Chaotic Data Prediction and Its Applications in Stock Market Based on Embedding Theory and Neural Networks
Zhang Zong-ping · Systems Engineering - Theory & Practice · 2001
This paper provides a method for predicting chaotic data with combining embedding theory and artificial neural networks. We discuss methods for calculating embedding dimension and embedding time delay and, from the view of signal processing, analyze the relationship between phase space reconstruction and prediction, with which the structure of the input layer of neural networks can be determined.Stock market prediction is implemented with the method provided here.The result showed that this method is widely applicable to the field of nonlinear signal processing.