International Conference on Construction and Real Estate Management 2020
Investment Risk Assessment Method of PPP Project Based on QPSO-LSSVM
Publication: ICCREM 2020: Intelligent Construction and Sustainable Buildings
ABSTRACT
The investment risk assessment remains a challenge for public-private partnership (PPP) projects under potential risks and complex uncertainties. To address this problem, a least squares support vector machine (LSSVM) based quantum-behaved particle swarm optimization (QPSO) method is proposed to evaluate the investment risk assessment for PPP projects in this paper. This method uses quantum theory to observe the particle state optimization to improve the accuracy of assessment results. Applying this method to the investment risk assessment of these PPP projects with 40 PPP projects in Hubei and Zhejiang Province in China. The results show that the maximum relative error and average relative error of this risk assessment are smaller than the traditional PSO-SVM and backpropagation neural network method. Compared with the existing methods of investment risk assessment, this method improves the accuracy and efficiency of risk assessment of PPP projects.
Get full access to this article
View all available purchase options and get full access to this chapter.
REFERENCES
Ahmadabadi, A.A. and Heravi, G. (2019). “Risk assessment framework of PPP-megaprojects focusing on risk interaction and project success.” Transportation Research Part A: Policy and Practice, 124, 169-188.
Ch, S., Anand, N., Panigrahi, B.K. and Mathur, S. (2013). “Streamflow forecasting by SVM with quantum behaved particle swarm optimization.” Neurocomputing, 101, 18-23.
Kifokeris, D. and Xenidis, Y. (2019) “Risk source-based constructability appraisal using supervised machine learning.” Automation in Construction, 104, 341-359.
Kumar, L., Jindal, A. and Velaga, N.R. (2018). “Financial risk assessment and modelling of PPP based Indian highway infrastructure projects.” Transport Policy, 62, 2-11.
Tang, B.Q., Han, J. and Guo, G.F. (2019). “Evaluation Model of Project Investment Risk Based on Particle Swarm Optimization Improved Least Squares Support Vector Machine.” Journal of Civil Engineering and Management, 36(02), 98-103. (In Chinese).
Wang, X. and Meng, L.L. (2015). “Ultra-short-term load forecasting based on EEMD-LSSVM.” Power System Protection and Control, 43(1), 61-66. (In Chinese).
Wei, Y.Y., Zhang, J.Y. and Wang, J. (2018). “Research on Building Fire Risk Fast Assessment Method Based on Fuzzy comprehensive evaluation and SVM.” Procedia Engineering, 211, 1141-1150.
Wu, Y.N., Li, L.W.Y., Xu, R.H., Chen, K.F., Hu, Y. and Lin, X.S. (2017). “Risk assessment in straw-based power generation public-private partnership projects in China: A fuzzy synthetic evaluation analysis.” Journal of Cleaner Production, 161, 977-990.
Yang, L., Sun, J., Feng, Z., Yue, D. and Yang, L. (2016). “Estimation Model of Forest Above-ground Biomass Based on PSO-LSSVM.” Transactions of the Chinese Society for Agricultural Machinery, 47(3), 273-279. (In Chinese).
Zhao, H. and Wang, X.Q. (2017). “Research on Dynamic Financing Risk Evaluation System of Large-scale Infrastructure Projects.” Journal of Beijing Institute of Technology (Social Sciences Edition), 19(1), 83-90. (In Chinese).
Zhong, Y. (2018). “Forecast Method of Construction Accident based on PSO-LSSVM.” Journal of Chongqing University of Technology (Natural Science), 32(12), 157-161. (In Chinese).
Information & Authors
Information
Published In
ICCREM 2020: Intelligent Construction and Sustainable Buildings
Pages: 84 - 92
Editors: Yaowu Wang, Ph.D., Harbin Institute of Technology, Thomas Olofsson, Ph.D., Luleå University of Technology, and Geoffrey Q. P. Shen, Ph.D., Hong Kong Polytechnic University
ISBN (Online): 978-0-7844-8323-7
Copyright
© 2020 American Society of Civil Engineers.
History
Published online: Oct 14, 2020
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.