Comparison of Various Machine Learning Models for Estimating Construction Projects Sales Valuation Using Economic Variables and Indices

Document Type : Regular Article

Author

Associate Professor, Civil Engineering Department, Faculty of Engineering Technology Al-Balqa Applied University, 11134 Amman, Jordan

Abstract

The capability of various machine learning techniques in predicting construction project profit in residential buildings using a combination of economic variables and indices (EV&Is) and physical and financial variables (P&F) as input variables remain uncertain. Although recent studies have primarily focused on identifying the factors influencing the sales of construction projects due to their significant short-term impact on a country's economy, the prediction of these parameters is crucial for ensuring project sustainability. While techniques such as regression and artificial neural networks have been utilized to estimate construction project sales, limited research has been conducted in this area. The application of machine learning techniques presents several advantages over conventional methods, including reductions in cost, time, and effort. Therefore, this study aims to predict the sales valuation of construction projects using various machine learning approaches, incorporating different EV&Is and P&F as input features for these models and subsequently generating the sales valuation as the output. This research will undertake a comparative analysis to investigate the efficiency of the different machine learning models, identifying the most effective approach for estimating the sales valuation of construction projects. By leveraging machine learning techniques, it is anticipated that the accuracy of sales valuation predictions will be enhanced, ultimately resulting in more sustainable and successful construction projects. In general, the findings of this research reveal that the extremely randomized trees model delivers the best performance, while the decision tree model exhibits the least satisfactory performance in predicting the sales valuation of construction projects.

Highlights

  • A prediction strategy for construction project sales valuation using machine learning models and various economic variables and indices is discussed.
  • A comparison of the efficiency of different machine learning models to determine the most effective approach for estimating construction project sales valuation is provided.
  • The results indicate the advantages of using machine learning techniques in construction sales prediction, such as cost, time, and effort reduction.

Keywords

Main Subjects

References

[1]     Peter NJ, Okagbue HI, Obasi EC, Akinola A. Review on the Application of Artificial Neural Networks in Real Estate Valuation. Int J Adv Trends Comput Sci Eng 2020;9:2918–25. https://doi.org/10.30534/ijatcse/2020/66932020.
[2]     Alfaro-Navarro J-L, Cano EL, Alfaro-Cortés E, García N, Gámez M, Larraz B. A Fully Automated Adjustment of Ensemble Methods in Machine Learning for Modeling Complex Real Estate Systems. Complexity 2020;2020:1–12. https://doi.org/10.1155/2020/5287263.
[3]     Chiu S-M, Chen Y-C, Lee C. Estate price prediction system based on temporal and spatial features and lightweight deep learning model. Appl Intell 2022;52:808–34. https://doi.org/10.1007/s10489-021-02472-6.
[4]     Peter NJ, Fateye OB, Oloke CO, Iyanda P. Changing urban land use and neighbourhood quality: evidence from Federal Capital Territory (FCT), Abuja, Nigeria. Int J Civ Eng Technol 2018;9:23–36.
[5]     Pinter G, Mosavi A, Felde I. Artificial Intelligence for Modeling Real Estate Price Using Call Detail Records and Hybrid Machine Learning Approach. Entropy 2020;22:1421. https://doi.org/10.3390/e22121421.
[6]     Frew J, Jud G. Estimating the Value of Apartment Buildings. J Real Estate Res 2003;25:77–86. https://doi.org/10.1080/10835547.2003.12091101.
[7]     Limsombunchao V. House price prediction: hedonic price model vs. artificial neural network 2004.
[8]     Ayuthaya NP na, Swierczek FW. Factors influencing variation in value and investors confidence. IOSR J Bus Manag 2014;16:41–51.
[9]     Skitmore M, Irons J, Armitage L. Valuation accuracy and variation: a meta analysis. Proc. from PRRES Conf. 2007, Pacific Rim Real Estate Society; 2007, p. 1–19.
[10]   Tchuente D, Nyawa S. Real estate price estimation in French cities using geocoding and machine learning. Ann Oper Res 2022;308:571–608. https://doi.org/10.1007/s10479-021-03932-5.
[11]   Durodola OD, Oluwatobi AO, Oni AA, Peter NJ. Factors Contributing to the Valuation of Arts and Artifacts in Ogun State, Nigeria. Int J Civ Eng Technol 2019;10:2224–31.
[12]   Calhoun CA. Property valuation models and house price indexes for the provinces of Thailand: 1992-2000. Hous Financ Int 2003;17:31–41.
[13]   Ćetković J, Lakić S, Lazarevska M, Žarković M, Vujošević S, Cvijović J, et al. Assessment of the Real Estate Market Value in the European Market by Artificial Neural Networks Application. Complexity 2018;2018:1–10. https://doi.org/10.1155/2018/1472957.
[14]   Fan G-Z, Ong SE, Koh HC. Determinants of house price: A decision tree approach. Urban Stud 2006;43:2301–15.
[15]   Gao L, Guo Z, Zhang H, Xu X, Shen HT. Video Captioning With Attention-Based LSTM and Semantic Consistency. IEEE Trans Multimed 2017;19:2045–55. https://doi.org/10.1109/TMM.2017.2729019.
[16]   Demetriou D. A spatially based artificial neural network mass valuation model for land consolidation. Environ Plan B Urban Anal City Sci 2017;44:864–83. https://doi.org/10.1177/0265813516652115.
[17]   Park B, Bae JK. Using machine learning algorithms for housing price prediction: The case of Fairfax County, Virginia housing data. Expert Syst Appl 2015;42:2928–34. https://doi.org/10.1016/j.eswa.2014.11.040.
[18]   Gribniak V, Mang HA, Kupliauskas R, Kaklauskas G, Juozapaitis A. Stochastic Tension-Stiffening Approach for the Solution of Serviceability Problems in Reinforced Concrete: Exploration of Predictive Capacity. Comput Civ Infrastruct Eng 2016;31:416–31. https://doi.org/10.1111/mice.12183.
[19]   El Hajj B, Schoefs F, Castanier B, Yeung T. A Condition-Based Deterioration Model for the Stochastic Dependency of Corrosion Rate and Crack Propagation in Corroded Concrete Structures. Comput Civ Infrastruct Eng 2017;32:18–33. https://doi.org/10.1111/mice.12208.
[20]   Rafiei MH, Adeli H. A Novel Machine Learning Model for Estimation of Sale Prices of Real Estate Units. J Constr Eng Manag 2016;142. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001047.
[21]   Kim G-H, Yoon J-E, An S-H, Cho H-H, Kang K-I. Neural network model incorporating a genetic algorithm in estimating construction costs. Build Environ 2004;39:1333–40. https://doi.org/10.1016/j.buildenv.2004.03.009.
[22]   Brnabic A, Hess LM. Systematic literature review of machine learning methods used in the analysis of real-world data for patient-provider decision making. BMC Med Inform Decis Mak 2021;21:1–19.
[23]   Manogaran G, Lopez D. Health data analytics using scalable logistic regression with stochastic gradient descent. Int J Adv Intell Paradig 2018;10:118–32.
[24]   Chakraborty D, Elhegazy H, Elzarka H, Gutierrez L. A novel construction cost prediction model using hybrid natural and light gradient boosting. Adv Eng Informatics 2020;46:101201. https://doi.org/10.1016/j.aei.2020.101201.
[25]   Raghavendra. N S, Deka PC. Support vector machine applications in the field of hydrology: A review. Appl Soft Comput 2014;19:372–86. https://doi.org/10.1016/j.asoc.2014.02.002.
[26]   Estimation of Bank Profitability Using Vector Error Correction Model and Support Vector Regression. Econ Altern 2022;28:157–70. https://doi.org/10.37075/EA.2022.2.01.
[27]   Schetinin V, Fieldsend JE, Partridge D, Coats TJ, Krzanowski WJ, Everson RM, et al. Confident interpretation of Bayesian decision tree ensembles for clinical applications. IEEE Trans Inf Technol Biomed 2007;11:312–9.
[28]   Höppner S, Stripling E, Baesens B, Broucke S vanden, Verdonck T. Profit driven decision trees for churn prediction. Eur J Oper Res 2020;284:920–33. https://doi.org/10.1016/j.ejor.2018.11.072.
[29]   Khaidem L, Saha S, Dey SR. Predicting the direction of stock market prices using random forest. arXiv 2016. ArXiv Prepr ArXiv160500003 n.d.
[30]   Zhu J-M, Geng Y-G, Li W-B, Li X, He Q-Z. Fuzzy decision-making analysis of quantitative stock selection in VR industry based on random forest model. J Funct Spaces 2022;2022:1–12.
[31]   Shang K, Yao Y, Li Y, Yang J, Jia K, Zhang X, et al. Fusion of Five Satellite-Derived Products Using Extremely Randomized Trees to Estimate Terrestrial Latent Heat Flux over Europe. Remote Sens 2020;12:687. https://doi.org/10.3390/rs12040687.
[32]   Egwim CN, Alaka H, Toriola-Coker LO, Balogun H, Sunmola F. Applied artificial intelligence for predicting construction projects delay. Mach Learn with Appl 2021;6:100166. https://doi.org/10.1016/j.mlwa.2021.100166.
[33]   Tsiapoki S, Bahrami O, Häckell MW, Lynch JP, Rolfes R. Combination of damage feature decisions with adaptive boosting for improving the detection performance of a structural health monitoring framework: Validation on an operating wind turbine. Struct Heal Monit 2021;20:637–60. https://doi.org/10.1177/1475921720909379.
[34]   Ding W, Zhao X, Meng W, Wang H. Smart Evaluation of Sustainability of Photovoltaic Projects in the Context of Carbon Neutrality Target. Sustainability 2022;14:14925. https://doi.org/10.3390/su142214925.
[35]   Guelman L. Gradient boosting trees for auto insurance loss cost modeling and prediction. Expert Syst Appl 2012;39:3659–67. https://doi.org/10.1016/j.eswa.2011.09.058.
[36]   Xiao H, Liu Y, Du D, Lu Z. An Approach for Predicting the Costs of Forwarding Contracts using Gradient Boosting. 2022 17th Conf. Comput. Sci. Intell. Syst., IEEE; 2022, p. 451–4.
[37]   Marvin G, Grbčić L, Družeta S, Kranjčević L. Water distribution network leak localization with histogram-based gradient boosting. J Hydroinformatics 2023. https://doi.org/10.2166/hydro.2023.102.
[38]   Tamim Kashifi M, Ahmad I. Efficient Histogram-Based Gradient Boosting Approach for Accident Severity Prediction With Multisource Data. Transp Res Rec J Transp Res Board 2022;2676:236–58. https://doi.org/10.1177/03611981221074370.
[39]   Chang Y-C, Chang K-H, Wu G-J. Application of eXtreme gradient boosting trees in the construction of credit risk assessment models for financial institutions. Appl Soft Comput 2018;73:914–20. https://doi.org/10.1016/j.asoc.2018.09.029.
[40]   Hou Y, Qin C. Contribution Analysis of Factors Affecting the Growth of Chinese Construction Enterprises Based on the XGBOOST Algorithm. Highlights Business, Econ Manag 2023;5:681–92. https://doi.org/10.54097/hbem.v5i.5258.
[41]   Shi D, Zhang H, Guan J, Zurada J, Chen Z, Li X. Deep Learning in Predicting Real Estate Property Prices: A Comparative Study 2023.
[42]   Renaud O, Victoria-Feser M-P. A robust coefficient of determination for regression. J Stat Plan Inference 2010;140:1852–62. https://doi.org/10.1016/j.jspi.2010.01.008.

Files

History

  • Receive Date: 02 October 2022
  • Revise Date: 25 April 2023
  • Accept Date: 19 May 2023

Share

How to cite

Statistics