Research on Credit risk Evaluation Model based on Self-Organizing Feature Map Neural Network
In this paper, we have established a credit risk evaluation model based on Self-Organizing Feature Map neural network. The model is used to identify two patterns samples of listed companies of our country, including train samples of 285 listed companies(59 companies with special treatment and 226 normal companies) and test samples of 117 listed companies(29 companies with special treatment and 88 normal companies). The two patterns mean that the listed companies are divided into two groups according to their business conditions: one is credit default group (ST and *ST listed companies) and the other is credit non-default group (normal listed companies). To each listed company, 4 main financial indexes are considered: earning per share, net asset per share, return on equity, cash 皁w per share. The simulating results showed that, when the neural network is only trained 20 steps, it enters steady state. To the 402 samples, one sample is of erroneous judgment. The misjudgment ratio is 0.25％ and the overall discriminant accuracy rate is 99.75％. This indicates the credit risk evaluation model based on self-Organizing Feature Map neural network we established is able to result in good classification and recognition effects and is of certain of research value to the reality.
Le Lei Sulin Pang Gang Hao Jiang Ma
Department of Accountancy and Mathematics Jinan University Guangzhou, China 510632 Department of Management Sciences City University of Hong Kong Hong Kong, China 999077
国际会议
南宁
英文
2007-07-20（万方平台首次上网日期，不代表论文的发表时间）