Research on Stock Price Analysis and Forecasting of Listed Companies Based on Time Series and Neural Network Models

The stock price prediction of listed companies and the analysis of influencing factors are the core topics of this paper. As of the end of June 2022, the number of A-share investors in my country reached 206.2391 million, of which 1.3303 million new investors were added in June 2022, an increase of 10.6% month-on-month. At the same time, stock price forecasting is a key topic of common concern in financial research and quantitative investment. Stock price forecasting is the use of mathematical models to predict the future trend of stock prices. The purpose of this paper is to study the data characteristics of stock prices. This paper constructs different analysis models, and interprets and analyzes the research results from a financial perspective. Explore the time-varying correlation between policies and regulations and BYD's stock price, and use the LSTM model to predict the future stock price, and build the LSTM-ARIMA model to improve the prediction accuracy; The stock price on December 31, 2023, and then aiming at the shortcomings of the LSTM model, construct an LSTM-ARIMA model to improve the forecasting effect. The final trend chart shows that the stock price will fall to a certain extent in the first half of 2023, and will show a steady upward trend in the future.