Research of financial crisis prediction based on FCM-PCA-SVM model

Financial crises prediction is an important and widely studied topic in the last three decades. Recently, the support vector machine (SVM) has been applied to the problem of financial crises prediction. Fuzzy c-means clustering (FCM) is among considerable techniques for data reduction. In addition, principal component analysis (PCA) is a powerful technique for feather extraction. This paper proposes using fuzzy c-means clustering algorithm, principle component analysis to make SVM more effective. The structure proposed in this paper, FCM-PCA-SVM composed of three subnetworks: fuzzy classifier, layer of feather extraction with principal component analysis and support vector machine. Empirical results using Chinese listed companies show that the hybrid model is very promising for financial crises in terms of predictive accuracy.