基于IDNPSO-BP神经网络的股票市场指数预测

针对动态邻居粒子群算法的局限性，引入新的动态邻居拓扑结构，动态调整粒子群算法参数设置，提出改进的动态邻居粒子群算法(IDNPSO).为了提高BP神经网络模型的预测准确性，提出一种基于改进动态邻居粒子群算法的BP神经网络模型(IDNPSO-BP神经网络).利用IDNPSO-BP神经网络和GA-BP神经网络对上证指数、深证指数进行预测，结果表明IDNPSO-BP神经网络的预测误差优于GA-BP神经网络，具有股票市场指数预测能力.

Stock Market Index Forecasting Based on IDNPSO-BP Neural Network

An improved dynamic neighborhood particle swarm optimization (IDNPSO) was proposed. A new topological structure which constructs dynamic neighbors was induced， and the parameter settings were dynamically adjusted. To improve the predictive accuracy of BP neural network， an improved prediction method of optimized BP neural network based on IDNPSO was introduced. Making use of the index price of Shanghai composite index and Shenzhen composite index， comparison of the forecast performance between IDNPSO BP and GA BP neural networks was taken. The result showed that INDPSO BP neural network outperformed GA BP neural network， and had the ability to forecast stock index price.