A Bayesian Belief Network Model for Software Risk Analysis
Uncertainty during the period of software project development will bring huge risks to contractors and clients. If we can establish an effective model to predict the cost and quality of software projects based on facts such as the project character and two-side cooperating capability at the beginning of the project, the risks may be mitigated. Bayesian Belief Network (BBN) is a good method for analyzing uncertain consequences, but it is difficult to produce precise network structure and conditional probability table. In this paper, we built up network structure by Delphi method for conditional probability table learning, and learn to update probability table and nodes confidence levels continuously according to the application cases. This gives the evaluation network its learning abilities, and the software development risk of organization can be evaluated more accurately. In addition, we introduced EM algorithm to enhance the ability in producing hidden nodes caused by variant software projects.
Software Risk Bayesian Belief Network EM algorithm
Yong Hu Juhua Chen Jiaxing Huang Jinghua Xiao Kang Xie Junbiao Tang
Guangdong University of Foreign Studies, Sun Yat-sen University, 510275,China Sun Yat-sen University, 510275, China
国际会议
武汉
英文
2007-09-21（万方平台首次上网日期，不代表论文的发表时间）