Application Research of BP Neural Networks Model in Financial Crisis Prediction
Lin Ding, Wenjun Liu · ICISEM '13 Proceedings of the 2013 International Conference on Information System and Engineering Management · 2013
This paper employs the method of BP neural networks for financial crisis prediction. By analyzing the data of China's listed real estate companies from 2003 to 2012, the paper explores the improvement of application processes to find out the best BP neural networks model for financial crisis prediction. We find that it is better to apply one specific calculation method into BP neural networks model than to use all of them. And accuracy of prediction about setting one hidden layer is better than two layers. We also find a series of ratios which are closely related to financial crisis prediction. They are net profit margin on sales, ROE, return on total assets ratio, ratio of total liability to equity market price, and inventory turnover ratio.