Credit scoring model based on radial basis function network

The paper establishes a credit evaluation model of listed companies based on radial basis function network. The model is applied to classify 96 listed companies of China respectively. The 96 data are separated into three groups according to their finance and management: a "good" group, a "middle" group and a "bad" group. For each listed company, we mainly consider four finance indexes which are earning per share, net assets per share, return on equity and cash flow per share. The simulations show that, to the model based on radial basis function network, the classification accuracy rate is 98.96%, which is higher than that of West\´s model (87.24%).