采用三层BP神经网络结构，输入层神经元数为5，隐含层神经元数为3，输出层神经元数为1，使用MATLAB编写。
将所给数据按14：1分为训练样本集，和测试样本集，经测试及分析，预测误差为0.1700，误差较小。
网络训练好后，输入前一天的6组数据，即：最高价、最低价、开盘价、收盘价、成交量，就能自动预测出后一天的收盘价。(The structure of three-layer BP neural network is adopted. The number of neurons in the input layer is 5, the number of neurons in the hidden layer is 3, and the number of neurons in the output layer is 1.

The data are divided into training sample set and testing sample set according to 14:1. After testing and analysis, the prediction error is 0.1700 and the error is small.

After network training, input six sets of data from the previous day, namely, the highest price, the lowest price, the opening price, the closing price and the volume, and then automatically predict the closing price of the next day.)