A k-means++-improved radial basis function neural network model for corporate financial crisis early warning: an empirical model validation for Chinese listed companies

Danyang Lv, Chong Wu and Linxiao Dong

Abstract

An early warning of corporate financial crises has long been the focus of investors and enterprises. Integrated early warning models for financial crises perform better than normal models, but most integrated models are very complex, elusive and computationally time-consuming. This paper aims to simplify the early warning model for financial crises by collecting and analyzing the financial data of Chinese special treatment (ST) companies, normally listed companies and cancel special treatment (CST) companies. To further predict the financial risks of companies, we put forward a finance-predicting model based on the k-means++ algorithm and an improved radial basis function neural network (RBF NN), and we compare their respective statistics. We indicate by experiment that combining k-means++ with the improved RBF NN helps to better predict financial risks for companies, which is effective in the risk control of financial management.