.Coeng-12848.
Koc, K., and A. P. Gurgun. 2022. “Scenario-based automated data preprocessing to predict severity of construction accidents.” Autom. Constr. 140 (Aug): 104351. https://doi.org/10.1016/j.autcon.2022.104351.
Lander, F., K. J. Nielsen, and J. Lauritsen. 2016. “Work injury trends during the last three decades in the construction industry.” Saf. Sci. 85 (Jun): 60–66. https://doi.org/10.1016/j.ssci.2015.10.013.
Laufer, A. 1987. “Construction accident cost and management safety motivation.” J. Occup. Accid. 8 (4): 295–315. https://doi.org/10.1016/0376-6349(87)90005-8.
Liu, J., H. Luo, and H. Liu. 2022. “Deep learning-based data analytics for safety in construction.” Autom. Constr. 140 (Aug): 104302. https://doi.org/10.1016/j.autcon.2022.104302.
López-Alonso, M., M. P. Ibarrondo-Dávila, M. C. Rubio-Gámez, and T. G. Munoz. 2013. “The impact of health and safety investment on construction company costs.” Saf. Sci. 60 (Dec): 151–159. https://doi.org/10.1016/j.ssci.2013.06.013.
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. Red Hook, NY: Curran Associates. https://doi.org/10.5555/3295222.3295230.
Luo, X., X. Li, Y. M. Goh, X. Song, and Q. Liu. 2023. “Application of machine learning technology for occupational accident severity prediction in the case of construction collapse accidents.” Saf. Sci. 163 (Jul): 106138. https://doi.org/10.1016/j.ssci.2023.106138.
Mistikoglu, G., I. H. Gerek, E. Erdis, P. E. Mumtaz Usmen, H. Cakan, and E. E. Kazan. 2015. “Decision tree analysis of construction fall accidents involving roofers.” Expert Syst. Appl. 42 (4): 2256–2263. https://doi.org/10.1016/j.eswa.2014.10.009.
MOHURD (Ministry of Housing and Urban-Rural Development). 2020. “Notification of production safety accidents of housing municipal works.” Accessed May 21, 2021. https://www.mohurd.gov.cn/gongkai/zhengce/zhengcefilelib/202210/20221026_768565.html.
Möller, A., V. Ruhlmann-Kleider, C. Leloup, J. Neveu, N. Palanque-Delabrouille, J. Rich, R. Carlberg, C. Lidman, and C. Pritchet. 2016. “Photometric classification of type Ia supernovae in the SuperNova Legacy Survey with supervised learning.” J. Cosmol. Astropart. Phys. 2016 (12): 008. https://doi.org/10.1088/1475-7516/2016/12/008.
Nazeer Ahamed, M. F., and M. Mariappan. 2023. “A study to determine human-related errors at the level of top management, safety supervisors & workers during the implementation of safety practices in the construction industry.” Saf. Sci. 162 (Jun): 106081. https://doi.org/10.1016/j.ssci.2023.106081.
Poh, C. Q. X., C. U. Ubeynarayana, and Y. M. Goh. 2018. “Safety leading indicators for construction sites: A machine learning approach.” Autom. Constr. 93 (Sep): 375–386. https://doi.org/10.1016/j.autcon.2018.03.022.
Salarian, A. A., H. Etemadfard, A. Rahimzadegan, and M. Ghalehnovi. 2023. “Investigating the role of clustering in construction-accident severity prediction using a heterogeneous and imbalanced data set.” J. Constr. Eng. Manage. 149 (2): 04022161. https://doi.org/10.1061/(ASCE)CO.1943-7862.0002406.
Shehu, Z., I. R. Endut, A. Akintoye, and G. D. Holt. 2014. “Cost overrun in the Malaysian construction industry projects: A deeper insight.” Int. J. Project Manage. 32 (8): 1471–1480. https://doi.org/10.1016/j.ijproman.2014.04.004.
Tang, S. L., K. C. Ying, W. Y. Chan, and Y. L. Chan. 2004. “Impact of social safety investments on social costs of construction accidents.” Construct. Manage. Econ. 22 (9): 937–946. https://doi.org/10.1080/0144619042000226315.
Teo, E. A.-L., and Y. Feng. 2011. “Costs of construction accidents to Singapore contractors.” Int. J. Constr. Manage. 11 (3): 79–92. https://doi.org/10.1080/15623599.2011.10773174.
Tixier, A. J. P., M. R. Hallowell, B. Rajagopalan, and D. Bowman. 2016. “Application of machine learning to construction injury prediction.” Autom. Constr. 69 (Sep): 102–114. https://doi.org/10.1016/j.autcon.2016.05.016.
Waehrer, G. M., X. S. Dong, T. Miller, E. Haile, and Y. Men. 2007. “Costs of occupational injuries in construction in the United States.” Accid. Anal. Prev. 39 (6): 1258–1266. https://doi.org/10.1016/j.aap.2007.03.012.
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.
Yılmaz, M., and R. Kanıt. 2018. “A practical tool for estimating compulsory OHS costs of residential building construction projects in Turkey.” Saf. Sci. 101 (Jan): 326–331. https://doi.org/10.1016/j.ssci.2017.09.020.
Zhang, W., S. Zhu, X. Zhang, and T. Zhao. 2020. “Identification of critical causes of construction accidents in China using a model based on system thinking and case analysis.” Saf. Sci. 121 (Jan): 606–618. https://doi.org/10.1016/j.ssci.2019.04.038.
Zhou, Z., S. Liu, and H. Qi. 2022. “Mitigating subway construction collapse risk using Bayesian network modeling.” Autom. Constr. 143 (Nov): 104541. https://doi.org/10.1016/j.autcon.2022.104541.
Zhu, R., X. Hu, J. Hou, and X. Li. 2021. “Application of machine learning techniques for predicting the consequences of construction accidents in China.” Process Saf. Environ. Prot. 145 (Jan): 293–302. https://doi.org/10.1016/j.psep.2020.08.006.
Information & Authors
Information
Published In
Journal of Construction Engineering and Management
Volume 150 • Issue 7 • July 2024
Copyright
© 2024 American Society of Civil Engineers.
History
Received: Aug 18, 2023
Accepted: Jan 24, 2024
Published online: Apr 16, 2024
Published in print: Jul 1, 2024
Discussion open until: Sep 16, 2024
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.