Integrating Independent Component Analysis and Principal Component Analysis with Neural Network to Predict Chinese Stock Market

摘要

We investigate the statistical behaviors of Chinese stock market fluctuationsby independent component analysis. The independent component analysis (ICA)method is integrated into the neural network model. The proposed approach usesICA method to analyze the input data of neural network and can obtain the latentindependent components (ICs). After analyzing and removing the IC that representsnoise, the rest of ICs are used as the input of neural network. In order to forectthe fluctuations of Chinese stock market, the data of Shanghai Composite Index isselected and analyzed, and we compare the forecasting performance of the proposedmodel with those of common BP model integrating principal component analysis(PCA) and single BP model. Experimental results show that the proposed modeloutperforms the other two models no matter in relatively small or relatively largesample, and the performance of BP model integrating PCA is closer to that of the proposedmodel in relatively large sample. Further, the prediction results on the points wherethe prices fluctuate violently by the above three models relatively deviate from thecorresponding real market data.