Application of XGBoost in Road Maintenance Cost Prediction
Downloads
Road maintenance costs play a critical role in government budgeting, as they represent a recurring expenditure required to sustain transportation infrastructure performance and traffic safety. Accurate cost prediction enables long-term efficiency by ensuring that maintenance budgets are allocated appropriately. This study aims to develop a predictive model for road maintenance cost using the Extreme Gradient Boosting (XGBoost) algorithm, optimized through iterative training to improve prediction accuracy based on deviations between predicted and actual costs. Model performance was evaluated using Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and the coefficient of determination (R²), all of which indicate a strong model fit and high predictive reliability. The model was developed using simulated and empirical data from 30 road sections with varying characteristics, incorporating key predictors such as road length, cold mix asphalt, asphalt emulsion, diesel fuel, gasoline, water consumption, working area, asphalt removal volume, and labor requirements. The results demonstrate that the proposed XGBoost-based model can effectively estimate maintenance costs and associated resource requirements. The findings provide practical insights for government agencies in planning material usage and workforce allocation for road maintenance activities.
Downloads
[1] Pamuković, J. K., Rogulj, K., Dumanić, D., & Jajac, N. (2021). A sustainable approach for the maintenance of asphalt pavement construction. Sustainability (Switzerland), 13(1), 1–18. doi:10.3390/su13010109.
[2] Mohammadi, A., Igwe, C., Amador-Jimenez, L., & Nasiri, F. (2020). Applying lean construction principles in road maintenance planning and scheduling. International Journal of Construction Management, 1–11. doi:10.1080/15623599.2020.1788758.
[3] Tee, K. F., & Ekpiwhre, E. (2019). Reliability-based preventive maintenance strategies of road junction systems. International Journal of Quality and Reliability Management, 36(5), 752–781. doi:10.1108/IJQRM-01-2018-0018.
[4] Huang, M., Dong, Q., Ni, F., & Wang, L. (2021). LCA and LCCA based multi-objective optimization of pavement maintenance. Journal of Cleaner Production, 283. doi:10.1016/j.jclepro.2020.124583.
[5] Makovska, J. (2020). Method of Evaluation of Road Routine Maintenance Strategies. Economics, Finance and Management Review, 4(4), 106–112. doi:10.36690/2674-5208-2020-4-106.
[6] Huang, L. L., Lin, J. D., Huang, W. H., Kuo, C. H., Chiou, Y. S., & Huang, M. Y. (2024). Developing Pavement Maintenance Strategies and Implementing Management Systems. Infrastructures, 9(7), 101. doi:10.3390/infrastructures9070101.
[7] Mohammadi, N., & Klein-Paste, A. (2025). Simulating winter maintenance efforts: A multiscale geographically weighted regression model. Cold Regions Science and Technology, 236. doi:10.1016/j.coldregions.2025.104512.
[8] Chen, S., Cao, J., Wan, Y., Shi, X., & Huang, W. (2024). Enhancing rutting depth prediction in asphalt pavements: A synergistic approach of extreme gradient boosting and snake optimization. Construction and Building Materials, 421. doi:10.1016/j.conbuildmat.2024.135726.
[9] Giustozzi, F., Crispino, M., & Flintsch, G. (2012). Multi-attribute life cycle assessment of preventive maintenance treatments on road pavements for achieving environmental sustainability. International Journal of Life Cycle Assessment, 17(4), 409–419. doi:10.1007/s11367-011-0375-6.
[10] de Bortoli, A., Féraille, A., & Leurent, F. (2022). Towards Road Sustainability—Part I: Principles and Holistic Assessment Method for Pavement Maintenance Policies. Sustainability (Switzerland), 14(3), 1513. doi:10.3390/su14031513.
[11] Sari, E. M., Setiawan, D., & Putranto, L. S. (2025). Evaluation of road project maintenance costs in Bogor City - West Java. Kompak: Jurnal Ilmiah Komputerisasi Akuntansi, 18(2), 434–445. doi:10.51903/kompak.v18i2.2959.
[12] Milad, A., Ali, A. A., Al-Sulaimi, Z. S., & Al-Kindi, K. M. (2025). Utilizing spatial artificial intelligence to develop pavement performance indices: A case study. Scientific Reports, 15(1), 39603. doi:10.1038/s41598-025-23290-7.
[13] Sarsam, S. I. (2016). Pavement maintenance management system: A review. Trends in Transport Engineering and Applications, 3(2), 19-30.
[14] Bortoli, A. de, Féraille, A., & Leurent, F. (2022). Towards Road Sustainability—Part II: Applied Holistic Assessment and Lessons Learned from French Highway Resurfacing Strategies. Sustainability (Switzerland), 14(12), 7336. doi:10.3390/su14127336.
[15] Zhang, M., Gong, H., Xiao, R., Jiang, X., Ma, Y., & Huang, B. (2023). Life-cycle cost analysis of rehabilitation strategies for asphalt pavements based on probabilistic models. Road Materials and Pavement Design, 24(1), 121–137. doi:10.1080/14680629.2021.2012235.
[16] Golroo, A., Fani, A. H., Naseri, H., & Mirhasani, S. A. (2021). Pavement Maintenance and Rehabilitation Planning Considering Budget Uncertainty. Amirkabir Journal of Civil Engineering, 53(7), 2781–2800. doi:10.22060/ceej.2020.17502.6583.
[17] Simić, N., Ivanišević, N., Nedeljković, Ð., Senić, A., Stojadinović, Z., & Ivanović, M. (2023). Early Highway Construction Cost Estimation: Selection of Key Cost Drivers. Sustainability (Switzerland), 15(6), 5584. doi:10.3390/su15065584.
[18] Erfani, A., & Mansouri, A. (2025). Uncertainty-Aware Pavement Roughness Forecasting Using Adaptive Conformal Prediction. International Journal of Pavement Research and Technology, 1–19. doi:10.1007/s42947-025-00689-z.
[19] Mosavi, A., Ozturk, P., & Chau, K. W. (2018). Flood prediction using machine learning models: Literature review. Water (Switzerland), 10(11), 1536. doi:10.3390/w10111536.
[20] Jafari, M., & Mousavi, E. (2026). A Critical Review of the Data-Driven Cost Estimation Approach in Construction Research. Journal of Construction Engineering and Management, 152(2), 3125013. doi:10.1061/jcemd4.coeng-16840.
[21] Habib, O., Abouhamad, M., & Bayoumi, A. E. M. (2025). Ensemble learning framework for forecasting construction costs. Automation in Construction, 170, 105903. doi:10.1016/j.autcon.2024.105903.
[22] Das, P., Kashem, A., Hasan, I., & Islam, M. (2024). 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(4), 3301–3316. doi:10.1007/s42107-023-00980-z.
[23] Beth Visintine, by A., Gary Hicks, R., Gary Hicks, P. R., Cheng, D., Director, P., Elkins, G. E., & Groeger, J. (2015). Factors Affecting the Performance of Pavement Preservation Treatments. In the 9th International Conference on Managing Pavement Assets (ICMPA9), 1–14.
[24] Qiao, Y., Dawson, A. R., Parry, T., & Flintsch, G. W. (2015). Evaluating the effects of climate change on road maintenance intervention strategies and Life-Cycle Costs. Transportation Research Part D: Transport and Environment, 41, 492–503. doi:10.1016/j.trd.2015.09.019.
[25] Zheng, X., Easa, S. M., Yang, Z., Ji, T., & Jiang, Z. (2019). Life-cycle sustainability assessment of pavement maintenance alternatives: Methodology and case study. Journal of Cleaner Production, 213, 659–672. doi:10.1016/j.jclepro.2018.12.227.
[26] Awaad, S., Mansour, D. M., Mahdi, I., & Abdelrasheed, I. (2024). Impact of material supply chain on the productivity optimization for the construction of roads projects. Scientific Reports, 14(1), 3294. doi:10.1038/s41598-024-53660-6.
[27] Khodabakhshian, A., Puolitaival, T., & Kestle, L. (2023). Deterministic and Probabilistic Risk Management Approaches in Construction Projects: A Systematic Literature Review and Comparative Analysis. Buildings, 13(5), 1312. doi:10.3390/buildings13051312.
[28] Zhai, L., Yan, X., & Liu, G. (2024). Cost Impact Factors and Control Measures of Road and Bridge Projects Based on Linear Regression Model. Informatica, 48(17). doi:10.31449/inf.v48i17.6370.
[29] Petruseva, S., Zileska-Pancovska, V., Žujo, V., & Brkan-Vejzović, A. (2017). Construction costs forecasting: comparison of the accuracy of linear regression and support vector machine models. Tehnicki Vjesnik - Technical Gazette, 24(5), 1431–1438. doi:10.17559/tv-20150116001543.
[30] Al-Mistarehi, B., Shtayat, A., Imam, R., & Abdallah, A. (2025). An Automated Assessment Technique for Pavement Defects Using a Laser Scanner and Deep Machine Learning. Civil Engineering Journal, 11(3), 1088–1105. doi:10.28991/CEJ-2025-011-03-015.
[31] De Figueiredo, B. H., Dos Santos, M., Fávero, L. P. L., Moreira, M. Â. L., & De Araújo Costa, I. P. (2022). Analysis of maintenance activities in Urban Pavement Management Systems based on Decision Tree Algorithm. Procedia Computer Science, 214(C), 712–719. doi:10.1016/j.procs.2022.11.233.
[32] Kaparthi, S., & Bumblauskas, D. (2020). Designing predictive maintenance systems using decision tree-based machine learning techniques. International Journal of Quality and Reliability Management, 37(4), 659–686. doi:10.1108/IJQRM-04-2019-0131.
[33] Gangadhari, R. K., Khanzode, V., & Murthy, S. (2022). Application of rough set theory and machine learning algorithms in predicting accident outcomes in the Indian petroleum industry. Concurrency and Computation: Practice and Experience, 34(26), 7277. doi:10.1002/cpe.7277.
[34] Lin, M.-L., & Huynh, L. L. (2024). Bridging causal explanation and predictive modeling: the role of PLS-SEM. International Journal of Research in Business and Social Science (2147- 4478), 13(10), 197–206. doi:10.20525/ijrbs.v13i10.3888.
[35] Republic of Indonesia. (2022). Law of the Republic of Indonesia Number 2 of 2022 on roads. Republic of Indonesia, Jakarta, Indonesia.
[36] PUPR. (2011). Regulation of the Minister of Public Works on Road Maintenance Procedures. Ministry of Public Works and Housing (PUPR), Jakarta, Indonesia.
[37] PUPR. (2020). Road Maintenance Management Guidelines, Directorate General of Highways. Ministry of Public Works and Housing (PUPR), Jakarta, Indonesia.
[38] Lartey, B., Homaifar, A., Girma, A., Karimoddini, A., & Opoku, D. (2021). XGBoost: A tree-based approach for traffic volume prediction. Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, 1280–1286. doi:10.1109/SMC52423.2021.9658959.
[39] Zhu, J., Yin, Y., Ma, T., & Wang, D. (2025). A novel maintenance decision model for asphalt pavement considering crack causes based on random forest and XGBoost. Construction and Building Materials, 477. doi:10.1016/j.conbuildmat.2025.140610.
- Authors retain all copyrights. It is noticeable that authors will not be forced to sign any copyright transfer agreements.
- This work (including HTML and PDF Files) is licensed under a Creative Commons Attribution 4.0 International License.
