Economic Analysis of Risky Projects Based on LS-SVM

Abstract:

Risk management and its accurate analysis are very important for project management. RBF and MLP Neural Network Model are common methods of risk management and analysis, which are not accurate enough. In this paper a new method based on LS-SVM is introduced. Analytical models of risky projects are investigated and function approximation results are compared. Experimental results show that the regression analysis of risk based on LS-SVM method has higher prediction accuracy and better generalization ability.

• Periodical: Applied Mechanics and Materials (Volumes 63-64)
• Pages: 403-406
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.63-64.403
• Online since: June 2011
• Authors: Xin Chen Guo, Chao Zhang, Fu Wei Zhang
• Keywords: Economic Analysis, Neural Network (NN), Risky Projects, Support Vector Machine (SVM)

References

[1] A. Taskin, A. F. Guneri: Economic analysis of risky projects by ANNs, Applied Mathematics and Computation. Vol. 175. (2006), pp.171-181.

DOI: 10.1016/j.amc.2005.07.016

[2] V. Vapnik: The nature of statistical learning theory, New York : springer - verlag, (2000).

[3] C. Cortes, V. Vapnik: Support vector networks, Machine Learning. Vol. 20. (1995), pp.273-297.

DOI: 10.1007/bf00994018

[4] Y. F. Wen: Materials experimental data analysis and application of support vector regression, Chongqing University Master's Thesis (2009), pp.22-32.

[5] S. Ward, C. Chapman: Transforming project risk management into project uncertainty management, International Journal of Project Management. Vol. 21. (2003), p.97–105.

DOI: 10.1016/s0263-7863(01)00080-1

[6] T. Raz, E. Michael: Use and benefits of tools for project risk management, International Journal of Project Management. Vol. 19. (2001), p.9–17.

DOI: 10.1016/s0263-7863(99)00036-8

[7] Z. H. Zou, H. Y. Jiao: Based on least squares support vector regression for short-term water demand forecast, Water Supply and Drainage. Vol. 34. (2008), pp.328-331.

[8] G. H. Yan, Y. S. Zhu: Support vector machine regression parameter selection method, Computer Engineering, Vol. 35. Supplement (2009), pp.218-220.

[9] C. Vladimir, Y. Q. M: Practical Selection of SVM Parameters and Noise Estimation for SVM Regression, Neural Networks, Vol. 17. (2004), pp.113-126.

DOI: 10.1016/s0893-6080(03)00169-2

[10] S. Sathiya, C. J. Keerthi: Asymptotic Behavior of Support Vector Machines with Gaussian Kernel, Neural Computation, Vol. 15. (2003), pp.1667-1689.

DOI: 10.1162/089976603321891855