Listed Company Reorganization Risk Evaluation Based on Neural Network Model

摘要

The reorganization of listed company is a complicated system engineer with great risk. While aiming at risk characteristics of listed company reorganization, this paper builds up evaluation index system of listed company reorganization risk, designs risk evaluation model based on variable structure neural network of re-linking random process, trains the model by using 10 cases of listed company reorganization and assess the reorganization risk of four listed company. The result shows that the average relative error of the model is 2.44 %, and the largest relative error is 2.96 %, which means that the model has a preferable prediction result.