Predicting Highway Construction Costs: Comparison of the Performance of Random Forest, Neural Network and Support Vector Machine Models

Document Type : Regular Article

Authors

1 Assistant Professor, Department of Construction Technology and Management, School of Civil Engineering and Architecture, Adama Science and Technology University, Adama, Ethiopia

2 Assistant Professor, Department of Construction Technology and Management, College of Engineering and Technology, Wollega University, Wollega, Ethiopia

Abstract

Inaccurate cost estimates have substantial effects on the final cost of construction projects and erode profits. Cost estimation at conceptual phase is a challenge as inadequate information is available. For this purpose, approaches for cost estimation have been explored thoroughly, however they are not employed extensively in practice. The main goal of this paper is to comparing the performance of various models in predicting the cost of construction projects at early conceptual phase in the project development. In this study, on the basis of the actual project data, three modeling algorithms such as random forest, support vector machine and artificial neural networks are used to forecast the construction cost of Ethiopian highway projects. The three models were then compared based on the outcomes of prediction and root mean square error. The findings revealed that random forest outperforms neural network and support vector machine in realizing better prediction accuracy. Based on root mean square error, the random forest cost model provides 18.8% and 23.4% more accurate result than neural network and support vector machine models respectively. It is anticipated that a more reliable cost estimation model could be designed in the early project phases by using a random forest regression technique in the development of a highway construction cost estimation model. In conclusion, the practitioners in the highway construction industry can make sound financial decisions at the early phases of the project development in Ethiopia.

Highlights

Google Scholar

Keywords

Main Subjects


[1]     Bayram S. Duration prediction models for construction projects: In terms of cost or physical characteristics? KSCE J Civ Eng 2017;21:2049–60. doi:10.1007/s12205-016-0691-2.
[2]     Magdum SK, Adamuthe AC. Construction Cost Prediction Using Neural Networks. ICTACT J Soft Comput 2018;8:1549–56. doi:10.21917/ijsc.2017.0216.
[3]     Kim S, Shim JH. Combining case-based reasoning with genetic algorithm optimization for preliminary cost estimation in construction industry. Can J Civ Eng 2014;41:65–73. doi:dx.doi.org/10.1139/cjce-2013-0223.
[4]     Arage SS, Dharwadkar N V. Cost Estimation of Civil Construction Projects using Machine Learning Paradigm. Int Conf I-SMAC (IoT Soc Mobile, Anal Cloud) (I-SMAC 2017), 2017, p. 594–9.
[5]     Ma Z, Liu Z, Wei Z. Formalized Representation of Specifications for Construction Cost Estimation by Using Ontology. Comput Civ Infrastruct Eng 2016;31:4–17. doi:10.1111/mice.12175.
[6]     Bouras CB-T. Regression models to house price prediction. 2018.
[7]     Chau AD, Moynihan GP, Vereen S. Design of a Conceptual Cost Estimation Decision Support System for Public University Construction. Constr Res Congr 2018, Reston, VA: American Society of Civil Engineers; 2018, p. 629–39. doi:10.1061/9780784481295.063.
[8]     Mayer M, Bourassa SC, Hoesli M, Scognamiglio D. Estimation and updating methods for hedonic valuation. J Eur Real Estate Res 2019;12:134–50. doi:10.1108/JERER-08-2018-0035.
[9]     Matel E, Vahdatikhaki F, Hosseinyalamdary S, Evers T, Voordijk H. An artificial neural network approach for cost estimation of engineering services. Int J Constr Manag 2019;0:1–14. doi:10.1080/15623599.2019.1692400.
[10]    Cao Y, Ashuri B, Baek M. Prediction of Unit Price Bids of Resurfacing Highway Projects through Ensemble Machine Learning. J Comput Civ Eng 2018;32:04018043. doi:10.1061/(ASCE)CP.1943-5487.0000788.
[11]    Poh CQX, Ubeynarayana CU, Goh YM. Safety leading indicators for construction sites: A machine learning approach. Autom Constr 2018;93:375–86. doi:10.1016/j.autcon.2018.03.022.
[12]    Golizadeh H, Banihashemi S, Sadeghifam AN, Preece C. Automated estimation of completion time for dam projects. Int J Constr Manag 2017;17:197–209. doi:10.1080/15623599.2016.1192249.
[13]    Rafiei MH, Adeli H. Novel Machine-Learning Model for Estimating Construction Costs Considering Economic Variables and Indexes. J Constr Eng Manag 2018;144:04018106. doi:10.1061/(ASCE)CO.1943-7862.0001570.
[14]    Kang K, Ryu H. Predicting types of occupational accidents at construction sites in Korea using random forest model. Saf Sci 2019;120:226–36. doi:10.1016/j.ssci.2019.06.034.
[15]    Dursun O, Stoy C. Conceptual estimation of construction costs using the multistep ahead approach. J Constr Eng Manag 2016;142:1–10. doi:10.1061/(ASCE)CO.1943-7862.0001150.
[16]    Petruseva S, Sherrod P, Pancovska VZ, Petrovski A. Predicting Bidding Price in Construction using Support Vector Machine. TEM J J 2016;5:143–51. doi:10.18421/TEM52-04.
[17]    Yousefi V, Yakhchali SH, Khanzadi M, Mehrabanfar E, Šaparauskas J. Proposing a neural network model to predict time and cost claims in construction projects. J Civ Eng Manag 2016;22:967–78. doi:10.3846/13923730.2016.1205510.
[18]    Petruseva S, Zileska-pancovska V, Vahida Ž, Vejzović AB-. Construction Costs Forecasting : Comparison of the Accuracy of Linear Regression and Support Vector Machine Models. Tech Gaz 2017;24:1431–8.
[19]    Peško I, Mučenski V, Šešlija M, Radović N, Vujkov A, Bibić D, et al. Estimation of costs and durations of construction of urban roads using ANN and SVM. Complexity 2017;2017:1–13. doi:10.1155/2017/2450370.
[20]    Shin SW. Construction Safety and Health Management Cost Prediction Model using Support Vector Machine. J Korean Soc Saf 2017;32:115–20. doi:https://doi.org/10.14346/JKOSOS.2017.32.1.115.
[21]    Neloy AA, Haque HMS, Ul Islam MM. Ensemble Learning Based Rental Apartment Price Prediction Model by Categorical Features Factoring. Proc 2019 11th Int Conf Mach Learn Comput - ICMLC ’19, New York, New York, USA, China: ACM Press; 2019, p. 350–6. doi:10.1145/3318299.3318377.
[22]    Angamuthu Chinnathambi R, Mukherjee A, Campion M, Salehfar H, Hansen T, Lin J, et al. A Multi-Stage Price Forecasting Model for Day-Ahead Electricity Markets. Forecasting 2018;1:26–46. doi:10.3390/forecast1010003.
[23]    BaniMustafa A. Predicting Software Effort Estimation Using Machine Learning Techniques. 2018 8th Int Conf Comput Sci Inf Technol, IEEE; 2018, p. 249–56. doi:10.1109/CSIT.2018.8486222.
[24]    Torres-Barrán A, Alonso Á, Dorronsoro JR. Regression tree ensembles for wind energy and solar radiation prediction. Neurocomputing 2019;326–327:151–60. doi:10.1016/j.neucom.2017.05.104.
[25]    Alaka HA. 'Big data analytics’ for construction firms insolvency prediction models. The University of the West of England, 2017.
[26]    Bai S, Li M, Kong R, Han S, Li H, Qin L. Data mining approach to construction productivity prediction for cutter suction dredgers. Autom Constr 2019;105:102833. doi:10.1016/j.autcon.2019.102833.
[27]    Shinde N, Gawande K. Valuation of House Prices Using Predictive Techniques. 2018.
[28]    Lu S, Li Z, Qin Z, Yang X, Goh RSM. A hybrid regression technique for house prices prediction. IEEE Int Conf Ind Eng Eng Manag, 2018. doi:10.1109/IEEM.2017.8289904.