Financial Crisis Warning Analysis for Companies Based on BP Neural Network
This paper chose 11 financial criteria based on the principle for criteria selection. Due to the relevance of criteria, this paper collected 5 common factors with the method of principal component analysis of factor. The comprehensive score of every sample is got from the score of every common factor. Considering whether enterprises are special treated as auxiliary reference, 3 ranges of score are divided into 3 financial status accordingly: health, focus, crisis, disregarding the division criteria of special treatment or otherwise.Finally, the network got trained and tested by regarding 5 common factor as input and the financial status as output. It is found that BP neural network has a good prediction ability, high accuracy and application value, which will give a great assistance to the development of capital market in our country.BP: financial crisis warning, empirical analysis, factor analysis, BP neural network.