Title :
Bankruptcy prediction using connectionist and symbolic learning algorithms
Author :
Martineli, E. ; Diniz, H. ; de Carvalho, A.C.P.L.F. ; Rezende, S.O.
Author_Institution :
Dept. of Comput. Sci., Sao Paulo Univ., Brazil
Abstract :
This article describes the use of connectionist and symbolic learning algorithms in the problem of bankruptcy prediction. Data about Brazilian banks represented by 26 or 10 indicators of their current financial situation were used. The difference among the number of existent examples in the classes of bankrupt and nonbankrupt banks was livened up through the reduction of learning examples of the class of nonbankrupts and the addition of noise samples in the class of bankrupts
Keywords :
bank data processing; forecasting theory; learning (artificial intelligence); neural nets; noise; symbol manipulation; Brazilian banks; bankruptcy prediction; connectionist learning algorithms; symbolic learning algorithms; Artificial intelligence; Artificial neural networks; Backpropagation algorithms; Computational intelligence; Computer science; Economic forecasting; Laboratories; Machine learning algorithms; Noise reduction; Production;
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4859-1
DOI :
10.1109/IJCNN.1998.682276
