基于LSTM模型的股价分析及预测

Analysis and Forecast of Stock Price Based on LSTM Model

股价预测一直都是股票投资者重点关注和重点研究的方向。针对股价具有高度非线性、高噪声、动态性等问题,本文采用长短期记忆网络(LSTM)模型对股价进行预测。数据取自半导体行业公司股票价格,采用python深度学习框架构造长短期记忆网络模型,分别对每一组股票的开盘价进行预测,再通过均方误差和决定系数对预测结果进行评价。实验结果表明将LSTM神经网络用于股票价格预测具有较好的效果,可以为投资者提供一定的参考。

Stock price forecasting has always been the focus and research direction of stock investors. Aiming at the problems of high non-linearity, high noise and dynamics in stock prices, this paper uses a long short-term memory network (LSTM) model to predict stock prices. The data is taken from the stock prices of companies in the semiconductor industry, and a long- and short-term memory network model is constructed using the python deep learning framework to predict the opening price of each group of stocks, and then the prediction results are evaluated through the mean square error and the coefficient of determination. The experimental results show that the use of LSTM neural network for stock price prediction has a good effect, and it can provide a certain reference for investors.