比较分析深度学习方法在沪深300指数价格预测的研究

Comparative Analysis of Deep Learning Methods in the Price Prediction of the Shanghai and Shenzhen 300 Index

沪深300指数价格变动反映市场股票价格变动趋势,是投资者最关注的问题之一。如何构建合适的模型拟合价格时间序列变成了解决这一问题的关键之处。本文探究了不同深度学习方法对于价格的预测情况,分析得到几点探索性建议。实证分析中,数据选择沪深300指数2016年3月至2021年3月的价格数据,包括每日开盘价、最高价、最低价、收盘价四个数据特征共1218条数据,并对不同模型预测结果通过评价性指标进行对比分析。结果表明,对于数据信息利用更充分的模型,预测效果更好。

The price change of the CSI300 price Index reflects the trend of market stock price changes, which is one of the most concerned issues for investors. How to build a suitable model to fit the price time series has become the key to solving this problem. This article explores the price predictions of different deep learning methods, and acquires several exploratory suggestions. In the empirical, this paper takes the CSI300 price index as the research object and the data from March 2016 to March 2021 is selected, including daily opening price, highest price, lowest price and closing price, with a total of 1218 data. Comparing and analyzing the prediction results of different models through evaluative indicators show that Models with more adequate use of data and information provide better prediction results.