DocumentCode :
480238
Title :
Financial Distress Prediction Study with Adaptive Genetic Fuzzy Neural Networks on Listed Corporations of China
Author :
Xiong, Zhibin
Author_Institution :
Sch. of Math. Sci., South China Normal Univ., Guangzhou
Volume :
4
fYear :
2008
fDate :
12-14 Dec. 2008
Firstpage :
898
Lastpage :
901
Abstract :
Neural networks (NNs) have been widely used to predict financial distress because of their excellent performances of treating non-linear data with self-learning capability. However, the shortcoming of NNs is also significant due to a ldquoblack boxrdquo syndrome. Moreover, in many situations NNs more or less suffer from the slow convergence and occasionally involve in a local optimal solution, which strongly limited their applications in practice. In this paper, a hybrid system combining fuzzy neural network and adaptive genetic algorithm - adaptive genetic fuzzy neural network (AGFNN) is proposed to overcome NNpsilas drawbacks. Furthermore, the new model has been applied to financial distress analysis based on the data collected from a set of Chinese listed corporations, and the results indicate that the performance of AGFNN model is much better than the ones of BPNN model and FNN model.
Keywords :
backpropagation; convergence; financial data processing; fuzzy neural nets; fuzzy reasoning; genetic algorithms; Chinese listed corporation; adaptive genetic fuzzy neural network; back-propagation; black box syndrome; convergence; financial distress prediction; fuzzy rule partition; reasoning mechanism; self-learning capability; Adaptive systems; Artificial intelligence; Computer science; Fuzzy logic; Fuzzy neural networks; Fuzzy sets; Genetic algorithms; Input variables; Neural networks; Predictive models; adaptive genetic BP algorithm; financial distress; fuzzy neural networks;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Science and Software Engineering, 2008 International Conference on
Conference_Location :
Wuhan, Hubei
Print_ISBN :
978-0-7695-3336-0
Type :
conf
DOI :
10.1109/CSSE.2008.715
Filename :
4722763
Link To Document :
بازگشت