本文基于数学模型考证股指波动的历史类似性,针对2005-2016年上证综指数据,利用神经网络算法对上证综指的走势进行了分析。以开盘价、最高价、最低价、成交量、成交金额5个指标作为BP神经网络的输入值,以收盘价作为输出值。对我国股票市场走势的“历史类似性”进行分析。 This article studies the historical similarities of stock index volatility based on mathematical models. According to the data of Shanghai Composite Index from 2005 to 2016, this paper analyzes the trend of Shanghai Composite Index by using neural network algorithm. Taking the opening price, the highest price, the lowest price, the volume and the turnover amount as the input values ​​of the BP neural network, the five indexes as the closing value are taken as the output values. Analyze the Historical Similarity of the Stock Market in China.