基于粒子群优化BP神经网络的上市公司财务风险预测研究

发布时间：2018-03-29 05:12

本文选题：财务风险预测　切入点：BP神经网络　出处：《东华大学》2017年硕士论文

【摘要】：在“互联网+”的时代,世界经济日益全球化和信息化,企业的生产经营环境瞬息万变,我国企业的经营发展面临着前所未有的机遇,但同时也饱受环境因素的制约,经济市场因素、法律法规因素、社会文化因素、政策环境因素等变化莫测的环境因素,都给企业的财务状况带来了不确定性,企业所面临的财务风险日益加大。目前,很多企业仍没有从经济危机的阵痛中恢复过来,外部环境恶化,内部管理混乱,资产流失严重,资金链出现问题,财务状况也令人堪忧,而企业的整体发展与自身的财务风险状况的处理是紧密联系的。大多数企业后期遭遇严重的财务危机,甚至破产,是因为对早期出现的财务问题没有给予足够的重视,并及时采取有效的手段处理危机状况,这对企业的后续发展是及其不利的。因此,关于企业财务风险状况的研究越来越受到重视。本文主要通过分析上市公司财务风险的相关理论,并结合主成分分析法、粒子群优化算法(PSO)和人工神经网络的原理,得出我国上市公司的财务风险指标体系。为提高财务风险预测的准确性,运用主成分分析和粒子群算法优化BP神经网络模型,改进了预测模型的输入数据,利用粒子群算法寻优赋予BP神经网络最优的初始权值和阈值,据此构建了粒子群优化BP神经网络(PSO-BP)的财务风险预测模型。以我国的上市公司财务指标数据为样本集进行仿真研究,结果表明,相较于传统的财务风险预测模型,PSO-BP模型的预测精度更高。
[Abstract]:In the era of "Internet", the world economy is becoming more and more global and information, and the production and management environment of enterprises is changing rapidly. Chinese enterprises are faced with unprecedented opportunities for business development, but at the same time, they are also restricted by environmental factors. The unpredictable environmental factors, such as economic market factors, laws and regulations, social and cultural factors, and policy and environmental factors, all bring uncertainty to the financial situation of enterprises, and the financial risks faced by enterprises are increasing day by day. At present, Many enterprises still have not recovered from the pain of the economic crisis, the external environment has deteriorated, the internal management has been chaotic, the assets have been lost seriously, the financial chain has had problems, and the financial situation is also worrying. However, the overall development of the enterprise is closely related to the handling of its own financial risk. Most enterprises experience serious financial crisis or even bankruptcy in the later period because they do not pay enough attention to the financial problems that occurred in the early period. And to take effective measures to deal with the crisis situation in time, which is unfavorable to the subsequent development of enterprises. More and more attention has been paid to the research on the financial risk of enterprises. This paper mainly analyzes the related theories of financial risk of listed companies, and combines the principal component analysis, particle swarm optimization algorithm (PSO) and the principle of artificial neural network. In order to improve the accuracy of financial risk prediction, the BP neural network model is optimized by using principal component analysis and particle swarm optimization algorithm, and the input data of the prediction model are improved. Particle swarm optimization is used to optimize the initial weights and thresholds of BP neural networks. Based on this, a PSO BP neural network model for financial risk prediction is constructed. The financial index data of listed companies in China are taken as the sample set. The results show that the financial risk prediction model of PSO-BP neural network is based on PSO-BP neural network. Compared with the traditional financial risk forecasting model, PSO-BP model is more accurate.
【学位授予单位】：东华大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：F275;F832.51

【相似文献】