Reaserch on Improved ART-2 Neural Network in Enterprise Group Credit Risk Identification

摘要

In this paper,an improved algorithm of ART-2 neural network is applied on the research of enterprise group credit risk identification and finally obtains better empirical results by taking some enterprise groups in China's Shanghai and Shenzhen stock markets from 2010 to 2011 as the study sample.The results show that the improved ART-2 neural network algorithm is more accurate than traditional logistic method and other neural network methods in the identification of group enterprise credit risk.