Correo Electrónico
DNINFOA - SIA
Bibliotecas
Convocatorias
Identidad U.N.
Published
Cost Forecasting of Public Construction Projects Using Multilayer Perceptron Artificial Neural Networks: A Case Study
Previsión de costos de proyectos de construcción pública utilizando Redes Neuronales Artificiales de Perceptrón Multicapa: un estudio de caso
DOI:
https://doi.org/10.15446/ing.investig.v41n3.87737Keywords:
Costs, artificial neural network, public undertakings (en)empresas públicas, costos, red neuronal artificial (es)
The execution of public sector construction projects often requires the use of financial resources not foreseen during the tendering phase, which causes management problems. This study aims to present a computational model based on artificial intelligence, specifically on artificial neural networks, capable of forecasting the execution cost of construction projects for Brazilian educational public buildings. The database used in the training and testing of the neural model was obtained from the online system of the Ministry of Education. The neural network used was a multilayer perceptron as a backpropagation algorithm optimized through the gradient descent method. To evaluate the obtained results, the mean absolute percentage errors and the Pearson correlation coefficients were calculated. Some hypothesis tests were also carried out in order to verify the existence of significant differences between real values and those obtained by the neural network. The average percentage errors between predicted and actual values varied between 5% and 9%, and the correlation values reached 0,99. The results demonstrated that it is possible to use artificial intelligence as an auxiliary mechanism to plan construction projects, especially in the public sector.
La ejecución de proyectos de construcción del sector público a menudo requiere el uso de recursos financieros no previstos durante la fase de licitación, lo que genera problemas de gestión. Este estudio tiene como objetivo presentar un modelo computacional basado en inteligencia artificial, específicamente en redes neuronales artificiales, capaz de pronosticar el costo de ejecución de proyectos de construcción de edificios públicos educativos brasileños. La base de datos utilizada en el entrenamiento y prueba del modelo neuronal se obtuvo del sistema en línea del Ministerio de Educación. La red neuronal utilizada fue un perceptrón multicapa como algoritmo de retropropagación optimizado por el método de descenso de gradiente. Para evaluar los resultados obtenidos, se calcularon los errores porcentuales absolutos medios y los coeficientes de correlación de Pearson. También se llevaron a cabo algunas pruebas de hipótesis con el fin de verificar la existencia de diferencias significativas entre los valores reales y los obtenidos por la red neuronal. Los errores porcentuales promedio entre los valores predichos y reales variaron entre el 5% y el 9 %, y los valores de correlación alcanzaron el 0,99. Los resultados demostraron que es posible utilizar la inteligencia artificial como mecanismo auxiliar para la planificación de proyectos de construcción, especialmente en el sector público.
References
Alvarenga, F. C. (2019). Análise das causas de aditivos de custo e de prazo em obras públicas de instituições federais de ensino. [Master’s thesis]. Universidade Federal do Pará. http://repositorio.ufpa.br/jspui/handle/2011/11129
Alvarenga, F. C., Maués, L. M. F., Santos Júnior, P. C. D., & Macedo, A. N. (2021). Alterações de custo e prazo em obras públicas. Ambiente Construído, 21(1), 161-180. http://doi.org/10.1590/s1678-86212021000100500
Asteris, P. G., Kolovos, K. G., Douvika, M. G., and Roinos, K. (2016). Prediction of self-compacting concrete strength using artificial neural networks. European Journal of Environmental and Civil Engineering, 8189 (November), 1-21. https://doi.org/10.1080/19648189.2016.1246693
Bassanezi, R., and Ferreira, W. (1988). Equações Diferenciais com Aplicações. São Paulo: Harbra.
Batista, C. F. B. (2012). Soluções de Equações Diferenciais Usando Redes Neurais de Múltiplas camadas com os métodos da Descida mais íngreme e Levenberg – Marquardt. [Master’s thesis]. Universidade Federal do Pará. https://cutt.ly/MbDEmg8
Bear, M. F., Connors, B. W. and Paradiso, M. A. (2002). Neurociências: Desvendando o Sistema Nervoso. (2nd edition). Porto Alegre, Brazil: Artmed.
Belalia, O., Bakhta, D., Mohamed, B., and Arezki, G. (2017). Prediction of properties of self-compacting concrete containing fly ash using artificial neural network. Neural Computing and Applications, 28 (1), 707–718. https://doi.org/10.1007/s00521-016-2368-7
Borba, R. T. R., and Marinho, M. (2019). Estatísticas dos Contratos de Obras Públicas no Estado de Pernambuco. Revista de Engenharia e Pesquisa Aplicada, 4(3), 52–66. https://doi.org/10.25286/repa.v4i3.994
Brasil. Lei 8.666 de 21 de junho de 1993. Regulamenta o art. 37, inciso XXI, da Constituição Federal, institui normas para licitação e contratos da Administração Pública e dá outras providências. Diário Oficial (Separata), 1993-06-26. http://www.planalto.gov.br/ccivil03=leis=l8666compilado:htm
Bucciol, A., Chillemi, O., and Palazzi, G. (2013). Cost overrun and auction format in small-size public works. European Journal of Political Economy, 30, 35–42. https://doi.org/10.1016/j.ejpoleco.2013.01.002
Bussab, W. de O. and Morettin, P. A. (2003). Estatística Básica, (5th edition). S˜ao Paulo, Brasil: Saraiva.
Cunha, W. S. and Caffé Filho, H. P. (2019). Management of Public Works: Logistics more suited to the fulfillment of planned deadlines. Revista de Psicologia, 13(45), 77–89. https://doi.org/10.14295/idonline.v13i45.1823
Dogan, G., Arslan, M. H., and Ceylan, M. (2015). Statistical feature extraction based on an ANN approach for estimating the compressive strength of concrete. Neural Network World, 25(3), 301. https://doi.org/10.14311/NNW.2015.25.016
Elmousalami, H. H. (2020). Artificial Intelligence and Parametric Construction Cost Estimate Modeling: State-of-the-Art Review. Journal of Construction Engineering and Management, 146(1), 03119008. https://doi.org/10.1061/(ASCE)CO.19437862.0001678
Famiyeh, S., Amoatey, C. T., Adaku, E. and Agbenohevi, C. S. (2017). Major causes of construction time and cost overruns: A case of selected educational sector projects in Ghana. Journal of Engineering, Design and Technology, 15(2), 181–198. https://doi.org/10.1108/JEDT-11-2015-0075
Haykin, S. (2001). Redes Neurais: Princípios e Prática, (2nd edition). Porto Alegre, Brasil: Bookman.
Hyari, K. H., Al-Daraiseh, A., and El-Mashaleh, M. (2016). Conceptual Cost Estimation Model for Engineering Services in Public Construction Projects. Journal of Management in Engineering, 32(1), 1–9. https://doi.org/10.1061/(ASCE)ME.1943-5479.0000381
Jorge, R., and Ribeiro, B. (2006). Possibilidades de atuação do Poder Legislativo frente à questão das obras inacabadas. Revista do TCU, 107(2006), 95-100. https://revista.tcu.gov.br/ojs/index.php/RTCU/article/view/510
Kaming, P. F., Olomolaiye, P. O., Holt, G. D., and Harris, F. C. (1997). Factors influencing construction time and cost overruns on high-rise projects in Indonesia. Construction Management and Economics, 15(1), 83–94. https://doi.org/10.1080/014461997373132
Lu, Y., Luo, X. Y., and Zhang, H. (2011). A gene expression programming algorithm for highway construction cost prediction problems. Journal of Transportation Systems Engineering and Information Technology, 11(6), 85–92. https://doi.org/10.1016/S1570-6672(10)60150-X
Mahamid, I. (2018). Critical Determinants of Public Construction Tendering Costs. International Journal of Architecture, Engineering and Construction, 7(1). https://doi.org/10.7492/ijaec.2018.005
Maués, M. (2017). Modelo para Estimar o Prazo de Execução de Obras Residenciais Verticais – Por meio da Lógica Fuzzy. [Master’s thesis]. Universidade Federal do Maranhão. http://repositorio.ufpa.br/jspui/handle/2011/9877
MEC. Minist´ério da Educa¸c˜ao. (2019). Sistema Integrado de Monitoramento Execuca˜o e Controle. http://simec.mec.gov.br/login.php
Monteiro, M. O. (2010). Processos de obras de infra-estruturas viárias municipais: uma análise dos desvios de custo e de prazo. [Doctoral dissertation]. Universidade de Tr´asosMontes e Alto Douro, Vila Real.
Oliveira, T. D. (2016). Improbidade administrativa e seus efeitos nos casos de desvio de recursos públicos nas obras inacabadas e contratadas pelo poder público. [Undergraduate’s thesis].Centro Universit´ario Tabosa de Almeida. https://cutt.ly/EbDE4J4
Rocha, P. L. (2018). Reconhecimento de Voz utilizando Seleção Dinâmica de Redes Neurais. Universidade Federal do Maranhão.
Santos, A. de P. L. and Garcia, L. E. M. (2012). Orçamento executivo como ferramenta do processo de planejamento e controle de custos de obras públicas. Revista Gestão e Políticas Públicas, 2(1), 40-67. https://www.revistas.usp.br/rgpp/article/view/97850 DOI: https://doi.org/10.11606/issn.2237-1095.v2i1p40-67
Shahandashti, S. M., and Ashuri, B. (2013). Forecasting engineering news-record construction cost index using multivariate time series models. Journal of Construction Engineering and Management}, 139(9), 1237–1243. https://doi.org/10.1061/(ASCE)CO.1943-7862.0000689
Shahandashti, S. M., and Ashuri, B. (2016). Highway Construction Cost Forecasting Using Vector Error Correction Models. Journal of Management in Engineering, 32(2), 1–8. https://doi.org/10.1061/(ASCE)ME.1943-5479.0000404
Silva, I. N., Spatti, D., & Flauzino, R. (2016). Redes Neurai Artificiais para Engenharia e Ciências Aplicadas: Curso Prático. (2nd edition). S˜ao Paulo, Brazil: Artliber.
Silva, M. A. O., Corrêa, L. R., and Ruas, A. X. A. (2018). Gerenciamento De Projetos Na Construção Civil: Tempo , Custo e Qualidade. Construindo, 10, 1–20. http://revista.fumec.br/index.php/construindo/article/view/5034
TCU. (2018). Relatório de Auditoria elaborado pelo Ministério da Economia.
Tisaka, M. (2006). Orçamento na construção civil consultoria , projeto e execução. São Paulo, Brasil: Pini.
Ugur, L. (2017). A Neuro-Adaptive Learning (NAL) approach about costs of residential buildings. Acta Physica Polonica A, 132(3), 585-587. https://doi.org/10.12693/APhysPolA.132.585
Wanjari, S. P., and Dobariya, G. (2016). Identifying factors causing cost overrun of the construction projects in India. Sadhana - Academy Proceedings in Engineering Sciences, 41(6), 679–693. https://doi.org/10.1007/s12046-016-0498-3
Zanella, L. C. H. (2011). Metodologia de Pesquisa. (2nd edition). Florianópolis: Departamento de Ciências da Administração. Universidade Federal de Santa Catarina / Sistema UAB. https://cutt.ly/obDRmp9
How to Cite
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Download Citation
CrossRef Cited-by
1. Harrynson Ramírez Murillo, Ricardo Rincon, Fabián Salazar, Martha Patricia Camargo, Natalia Rojas-Medina, Camilo Leal-Rincón. (2025). Strategy for EV Charging Station Placement Using a Bootstrapping-Based Probabilistic Power Flow. Ingeniería e Investigación, 45(2), p.e116496. https://doi.org/10.15446/ing.investig.116496.
2. Mohd. Ahmed, Saeed AlQadhi, Javed Mallick, Nabil Ben Kahla, Hoang Anh Le, Chander Kumar Singh, Hoang Thi Hang. (2022). Artificial Neural Networks for Sustainable Development of the Construction Industry. Sustainability, 14(22), p.14738. https://doi.org/10.3390/su142214738.
3. Yung-Chia Chang, Kuei-Hu Chang, Hsien-Mi Meng, Hung-Chih Chiu, Gengxin Sun. (2022). A Novel Multicategory Defect Detection Method Based on the Convolutional Neural Network Method for TFT-LCD Panels. Mathematical Problems in Engineering, 2022, p.1. https://doi.org/10.1155/2022/6505372.
4. Mohamed Nabawy, Ahmed Gouda Mohamed. (2024). Risks assessment in the construction of infrastructure projects using artificial neural networks. International Journal of Construction Management, 24(4), p.361. https://doi.org/10.1080/15623599.2022.2156902.
5. Khalid S. Al-Gahtani, Abdullah M. Alsugair, Naif M. Alsanabani, Abdulmajeed A. Alabduljabbar, Abdulmohsen S. Almohsen. (2025). ANN prediction model of final construction cost at an early stage. Journal of Asian Architecture and Building Engineering, 24(2), p.775. https://doi.org/10.1080/13467581.2023.2294883.
6. Shadi Salimimoghadam, Amir Naser Ghanbaripour, Roksana Jahan Tumpa, Amir Kamel Rahimi, Mehdi Golmoradi, Sara Rashidian, Martin Skitmore. (2025). The Rise of Artificial Intelligence in Project Management: A Systematic Literature Review of Current Opportunities, Enablers, and Barriers. Buildings, 15(7), p.1130. https://doi.org/10.3390/buildings15071130.
7. Shasha Peng, Ya Zuo, Xiangping Li, Mingrui Zhao, Bingkang Li. (2025). Cost Prediction for Power Transmission and Transformation Projects in High-Altitude Regions Based on a Hybrid Deep-Learning Algorithm. Processes, 13(7), p.2092. https://doi.org/10.3390/pr13072092.
8. Nidal Adnan Jasim, Abdulrahman Adnan Ibrahim, Wadhah Amer Hatem. (2023). Artificial neural networks models for predicting performance measurement of oil projects. Asian Journal of Civil Engineering, 24(8), p.3597. https://doi.org/10.1007/s42107-023-00737-8.
9. Luís Jacques de Sousa, João Poças Martins, João Santos Baptista, Luís Sanhudo. (2023). Trends on Construction in the Digital Era. Lecture Notes in Civil Engineering. 306, p.101. https://doi.org/10.1007/978-3-031-20241-4_8.
10. Alexsandr Kudryavtsev, Maksim Zheleznov, Vladimir Filatov, Lyubov' Adamcevich. (2025). Analysis of the capabilities of information and simulation mathematical modeling technologies for forecasting the cost of work at the construction stage. Construction and Architecture, 13(2), p.7. https://doi.org/10.29039/2308-0191-2025-13-2-7-7.
Dimensions
PlumX
Article abstract page views
Downloads
License
Copyright (c) 2021 Alcineide Pessoa, Gean Sousa, Luiz Maués, Felipe Alvarenga, Débora Santos
This work is licensed under a Creative Commons Attribution 4.0 International License.
The authors or holders of the copyright for each article hereby confer exclusive, limited and free authorization on the Universidad Nacional de Colombia's journal Ingeniería e Investigación concerning the aforementioned article which, once it has been evaluated and approved, will be submitted for publication, in line with the following items:
1. The version which has been corrected according to the evaluators' suggestions will be remitted and it will be made clear whether the aforementioned article is an unedited document regarding which the rights to be authorized are held and total responsibility will be assumed by the authors for the content of the work being submitted to Ingeniería e Investigación, the Universidad Nacional de Colombia and third-parties;
2. The authorization conferred on the journal will come into force from the date on which it is included in the respective volume and issue of Ingeniería e Investigación in the Open Journal Systems and on the journal's main page (https://revistas.unal.edu.co/index.php/ingeinv), as well as in different databases and indices in which the publication is indexed;
3. The authors authorize the Universidad Nacional de Colombia's journal Ingeniería e Investigación to publish the document in whatever required format (printed, digital, electronic or whatsoever known or yet to be discovered form) and authorize Ingeniería e Investigación to include the work in any indices and/or search engines deemed necessary for promoting its diffusion;
4. The authors accept that such authorization is given free of charge and they, therefore, waive any right to receive remuneration from the publication, distribution, public communication and any use whatsoever referred to in the terms of this authorization.
