基于相关分析-BP神经网络的股价预测

Prediction Model of Stock Prices Based on Relativity Analysis and Neural Networks

神经网络的最大优点在于对复杂的系统不需要清楚的知道其内部机理,只要确定其输入输出变量,就可以构造一个网络模型来模拟这个系统.基于此,本文提出采用相关分析技术对输入变量做预处理,优选输入变量.分别建立未经预处理的网络预测模型和本文提出的模型,通过实验对比,本文模型具有更高的预测准确度.

The greatest strongpoint of Neural networks is not clearly aware of the internal mechanisms of its complex system, as long as given inputs and outputs, it can simulate the system by the network model. Based on this point , the proposed method is to optimize the inputs through using the relativity analytical technology, then builds BP neural network forecasting model and relativity analysis and BP neural network forecasting model. The experiments show that the proposed method is efficient.