Cost Estimation and Prediction for Residential Projects Based on Grey Relational Analysis–Lasso Regression–Backpropagation Neural Network
Abstract
:1. Introduction
2. Methodology
2.1. Data Collection Method
- Data Request: Send a request to the server of the specified website to obtain its corresponding web content.
- Webpage Analysis: Use regular expressions and other rules to selectively filter the needed information from the extensive content on the web server.
- Data Storage: Save the initially captured key information into files in formats such as EXCEL to prepare for subsequent data preprocessing.
2.2. Grey Relational Analysis
2.3. LASSO Regression
2.4. GRA-LASSO-BPNN
2.5. Performance Evaluation
3. Research Applications
3.1. Data Acquisition and Preprocessing
3.2. Selection of Input Variables for Residential Project Costs
3.2.1. Input Variable Importance Ranking
3.2.2. Correlation Analysis
3.2.3. Determination of Input Variables
3.3. GRA-LASSO-BP Prediction Model Establishment
4. Results and Discussion
4.1. Conclusion and Analysis of Input Variable Selection
4.2. Performance Analysis of the Residential Project Cost Estimation Hybrid Model
5. Conclusions
- Among the 17 input variables, the ones with the most significant impact on the unit cost of residential projects in Shanghai, after GRA and LASSO regularization, are the seismic fortification intensity, commercial concrete grade, type of doors and windows, and total building area. A total of 12 input variables were ultimately selected.
- The evaluation metrics of the proposed GRA-LASSO-BPNN hybrid prediction model are significantly lower than those of the BPNN and LASSO regression models, indicating that the GRA-LASSO-BPNN hybrid prediction model proposed in this study has superior predictive performance in estimating residential project costs.
- The GRA-LASSO-BPNN model outperforms the BPNN model alone, demonstrating that input variable selection can enhance model prediction accuracy. Additionally, when comparing the BPNN and LASSO models, as well as the GRA-LASSO-BPNN and LASSO models, it is evident that the errors of the hybrid models are lower than those of LASSO, suggesting that BPNN can improve prediction accuracy on high-dimensional small sample datasets.
- Collect more datasets to further reduce prediction model errors.
- Introduce additional relevant feature parameters that impact the cost of underground structures, and then use GRA-LASSO for feature selection.
- Introduce optimization algorithms to improve the GRA-LASSO-BPNN model.With the progressive informatization of construction, deep learning is expected to become increasingly integral to the cost management in construction.
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Dandan, T.H.; Sweis, G.; Sukkare, L.S.; Sweis, R.J. Factors affecting the accuracy of cost estimate during various design stages. J. Eng. Des. Technol. 2019, 18, 787–819. [Google Scholar]
- Wang, B.; Dai, J. Discussion on the prediction of engineering cost based on improved BP neural network algorithm. J. Intell. Fuzzy Syst. 2019, 37, 6091–6098. [Google Scholar]
- Stoy, C.; Kalusche, W. The determination of occupancy costs during early project phases. Constr. Manag. Econ. 2006, 24, 933–944. [Google Scholar]
- Bimenyimana, S.; Asemota, G.N.O.; Ihirwe, P.J.; Mesa, K.C. Performance estimation of Ntaruka hydropower plant and its comparison with the prediction results obtained by SPSS. Energy Environ. 2018, 29, 1004–1021. [Google Scholar] [CrossRef]
- Wang, Y.R.; Yu, C.Y.; Chan, H.H. Predicting construction cost and schedule success using artificial neural networks ensemble and support vector machines classification models. Int. J. Proj. Manag. 2012, 30, 470–478. [Google Scholar]
- Jin, R.Z.; Cho, K.M.; Hyun, C.T.; Son, M.J. MRA-based revised CBR model for cost prediction in the early stage of construction projects. Expert Syst. Appl. 2012, 39, 5214–5222. [Google Scholar]
- Son, H.; Kim, C.; Kim, C. Hybrid principal component analysis and support vector machine model for predicting the cost performance of commercial building projects using pre-project planning variables. Autom. Constr. 2012, 27, 60–66. [Google Scholar]
- Ongpeng, J.; Roxas, C. An artificial neural network approach to structural cost estimation of building projects in the Philippines. In Proceedings of the DLSU Research Congress, Manila, Philippines, 6–8 March 2014. [Google Scholar]
- Bala, K.; Bustani, S.A.; Waziri, B.S. A computer-based cost prediction model for institutional building projects in Nigeria: An artificial neural network approach. J. Eng. Des. Technol. 2014, 12, 519–530. [Google Scholar]
- Deepa, G.; Niranjana, A.J.; Balu, A.S. A hybrid machine learning approach for early cost estimation of pile foundations. J. Eng. Des. Technol. 2023; ahead-of-print. [Google Scholar] [CrossRef]
- Ye, D. An Algorithm for Construction Project Cost Forecast Based on Particle Swarm Optimization-Guided BP Neural Network. Sci. Program. 2021, 2021, 8. [Google Scholar]
- Du, Z.; Li, B. Construction project cost estimation based on improved BP neural network. In Proceedings of the 2017 International Conference on Smart Grid and Electrical Automation (ICSGEA), Changsha, China, 27–28 May 2017. [Google Scholar]
- Feng, G.L.; Li, L. Application of genetic algorithm and neural network in construction cost estimate. Adv. Mat. Res. 2013, 756–759, 3194–3198. [Google Scholar]
- Sandoval-Moreno, G.; Galea, M.; Arellano-Valle, R. Inference in multivariate regression models with measurement errors. J. Stat. Comput. Simul. 2023, 93, 1997–2025. [Google Scholar]
- De Mello, R.; Manapragada, C.; Bifet, A. Measuring the Shattering coefficient of Decision Tree models. Expert Syst. Appl. 2019, 137, 443–452. [Google Scholar]
- Sabzekar, M.; Hasheminejad, S.M.H. Robust regression using support vector regressions. Chaos Solitons Fractals 2021, 144, 110738. [Google Scholar]
- Wang, S.Z.; Ji, B.X.; Zhao, J.S.; Liu, W.; Xu, T. Predicting ship fuel consumption based on LASSO regression. Transport. Res. Part D—Transp. Environ. 2018, 65, 817–824. [Google Scholar]
- Li, Z.T.; Jiang, L.L.; Zhao, R.; Huang, J.; Yang, W.; Wen, Z.; Zhang, B.; Du, G. MiRNA-based model for predicting the TMB level in colon adenocarcinoma based on a LASSO logistic regression method. Medicine 2021, 100, e26068. [Google Scholar]
- Lee, J.H.; Shi, Z.T.; Gao, Z. On LASSO for predictive regression. J. Econom. 2022, 229, 322–349. [Google Scholar]
- Meharie, M.G.; Gariy, Z.; Mutuku, R.; Mengesha, W.J. An effective approach to input variable selection for preliminary cost estimation of construction projects. Adv. Civ. Eng. 2019, 2019, 1–14. [Google Scholar]
- Alshemosi, A.M.B.; Alsaad, H.S.H. Cost estimation process for construction residential projects by using multifactor linear regression technique. Int. J. Sci. Res. 2017, 6, 151–156. [Google Scholar]
- Greenacre, M.; Groenen, P.J.F.; Hastie, T.; D’Enza, A.I.; Markos, A.; Tuzhilina, E. Principal component analysis. Nat. Rev. Methods Primers 2022, 2, 100. [Google Scholar]
- Sayed, M.; Abdel-Hamid, M.; El-Dash, K. Improving cost estimation in construction projects. Int. J. Constr. Manag. 2020, 23, 135–143. [Google Scholar]
- Youssefi, I.; Celik, T. Optimized approach toward identification of influential cost overrun causes in construction industry. ASCE-ASME J. Risk Uncertain. Eng. Syst. Part A Civ. Eng. 2023, 9, 04023003. [Google Scholar]
- Mao, S.; Tseng, C.H.; Shang, J.; Wu, Y.; Zeng, X.J. In Proceedings of Construction cost index prediction: A visibility graph network method. In Proceedings of the 2021 International Joint Conference on Neural Networks (IJCNN), Shenzhen, China, 18–22 July 2021. [Google Scholar]
- Wang, C.X.; Qiao, J.L. Construction Project Cost Prediction Method Based on Improved BiLSTM. Appl. Sci. 2024, 14, 978. [Google Scholar] [CrossRef]
- Gai, R.; Guo, Z. A Water Quality Assessment Method Based on an Improved Grey Relational Analysis and Particle Swarm Optimization Multi-classification Support Vector Machine. Front. Plant Sci. 2023, 14, 1099668. [Google Scholar]
- Tong, B.; Guo, J.J.; Fan, S. Predicting Budgetary Estimate of Highway Construction Projects in China Based on GRA-LASSO. J. Manage. Eng. 2021, 37, 04021012. [Google Scholar]
- Yu, W.K.; Wu, H.R.; Peng, C. Short-Term Price Forecast of Vegetables Based on Combination Model of Lasso Regression Method and BP Neural Network. Smart Agric. 2020, 2, 108–117. [Google Scholar]
- Muehlethaler, C.; Albert, R. Collecting data on textiles from the internet using web crawling and web scraping tools. Forensic Sci. Int. 2021, 322, 110753. [Google Scholar]
- Shi, T.; Jiang, W.; Luo, P. A Method of Clustering Ensemble Based on Grey Relation Analysis. Wirel. Pers. Commun. 2018, 103, 871–885. [Google Scholar]
- Singh, T.; Patnaik, A.; Chauhan, R. Optimization of tribological properties of cement kiln dust-filled brake pad using grey relation analysis. Mater. Des. 2016, 89, 1335–1342. [Google Scholar]
- Tibshirani, R. Regression shrinkage and selection via the lasso. J. R. Stat. Soc. Ser. B 1996, 58, 267–288. [Google Scholar]
- Fang, S.; Zhao, T.; Zhang, Y. Prediction of construction projects’ costs based on fusion method. Eng. Comput. 2017, 34, 2396–2408. [Google Scholar]
- Rafiei, M.H.; Adeli, H. Novel machine-learning model for estimating construction costs considering economic variables and indexes. J. Constr. Eng. Manag. 2018, 144, 04018106. [Google Scholar]
- Ahn, J.; Park, M.; Lee, H.S.; Ahn, S.J.; Ji, S.H.; Song, K.; Son, B.S. Covariance effect analysis of similarity measurement methods for early construction cost estimation using case-based reasoning. Autom. Constr. 2017, 81, 254–266. [Google Scholar]
- Jiang, S.J. Green supplier selection for sustainable development of the automotive industry using grey decision-making. Sustain. Dev. 2018, 26, 890–903. [Google Scholar]
- Zeng, B.; Guo, J.; Zhang, F.; Zhu, W.; Xiao, Z.; Huang, S.; Fan, P. Prediction model for dissolved gas concentration in transformer oil based on modified grey wolf optimizer and LSSVM with grey relational analysis and empirical mode decomposition. Energies 2020, 13, 422. [Google Scholar] [CrossRef]
- Delcea, C.; Cotfas, L.A. Public opinion assessment through grey relational analysis approach. In Advancements of Grey Systems Theory in Economics and Social Sciences; Springer Nature: Singapore, 2023; pp. 179–199. [Google Scholar]
- Fan, H.B. Research on Estimation Model of Construction Cost Based on Optimal Neural Network. Master’s Dissertation, Shenyang Jianzhu University, Shenyang, China, 2019. [Google Scholar]
- Wang, D.H. Multivariate Statistical Analysis and SPSS Applications; East China University of Science and Technology Press: Shanghai, China, 2010. [Google Scholar]
Number | Input Variables |
---|---|
X1 | Project location |
X2 | Number of underground floors |
X3 | Structural type |
X4 | Total building area |
X5 | Above-ground building area |
X6 | Underground building area |
X7 | Presence of basement |
X8 | Number of floors |
X9 | Number of above-ground floors |
X10 | Ground floor height |
X11 | Standard floor height |
X12 | Eaves’ height |
X13 | Seismic fortification intensity |
X14 | Type of doors |
X15 | Type of windows |
X16 | Percentage of grade III steel |
X17 | Commercial concrete grade |
Number | Input Variables | Correlation Degrees |
---|---|---|
X13 | Seismic fortification intensity | 0.9050 |
X17 | Commercial concrete grade | 0.9019 |
X15 | Type of windows | 0.9012 |
X14 | Type of doors | 0.8967 |
X11 | Standard floor height | 0.8913 |
X10 | Ground floor height | 0.8848 |
X16 | Percentage of grade III steel | 0.8795 |
X4 | Total building area | 0.8098 |
X5 | Above-ground building area | 0.8065 |
X12 | Eaves’ height | 0.8064 |
X3 | Structural type | 0.7984 |
X8 | Number of floors | 0.7947 |
X9 | Number of above-ground floors | 0.7937 |
X1 | Project location | 0.7257 |
X6 | Underground building area | 0.7119 |
X2 | Number of underground floors | 0.6916 |
X7 | Presence of basement | 0.6865 |
MODEL | MAE | MSE | RMSE |
---|---|---|---|
GRA-LASSO-BPNN | 197.02 | 55,057.04 | 234.64 |
BPNN | 246.77 | 92,251.84 | 303.73 |
LASSO | 278.33 | 237,556.01 | 487.40 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Chen, L.; Wang, D. Cost Estimation and Prediction for Residential Projects Based on Grey Relational Analysis–Lasso Regression–Backpropagation Neural Network. Information 2024, 15, 502. https://doi.org/10.3390/info15080502
Chen L, Wang D. Cost Estimation and Prediction for Residential Projects Based on Grey Relational Analysis–Lasso Regression–Backpropagation Neural Network. Information. 2024; 15(8):502. https://doi.org/10.3390/info15080502
Chicago/Turabian StyleChen, Lijun, and Dejiang Wang. 2024. "Cost Estimation and Prediction for Residential Projects Based on Grey Relational Analysis–Lasso Regression–Backpropagation Neural Network" Information 15, no. 8: 502. https://doi.org/10.3390/info15080502