A project risk forecast model based on support vector machine

Author

Liyi, Ma ; Shiyu, Zhang ; Jian, Ge

Author_Institution

Dept. of Inf. Manage. & E-commerce, Beijing Union Univ., Beijing, China

fYear

2010

Firstpage

463

Lastpage

466

Abstract

A Project risk forecast model was investigated using least square support vector machine(LS-SVM) method. Risk estimation data of experts was acted as eigenvector of learning samples to train the constructed LS-SVM regression model for realizing mapping relationship between the risk and the characteristic. The test samples were used to compare between the constructed LS-SVM model and BP neural network. The result showed that LS-SVM model has high prediction accuracy and strong generalization ability. So it is suitable for the forecast of large scale project risk.

Keywords

generalisation (artificial intelligence); least squares approximations; project management; regression analysis; risk management; support vector machines; LS-SVM method; LS-SVM regression model; eigenvector; generalization ability; least square support vector machine; project risk forecast model; Artificial neural networks; Biological system modeling; Data models; Kernel; Predictive models; Support vector machines; Training; forecast; project risk; support vector machine;

fLanguage

English

Publisher

ieee

Conference_Titel

Software Engineering and Service Sciences (ICSESS), 2010 IEEE International Conference on

Conference_Location

Beijing

Print_ISBN

978-1-4244-6054-0

Type

conf

DOI

10.1109/ICSESS.2010.5552331

Filename

5552331