FOREIGN EXPERIENCE IN USING ARTIFICIAL NEURAL NETWORK FOR CONSTRUCTION COST PREDICTION

UDC 338.242

  • Holubava Volha Sergeevna – PhD (Economics), Assisstant Professor, the Department of Economics, Construction Organization and Real Estate Management. Belarusian National Technical University (65, Nezavisimosti Ave., 220013, Minsk, Republic of Belarus). E-mail: v.holubava@gmail.com

  • Nhuen Tkhi Tkhu Nhan – PhD student, the Department of Economics, Construction Organization and Real Estate Management. Belarusian National Technical University (65, Nezavisimosti Ave., 220013, Minsk, Republic of Belarus). E-mail: nguyennatalia13@gmail.com

DOI: https://doi.org/10.52065/2520-6877-2023-268-1-3

Keywords: building cost forecasting, artificial neural network, artificial neural network for cost forecasting.

For citation: Holubava V. S., Nhuen T. T. N. Foreign experience in using artificial neural network for construction cost prediction. Proceedings of BSTU, issue 5, Economics and Management, 2023, no. 1 (268), pр. 22–30. DOI: https://doi.org/10.52065/2520-6877-2023-268-1-3.

Abstract

Cost construction forecasting is of great importance for the determining investments needs and assessing the economic efficiency of their use. The accuracy of cost forecasting ensures the stability of cost planning, the reliability of the execution of work contracts, and the rational use of the country’s financial resources. Therefore, in the Republic of Belarus the development and use of new innovative methods for predicting the cost of construction based on artificial neural networks are a relevant and important area of research.

Based on the study of scientific sources the main advantages of artificial neural networks such as information content, resistance to noise in the input parameters, adaptability to environmental changes, reliability and learnability are presented in the paper. The advantages of artificial neural networks have created the basis for their application in predicting the estimated value of real estate and construction costs.

A review of the works of foreign authors confirms that a sample containing up to 100 objects is sufficient to build neural network models for predicting the cost of construction. The error in the cost construction prediction using artificial neural networks is less than 20%. Such accuracy in estimating the cost construction in the early stages of project development is acceptable. In order to predict the cost construction ensuring the accuracy and efficiency of the assessment there is a need to develop artificial neural network models adapted to the economic conditions of the Republic of Belarus.

Download

References

  1. Burova I. V. Use of regression analysis in evaluation of the cost of object of the real estate market. Regional’nyye problemy preobrazovaniya ekonomiki [Regional Problems of Economic Transformation], 2020, no. 2 (112), pp. 39–45 (In Russian).
  2. Yasnitsky V. L. Neural network modeling in the problem of mass assessment of residential real estate in the city of Perm. Fundamental’nyye issledovaniya [Fundamental Research], 2015, no. 3–10, pp. 650–653 (In Russian).
  3. Borovikov V. P. Neyronnye seti. STATISTICA Neural Networks: metodologiya i tekhnologiya sovremennogo analiza dannykh [Neural networks. STATISTICA Neural Networks: Methodology and technologies of modern data analysis]. Moscow, Hotline – Telecom Publ., 2008. 392 p. (In Russian).
  4. Nhuen T. T. N. Neural networks – a new tool for economic analysis of construction enterprises of the Republic of Belarus. Neyronnye seti – novyy instrument ekonomicheskogo analiza stroitel’nykh predpriyatiy respubliki Belarus’ [Economics, organization of construction and real estate management: a collection of materials of the scientific and technical conference]. Minsk, BNTU Publ., 2021. P. 63. (In Russian).
  5. Elhag T. M., Boussabaine A. H. An artificial neural system for cost estimation of construction projects. Avaliable at: https://www.arcom.ac.uk/-docs/proceedings/ar1998-219-226_Elhag_and_Boussabaine.pdf (accessed 13.02.2023).
  6. Günaydın H. M., Doğan S. Z. A neural network approach for early cost estimation of structural systems of buildings. International Journal of Project Management. Available at: https://doi.org/10.1016/j.ijproman.2004.04.002 (accessed 13.02.2023).
  7. 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 cost. Building and Environment, 2004, vol. 39, no. 11, pp. 1333–1340.
  8. Cheng M. Y., Tsai H. C., Sudjono E. Conceptual cost estimates using evolutionary fuzzy hybrid neural network for projects in construction industry. Expert Systems with Applications, 2010, vol. 37, pp. 4224 –4231.
  9. Luu T. V., Phan V. K. Using Matlab to train ANNs in the problem of apartment construction costs. Tap chi khoa hoc: Science magazine. Available at: https://journalofscience.ou.edu.vn/index.php/techvi/article/view/1278 (accessed 13.02.2023). (In Vietnamese).
  10. Arafa M., Alqedra M. Early stage cost estimation of buildings construction projects using artificial neural networks. Journal of Artificial Intelligence, 2011, vol. 4, no. 1, pp. 63–75. DOI: 10.3923/jai.2011.63.75.
  11. ElSawy H., Hosny H., Razek M. A. Neural network model for construction projects site overhead cost estimating in Egypt. International Journal of Computer Science Issues, 2011, vol. 8, issue 3, pp. 273– 283.
  12. Feng G., Li L. Application of genetic algorithm and neural network in construction cost estimate. International Conference on Computer and Information Application. Available at: https://www.atlantispress. com/article/4202.pdf (accessed 13.02.2023).
  13. Bala K., Bustani S. A., Shehu W. B. Artificial neural networks in construction engineering and management. International Journal of Architecture, Engineering and Construction, 2017, vol. 6, no. 1, pp. 50–60.
  14. Roxas C. L. C, Ongpen J. M. C. An artificial neural network approach to structural cost estimation of building projects in the Philippines. DLSU Research Congress, Manila, 2014. Available at: https://www.dlsu.edu.ph/wp-content/uploads/dlsu-research-congress-proceedings/2014/SEE-I-005-FT.pdf (accessed 13.02.2023)
  15. El-Sawalhi N. I., Shehatto O. Neural network model for building construction projects. Cost estimating. Journal of Construction Engineering and Project Management. Available at: https://doi.org/10.6106/JCEPM.2014.4.4.009. (accessed 13.02.2023).
  16. Magdum S. K., Adamuthe A. C. Construction cost estimation using neural networks. International Journal (ICTACT). Journal on Soft Computing. Available at: https://ictactjournals.in/paper/IJSC_Vol_8_Iss_1_Paper_4_1549_1556.pdf (accessed 13.02.2023).
  17. Chandanshive V. B., Kambekar A. R. Estimation of building construction cost using artificial neural networks. Journal of Soft Computing in Civil Engineering. Available at: http://www.jsoftcivil.com/article_89032_9a2e28148ec5b773f259194d5709c658.pdf (accessed 13.02.2023).
  18. Yun S. Performance analysis of construction cost prediction using neural network for multioutput regression. MDPI. Available at: https://doi.org/10.3390/app12199592ost (accessed 13.02.2023).
  19. Polkovnikov A. V., Dubovik M. F. Upravlenie proektami. Polnyy kurs MBA [Project management. Complete MBA course]. Moscow, Olimp-Business Publ., 2013. 538 p. (In Russian).
14.02.2023