基于灰色粒子群神经网络的期货价格预测

here were existed some problems in the price forecast by BP neural network in light of Chinese futures’ market.This paper optimize the model of BP neural network from the input and parameters of network. First in order to identify important factor in the network’s input, use grey correlation analysis to filtrate input variables. Then the particle swarm optimization algorithm was used to optimize the parameters of BP neural network, after the network was optimized then used the model to forecast futures price. The simulation results showed that optimized BP neural network model in the speed and accuracy of forecasts is superior to simple BP neural network model.