Research on Valuation System of Listed Companies Based on Neural Network Model
Mengqiao Liu, Yali Shen, Jiajie Tang, Xiaomeng Li · 2020
In order to improve the accuracy of the value evaluation of listed companies, this paper puts forward a method to construct the value evaluation system of listed companies based on neural network model. This construction method gives full play to the unique advantages of BP neural network, that is, strong nonlinear mapping ability and strong self-learning ability. at the same time, the construction method also makes full use of the powerful functions of BP neural network scientifically, such as the ability of arbitrary complex pattern classification and powerful multi-dimensional function mapping. In addition, the construction method scientifically introduces BP neural network into the value evaluation system of listed companies, and skillfully constructs the value evaluation system of listed companies based on neural network model. The research results show that the construction method can break through the limitations of the traditional value evaluation system of listed companies, solve the problems that can not be solved by simple perceptrons, and have the function of simple operation. it can fundamentally improve the accuracy and efficiency of the value evaluation of listed companies.