The use of fuzzy clustering algorithm and self-organizing neural networks for identifying potentially failing banks: an experimental study

In this paper, we present experimental results of fuzzy clustering and two self-organizing neural networks used as classification tools for identifyin g potentially failing banks. We first describe the distinctive characterist ics of fuzzy clustering algorithm, which provides probability of the likeli hood of bank failure. We then perform the comparison between the results of the closest hard partitioning of fuzzy clustering and of two self-organizi ng neural networks and present our results as the ranking structure of rela tive bankruptcy likelihood. Our findings indicate that both the fuzzy clust ering and self-organizing neural networks are promising classification tool s for identifying potentially failing banks. (C) 2000 Elsevier Science Ltd. All rights reserved.