With the global crisis, bankruptcies have increased and bankruptcy prediction models have become more important. The purpose of this study is to actualize the prediction of Turkish bank bankruptcies with Neuro Fuzzy (NF). NF does not have the problems, which come from the assumptions of statistical methods, and, as in Artificial Neural Network (ANN), it has learning ability. At the same time, the model does not stay in a black box. The proposed NF bank bankruptcy prediction model's performance was compared with Multivariate Discriminant Analysis (MDA) and ANN. Besides getting the best prediction of accuracy from Neuro Fuzzy, in this study, the addition of the forerunner indicators on the decision making process can also be interpreted.
Birol Yildiz and Soner Akkoc. "Bankruptcy Prediction Using Neuro Fuzzy: An Application in Turkish Banks." Proceedings of the New York State Economics Association. vol. 3, September 2010, p. 143-154
BibTeX entry download