Financial Crisis Prediction Based on Intelligent Algorithm

Abstract

The typical intelligent algorithm based financial crisis prediction is the neural network. But training time of the neural network is too long to apply to the actual system. The paper applies the rough set theory into the artificial neural network based financial crisis prediction. The paper proposes an improved neural network algorithm. The rough set theory is used to reduce the financial indexes and samples. The numbers of inputs and training samples are decreased and the training time of neural network is shortened. The empirical analysis shows that the method can obviously accelerate the training speed of the neural network.