A Study of Chinese Stock Price Prediction Based on LSTM and Time Series Linear Regression Model

With the advancement of technology and the increasing popularity of machine learning, new opportunities have emerged across various industries. In the financial sector, an increasing number of individuals are attempting to utilize machine learning to enhance the accuracy of stock price predictions. This paper will also endeavor to apply the LSTM model for predicting the stock prices of companies listed on the main boards of the Chinese stock market, while simultaneously comparing it with traditional time series linear regression model. Against the highly complex backdrop of the stock market, this paper aims to explore whether machine learning can surpass traditional models in achieving superior predictive results. However, in this research, the result did not show that LSTM overperform significantly linear regression model due to completely different economic and political background and limited parameters used. In order to improve the accuracy and stability of LSTM, it might be considered to incorporate additional influencing factors and combining with other models for market prediction.