Research on Stock Trading Strategy Based on Deep Reinforcement Learning

Abstract

The stock market occupies an important position in the country's overall economic system, and changes in the stock market affect the investment returns of investors and investment institutions. With the advancement of science and technology and the development of the economic market, the price trend of stocks is disturbed by more and more factors, and the traditional forecasting method is becoming more and more difficult to meet people's requirements. Among them, the stock price time series as a dynamic, irregular, non-linear, non-parameterized complex data, brings great challenges to stock price prediction, so The study proposed to use CNN and LSTM models to predict stock prices. First, the data features are extracted using the CNN network structure, and then the stock price is predicted using LSTM. Experiments have proved that the model can be successfully applied to the study of stock forecasting and has a high accuracy in forecasting.