论文部分内容阅读
财务危机预测是金融管理决策中的重要问题,其实质是对未来财务状况的预报和分类。鉴于目前单一分类器预测性能不稳定,本文运用分类器集成技术,以BP神经网络为分类学习算法,建立基于RS-Bag算法的神经网络分类器集成模型。然后,以我国上市公司财务数据为例进行财务危机预测实证研究,结果表明,基于RS-Bag算法的神经网络分类器集成预测精度和泛化性能优于单一神经网络分类器,也优于Bagging分类器集成和RS分类器集成。
Financial crisis forecasting is an important issue in the financial management decision-making, and its essence is to forecast and classify the future financial status. In view of the current single classifier prediction performance is not stable, this paper uses classifier integration technology, BP neural network as a classification learning algorithm, the establishment of an integrated model of neural network classifier based on RS-Bag algorithm. Then, taking the financial data of listed companies in our country as an example, the paper studies the financial crisis prediction. The results show that the prediction accuracy and generalization performance of the neural network classifier based on RS-Bag algorithm is better than the single neural network classifier and also superior to the Bagging classification Integrated with RS classifier.