Optimization-Driven Cost Estimation in House Construction: A Predictive Modeling Approach Using Fruit Fly Optimization Algorithm

Yinghong  Shi

doi:10.6180/jase.202606_29(6).0006

Optimization-Driven Cost Estimation in House Construction: A Predictive Modeling Approach Using Fruit Fly Optimization Algorithm

Civil Engineering

Yinghong ShiThis email address is being protected from spambots. You need JavaScript enabled to view it.

Chongqing Vocational and Technical University of Mechatronics, Chongqing 402760, China

Received: May 8, 2025
Accepted: August 24, 2025
Publication Date: October 19, 2025

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202606_29(6).0006

Accurate forecasting of house construction cost is central to good forecasting and resource management. Traditional methods of estimation fall short due to uncertainty in material, labor, and macroeconomic drivers. Machine Learning models are employed for cost estimation in this study using a tabular time-series Irish data sample from January 1975 to August 2017, which contains 512 monthly observations. The data includes the national House Construction Cost Index as the target variable, augmented with engineered temporal variables such as Year and Month_Num to capture long-term and seasonal patterns. After data preprocessing and feature engineering, a range of Machine Learning models such as Random Forest, Gradient Boosting, Light Gradient Boosting Machine, Categorical Boost, Extreme Gradient Boosting, and Elastic Net were utilized. To enhance predictive accuracy, Fruit Fly Optimization Algorithm was used for optimizing hyperparameters of models. Among the trained models, Fruit Fly Optimization Algorithm-optimized Extreme Gradient Boosting performed the best with Coefficient of Determination of 0.9999, Mean Absolute Error of 0.3570, Root Mean Squared Error of 0.5946, and Symmetrical Mean Absolute Percentage Error of 0.4970 on the test set. Fruit Fly Optimization Algorithm-optimized Extreme Gradient Boosting stability of performance demonstrated strong generalization, with K-Fold errors averaging 1.2676 and ranging between 0.8376 and 1.7159. Shapley Additive Explanations-based sensitivity analysis identified the "Year" feature as the most influential predictor of construction cost, which captures the dominant impact of long-run economic forces such as inflation and policy changes. On the other hand, the "Month" feature was relatively unimportant, suggesting that short-run fluctuation plays less of a role in prediction modeling. This research demonstrates the potential of integrating temporal feature engineering with nature-inspired optimization to improve construction cost forecasting. The technique offers an extremely accurate, fact-based tool to aid in budgeting and strategic financial planning within the building industry.

Keywords: House Construction Cost Prediction; Machine Learning for Cost Estimation; Fruit Fly Optimization Algorithm; Shapley Additive Explanations; Macroeconomic Influence on Construction Costs

[1] R. Chudley, R. Greeno, and K. Kovac. Chudley and Greeno’s Building Construction Handbook. Routledge, 2024. DOI: https: //doi.org/10.1201/9781003392996.
[2] Q. Gao, V. Shi, C. Pettit, and H. Han, (2022) “Property valuation using machine learning algorithms on statistical areas in Greater Sydney, Australia" Land Use Policy 123: 106409. DOI: https: //doi.org/10.1016/j.landusepol.2022.106409.
[3] A. Hammad, S. Abou Rizk, and Y. Mohamed, (2014) “Application of KDD techniques to extract useful knowledge from labor resources data in industrial construction projects" Journal of Management in Engineering 30: 05014011. DOI: https: //doi.org/10.1061/(ASCE)ME.1943-5479.0000280.
[4] J. Liu, X. Zhao, and P. Yan, (2016) “Risk paths in inter national construction projects: Case study from Chinese contractors" Journal of construction engineering and management 142: 05016002. DOI: https: //doi.org/10.1061/(ASCE)CO.1943-7862.0001116.
[5] P. N. Prasetyono, H. S. M. Suryanto, and H. Dani. “Predicting construction cost using regression techniques for residential building”. In: Journal of Physics: Conference Series. 1899. IOP Publishing, 2021, 012120. DOI: https: //doi.org/10.1088/1742-6596/1899/1/012120.
[6] L. O. Ugur, R. Kanit, H. Erdal, E. Namli, H. I. Erdal, U. N. Baykan, and M. Erdal, (2019) “Enhanced predictive models for construction costs: A case study of Turkish mass housing sector" Computational Economics 53: 1403–1419. DOI: https: //doi.org/10.1007/s10614-018-9814-9.
[7] A. Ashraf, M. Rady, and S. Y. Mahfouz, (2024) “Price prediction of residential buildings using random forest and artificial neural network" HBRC Journal 20: 23–41. DOI: https: //doi.org/10.1080/16874048.2023.2296036.
[8] A.GurmuandM.P.Miri, (2025) “Machine learning regression for estimating the cost range of building projects" Construction Innovation 25: 577–593. DOI: https: //doi.org/10.1108/CI-08-2022-0197.
[9] S. T. Hashemi, O. M. Ebadati, and H. Kaur, (2020) “Cost estimation and prediction in construction projects: A systematic review on machine learning techniques" SN Applied Sciences 2: 1703. DOI: https: //doi.org/10.1007/s42452-020-03497-1.
[10] H. H. Elmousalami, (2019) “Comparison of Artificial Intelligence Techniques for Project Conceptual Cost Pre diction" arXiv preprint arXiv:1909.11637: DOI: https: //doi.org/10.48550/arXiv.1909.11637.
[11] C. Zhan, Y. Liu, Z. Wu, M. Zhao, and T. W. S. Chow, (2023) “A hybrid machine learning framework for forecasting house price" Expert Systems with Applications 233: 120981. DOI: https: //doi.org/10.1016/j.eswa.2023.120981.
[12] H. Zhang, Y. Li, and P. Branco, (2024) “Describe the house and I will tell you the price: House price prediction with textual description data" Natural Language Engineering 30: 661–695. DOI: https: //doi.org/10.1017/S1351324923000360.
[13] M.Günnewig-Mönert and R. C. Lyons, (2024) “Housing prices, costs, and policy: The housing supply equation in Ireland since 1970" Real Estate Economics 52: 1075 1102. DOI: https: //doi.org/10.1111/1540-6229.12491.
[14] G. Biau, (2012) “Analysis of a random forests model" TheJournalofMachineLearningResearch13:1063 1095. .
[15] Z. E. Mrabet, N. Sugunaraj, P. Ranganathan, and S. Abhyankar, (2022) “Random forest regressor-based approach for detecting fault location and duration in power systems" Sensors 22: 458. DOI: http: //dx.doi.org/10.3390/s22020458.
[16] P. Nie, M. Roccotelli, M. P. Fanti, Z. Ming, and Z. Li, (2021) “Prediction of home energy consumption based on gradient boosting regression tree" Energy Reports 7: 1246–1255. DOI: https: //doi.org/10.1016/j.egyr.2021.02.006.
[17] U. Singh, M. Rizwan, M. Alaraj, and I. Alsaidan, (2021) “A machine learning-based gradient boosting regression approach for wind power production forecasting: A step towards smart grid environments" Energies 14: 5196.
[18] T. Toharudin, R. E. Caraka, I. R. Pratiwi, Y. Kim, P. U. Gio, A. D. Sakti, M. Noh, F. A. L. Nugraha, R. S. Pontoh, and T. H. Putri, (2023) “Boosting algorithm to handle unbalanced classification of PM 2.5 concentration levels by observing meteorological parameters in Jakarta-Indonesia using AdaBoost, XGBoost, Cat Boost, and Light GBM" IEEE Access 11: 35680–35696. DOI: https: //doi.org/10.1109/ACCESS.2023.3265019.
[19] J. T. Hancock and T. M. Khoshgoftaar, (2020) “Cat Boost for big data: an interdisciplinary review" Journal of big data 7: 94. DOI: https: //doi.org/10.1186/s40537-020-00369-8.
[20] J. Liang, Y. Bu, K. Tan, J. Pan, Z. Yi, X. Kong, and Z. Fan, (2022) “Estimation of stellar atmospheric parameters with light gradient boosting machine algorithm and principal component analysis" The Astronomical Journal 163: 153. DOI: https: //doi.org/10.3847/1538-3881/ac4d97.
[21] S.Deng, J. Su, Y. Zhu, Y. Yu, and C. Xiao, (2024) “Fore casting carbon price trends based on an interpretable light gradient boosting machine and Bayesian optimization" Expert Systems with Applications 242: 122502. DOI: https: //doi.org/10.1016/j.eswa.2023.122502.
[22] A. S. Al-Jawarneh, M. T. Ismail, and A. M. Awajan, (2021) “Elastic net regression and empirical mode decom position for enhancing the accuracy of the model selection" International Journal of Mathematical, Engineering and Management Sciences 6: 564. DOI: https: //doi.org/10.33889/IJMEMS.2021.6.2.034.
[23] S. I. Altelbany, (2021) “Evaluation of Ridge, Elastic Net and Lasso Regression Methods in Precedence of Multi collinearity Problem: A Simulation Study." Journal of Applied Economics & Business Studies (JAEBS) 5: DOI: https: //doi.org/10.34260/jaebs.517.
[24] P. J. García-Nieto, E. García-Gonzalo, and J. P. Paredes-Sánchez, (2021) “Prediction of the critical temperature of a superconductor by using the WOA/MARS, Ridge, Lasso and Elastic-net machine learning techniques" Neural Computing and Applications 33: 17131 17145. DOI: https: //doi.org/10.1007/s00521-021-06304-z.
[25] M. Amjad, I. Ahmad, M. Ahmad, P. Wróblewski, P. Kami´nski, and U. Amjad, (2022) “Prediction of pile bearing capacity using XG Boost algorithm: modeling and performance evaluation" Applied Sciences 12: 2126. DOI: https: //doi.org/10.3390/app12042126.
[26] A. I. A. Osman, A. N. Ahmed, M. F. Chow, Y. F. Huang, and A. El-Shafie, (2021) “Extreme gradient boosting (Xgboost) model to predict the groundwater levels in Selangor Malaysia" Ain Shams Engineering Journal 12: 1545–1556. DOI: https: //doi.org/10.1016/j.asej.2020.11.011.
[27] W.-T. Pan, (2012) “A new fruit fly optimization algorithm: taking the financial distress model as an example" Knowledge-Based Systems 26: 69–74. DOI: https: //doi.org/10.1016/j.knosys.2011.07.001.
[28] R. Sonia, J. Joseph, D. Kalaiyarasi, N. Kalyani, A. S. G. Gupta, G. Ramkumar, H.S. Almoallim, S. A. Alharbi, andS. S. Raghavan, (2024) “Segmenting and classifying skin lesions using a fruit fly optimization algorithm with a machine learning framework" Automatika: ˇcasopis za automatiku, mjerenje, elektroniku, raˇcunarstvo i komunikacije 65: 217–231. DOI: https: //doi.org/10.1080/00051144.2023.2293515.
[29] D. Chicco, M. J. Warrens, and G. Jurman, (2021) “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation" Peerj computer science 7: e623. DOI: https: //doi.org/10.7717/peerj-cs.623.
[30] P. Dumre, S. Bhattarai, and H. K. Shashikala. “Optimizing linear regression models: A comparative study of error metrics”. In: 2024 4th International Conference on Technological Advancements in Computational Sciences (ICTACS). IEEE, 2024, 1856–1861. DOI: https: //doi.org/10.1109/ICTACS62700.2024.10840719.
[31] T. O. Hodson, (2022) “Root mean square error (RMSE) or mean absolute error (MAE): When to use them or not" Geoscientific Model Development Discussions 2022: 1–10. DOI: https: //doi.org/10.5194/gmd-15-5481-2022.
[32] J. Terven, D. M. Cordova-Esparza, A. Ramirez Pedraza, E. A. Chavez-Urbiola, and J. A. Romero Gonzalez, (2023) “Loss functions and metrics in deep learning" arXiv preprint arXiv:2307.02694: DOI: https: //doi.org/10.48550/arXiv.2307.02694.