Title :
Study on Investment Risk of Engineering Project Based on LS-SVM
Author :
Feng, Li-jun ; Wang, Ping ; Xu, Lin-Na
Author_Institution :
Tianjin Univ. of Finance & Econ., Tianjin
Abstract :
Before the project manager decides whether to invest in a project, he often uses all kinds of methods to forecast the investment risk of the project in order to improve the correctness of his decision-making. Based on the establishment of risk forecast index system about engineering project, this paper put forward the method about using least Squares Support Vector Machine to forecast the investment risk of a project, which could provide the project manager with better decision-making bases. Then using this method, we carried out data experiments on the investment risk of a certain project. The result of experiments had indicated the validity and superiority of the method of least Squares Support Vector Machine, comparing to artificial neural network (Back Propagation, BP). So it has broad application prospect in many fields.
Keywords :
decision making; forecasting theory; investment; least squares approximations; project management; risk management; support vector machines; LS-SVM; decision-making; engineering project; investment risk; least squares support vector machine; project management; risk forecast index system; Artificial neural networks; Cybernetics; Economic forecasting; Investments; Least squares methods; Machine learning; Project management; Risk management; Support vector machine classification; Support vector machines; Engineering project; Forecast; Investment risk; Least Squares Support Vector Machine;
Conference_Titel :
Machine Learning and Cybernetics, 2007 International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-0973-0
Electronic_ISBN :
978-1-4244-0973-0
DOI :
10.1109/ICMLC.2007.4370623
