基于BP神经网络和面板数据上市公司财务危机预警_杨淑娥.pdfVIP

　2007 2 2 　 :1000-6788(2007)02-0061-07 BP 1 2 杨淑娥 , 王乐平 (1., 201620;2. , 710049) :　, T-2 、T-3 (panel data) , BP ., 1) BP 、, , ;2)3 4 88.46%75.64 %, . :　;;BP ; :　F275.5　　　　　　　　:　A 　　　 Research on Financial Warning or Listed Companies by Using BP Neural Networks and Panel Data 1 2 YANG Shu-e , WANG Le-ping (1.Shanghai Institute o Foreigh Trade, Shanghai 201620, China;2.Xian Jiaotong University, Xi an 710049, China) Abstract:　On the basis o the authors previous research and with the introduction o panel data, this paper constructed a BP neural networks model to predict the inancial status o listed companies, by taking panel data composed o the inancial data o T-2 and T-3 as the sample.The research indicates that:1)with panel data, the BP neural netw orks w arning analysis is o stable and continuou s predictability, which is suitable in constructing practical mid-term and long-erm prediction models to make the model more applicable;2)the predictability precision is 88.46% and 75.64 % or T-3 and T-4, respectively, superior to that o counterparts and the previou s research. Key words:　inancial distress;panel data;BP neural netw orks;early w arning 1 　 , , 、 ., , , .20 , 40 .10 ., , ., , .2005 1 PB [1] , 1 2 ., ;, T-2 、T-3 BP . , BP 、, . 2 　 :2005-06-28 :“AIS ”70672053) 　　:, , , :;, , :. 62 2007 2 [2] Beaver(1966 ) .30 1 ～5 , 87 %、79%、77 %、76%、78%., , , .Altman (196