The Application of BP Neural Network Algorithm to Risk Evaluation of High-Tech Entrepreneurial Projects
Xiaofeng Li, Pan Guo · 2021 4th International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE) · 2021
Back propagation (BP) neural network is characterized by the advantages of large-scale parallel, distributed processing, self-organization, and self-learning. It is suitable for handling problems that need to consider multiple conditions and fuzzy information simultaneously. Firstly, this paper expounds on the construction and algorithm of the BP neural network. Then, the risk index system of high-tech entrepreneurial projects was designed, and the evaluation levels and scoring method for the risk factor indicators were determined. Finally, we developed a model for risk evaluation of high-tech entrepreneurial projects based on the BP neural network. The empirical results show that the BP neural network has strong feasibility and effectiveness, and can accurately fit the training values to derive accurate prediction results. This method provides a new approach for risk evaluation of entrepreneurial projects.