The model of project risk assessment based on BP neural network algorithm

For the reason of the complexity of software projects and the uncertainty of software risk factors, it is difficult to use a mathematical expression to represent the model of risk assessment. It belongs to the classification of nonlinear. In this paper, we established the evaluation model of software project risk based on BP neural network. Firstly, an evaluation index system of software project risk is designed. Then, give the model of BP neural network and the algorithm process. At last, the results of experiment validate the feasibility and validity of the approach. The experimental results show that the model improves the accuracy of project risk assessment and reduces project risks.