HUANG Hongyun,ZHU Jiaming*,ZHAO Yun,et al.Application of instructor-supervised Kohonen neural network based on factor analysis in corporate financial early warning[J].Journal of Yanbian University,2017,43(02):158-166.
基于因子分析的有导师监督型Kohonen神经网络在公司财务预警中的应用研究
- Title:
- Application of instructor-supervised Kohonen neural network based on factor analysis in corporate financial early warning
- 关键词:
- 因子分析; 有导师监督; Kohonen神经网络; 财务预警; 学习向量量化
- Keywords:
- factor analysis; supervised by supervisor; Kohonen neural network; financial early warning; leaing vector quantization
- 分类号:
- F275; TP183
- 文献标志码:
- A
- 摘要:
- 针对衡量公司绩效能力的财务指标众多,难以建立高效的公司财务预警系统问题,本文首先通过变异系数和相关系数对最为常用的衡量公司绩效的22项指标进行初步筛选和二次筛选,得到资产收益率、销售净利率、净资产收益率、留存收益与总资产比率、资产现金回收率、营运资本总资产比、经营性现金流量流动负债比、经营性现金流量债务总额比和净资产增长率等9项指标,然后利用因子分析将这9项指标划分为盈利能力、偿债能力和成长能力3个主因子,并以此建立一个按资产收益率层级划分的监督型主元Kohonen神经网络.利用Kohonen神经网络模型
- Abstract:
- Due to the large number of financial indicators to measure the performance of the company, this brings many difficulties to the establishment of the company’s financial early warning system. In this paper, we firstly screened the 22 most commonly used indicators through the variation coefficient and correlation coefficient, and getting the ratio of return on assets, net profit rate, return on net assets, retained earnings to total assets, capital recovery rate, working capital total assets ratio, operating cash flow current liabilities ratio, total operating cash flow debt and net assets growth rate of nine indicators. Then using factor analysis to divide these nine indicators into three main factors of profitability, solvency and growth capacity. The empirical results of 24 listed companies show that this model has a higher discriminant accuracy than the existing F-score model and BPNN model, which can effectively avoid the situation of rejection, so it has a higher application value in practice.
参考文献/References:
[1] Edward I Altman. A further empirical investigation of the bankruptcy cost question[J]. The Journal of Finance, 1984,39(1):1067-1089.
[2] 周首华,杨济华,王平.论财务危机的预警分析-F分数模式[J].会计研究,1996(8):25-27.
[3] 李吉林.基于F分数模型的上市公司财务危机预警系统研究[J].中小企业管理与科技(下旬刊),2010(6):72-74.
[4] 黄宏运,吴礼斌,李诗争.BP神经网络在股票指数预测中的应用[J].通化师范学院学报(自然科学版),2016(10):32-34.
[5] Chris Charalambous, Andrews Charitou, Froso Kaourou. Comparative analysis of artificial neural network models:application in bankruptcy prediction[J]. Annals of Operation Research, 2000,99(1):403-425.
[6] 高吉吉.基于BP神经网络模型的制造业上市公司财务预警研究[D].北京:北京交通大学,2015.
[7] 秦秀秀.基于BP神经网络的创业板上市公司财务预警研究[D].淮南:安徽理工大学,2015.
[8] 黄宏运,吴礼斌,李诗争,等.一种改进的IPSO-BP神经网络在股指预测中的应用——以上证综指为例[J].延边大学学报(自然科学版),2016,42(4):351-356.
[9] Xu Gang, Cai Yong, Song Xin, et al. A review of correlation, regression and multiple factors analysis methods[J]. Shanghai Kouqiang Yixue, 2004,13(5):426-429.
[10] 易跃明,梁戈夫.主成分分析和因子分析在财务诊断中的比较[J].会计之友(中旬刊),2010,5:30-34.
[11] 王庆丰,党耀国,王丽敏.基于因子和聚类分析的县域经济发展研究——以河南省18个县(市)为例[J].数理统计与管理,2009(3):495-501.
[12] Carosone F, Cenedese A, Querzoli G. Recognition of partially overlapped particle images using the Kohonen neural network[J]. Experiments in Fluids, 1995,19(4):225-232.
[13] Kohonen T. The self-organization maps[J]. Proc of IEEE, 1990,78(9):1464-1480.
[14] 麻书钦.基于Kohonen神经网络算法的网络入侵聚类算法的测试研究[J].中国测试,2013,4:113-116.
[15] Muhammad Nizam. Kohonen neural network clustering for voltage control in power systems[J]. Telkomnika,2010,8(2):115-116.
[16] Susanta Kumar Gauri. Control chart pattern recognition using feature-based learning vector quantization[J]. The International Journal of Advanced Manufacturing Technology, 2010,48(9):1061-1073.
[17] 刘彦文.上市公司财务危机预警模型研究[D].大连:大连理工大学,2009.
[18] 林海明.因子分析应用中一些常见问题的解析[J].统计与决策,2012(15):65-69.
备注/Memo
收稿日期: 2017-03-02 *通信作者: 朱家明(1973—),男,副教授,研究方向为应用数学与数学建模.
基金项目: 国家自然科学基金资助项目(11601001); 安徽高等学校省级自然科学基金资助项目(KJ2013Z001)