Optimized Hybrid Deep Learning for Cost Estimation of Construction Projects Considering the Time-Dependent Characteristics of Economic Variables and Indices
Abstract
The SOS-NN-LSTM hybrid model emerges as a transformative solution to the perpetual challenge of accurate cost estimation in the construction industry. By integrating Neural Networks (NN) and Long Short-Term Memory networks (LSTM), optimized through the Symbiotic Organism Search (SOS) algorithm, the model distinguishes itself with remarkable performance metrics. Achieving an R-squared value of 0.9631 and a minimal Root Mean Squared Error (RMSE) of 0.023, SOS-NN-LSTM showcases its efficacy in handling project physical, financial, and time-dependent economic variables. The model's superiority is further emphasized by a minimal Mean Absolute Error (MAE) of 0.0168 and a notable Relative Improvement (RI) value of 0.96018. Importantly, the Mean Absolute Percentage Error (MAPE) experiences a significant decrease from 20% to 10%, highlighting the model's enhanced precision in cost estimation. SOS-NN-LSTM not only outperforms other AI models but also demonstrates its adaptability to dynamic economic conditions, effectively addressing the volatility of economic variables in construction projects. These exceptional results position SOS-NN-LSTM as a pioneering advancement in cost estimation methodologies for the construction industry. The model's nuanced handling of complex datasets and its ability to provide accurate projections underscore its potential to revolutionize project budgeting, mitigate risks, and contribute to the overall success and financial viability of construction projects. The integration of deep learning with SOS optimization represents a paradigm shift, offering a reliable and effective tool for project stakeholders in navigating the intricacies of construction cost estimation.
References
Abioye, S. O., Oyedele, L. O., Akanbi, L., Ajayi, A., Davila Delgado, J. M., Bilal, M., Akinade, O. O., & Ahmed, A. (2021). Artificial intelligence in the construction industry: A review of present status, opportunities and future challenges. Journal of Building Engineering, 44, 103299. https://doi.org/https://doi.org/10.1016/j.jobe.2021.103299
Alekhya, G. B. S., Shashikanth, K., & Prasad, M. A. (2022). Risk assessment of cost overrun using fuzzy logic model. Materials Today: Proceedings, 62, 1803-1810. https://doi.org/https://doi.org/10.1016/j.matpr.2021.12.415
Barnes, M. (1988). Construction project management. International Journal of Project Management, 6(2), 69-79. https://doi.org/https://doi.org/10.1016/0263-7863(88)90028-2
Cheng, M.-Y., Cao, M.-T., & Herianto, J. G. (2020). Symbiotic organisms search-optimized deep learning technique for mapping construction cash flow considering complexity of project. Chaos, Solitons & Fractals, 138, 109869.
Cheng, M.-Y., Chang, Y.-H., & Korir, D. (2019). Novel approach to estimating schedule to completion in construction projects using sequence and nonsequence learning. Journal of Construction Engineering and Management, 145(11), 04019072.
Cheng, M.-Y., & Prayogo, D. (2014). Symbiotic Organisms Search: A new metaheuristic optimization algorithm. Computers & Structures, 139, 98-112. https://doi.org/https://doi.org/10.1016/j.compstruc.2014.03.007
Ezugwu, A. E., & Prayogo, D. (2019). Symbiotic organisms search algorithm: Theory, recent advances and applications. Expert Systems with Applications, 119, 184-209. https://doi.org/https://doi.org/10.1016/j.eswa.2018.10.045
Flyvbjerg, B., Skamris, M., & Buhl, S. (2002). Underestimating Costs in Public Works Projects: Error or Lie? Journal of the American Planning Association, 68, 279-295. https://doi.org/10.1080/01944360208976269.
Gunawan, L. S. M., Cheng, M.-Y., & Prayogo, D. (2019). Optimized Management Strategy For Construction Projects Considering The Trade-Off Of Estimate Schedule And Cost At Completion. Dimensi Utama Teknik Sipil, 6(2), 26-37. https://doi.org/10.9744/duts.6.2.26-37
Musarat, M. A., Alaloul, W. S., & Liew, M. S. (2021). Impact of inflation rate on construction projects budget: A review. Ain Shams Engineering Journal, 12(1), 407-414. https://doi.org/https://doi.org/10.1016/j.asej.2020.04.009
Rafiei, M. H., & Adeli, H. (2018). Novel machine-learning model for estimating construction costs considering economic variables and indexes. Journal of Construction Engineering and Management, 144(12), 04018106.
Shoar, S., Chileshe, N., & Edwards, J. D. (2022). Machine learning-aided engineering services' cost overruns prediction in high-rise residential building projects: Application of random forest regression. Journal of Building Engineering, 50, 104102. https://doi.org/https://doi.org/10.1016/j.jobe.2022.104102