Stock transaction method and system based on reinforcement learning algorithm and time sequence model

Abstract

The invention relates to the field of deep reinforcement learning and financial quantitative transaction, in particular to a stock transaction method and system based on a reinforcement learning algorithm and a time series model, and the method comprises the steps: data preprocessing, sorting collected stock data according to categories, filtering wrong data and repeated data, normalizing the data, and after preprocessing is completed, obtaining a stock data set; establishing a time sequence model to predict a stock price, dividing a stock basic price data set, establishing and training a time sequence GRU model which can be used for stock basic price data, and outputting a stock prediction price; enabling the stock transaction reinforcement learning model to output a decision, and adopting a PPO algorithm to train an intelligent agent to obtain the reinforcement learning model applied to the stock transaction so as to output an action decision of the stock transaction. According to the invention, information hidden in stock basic data can be fully mined, a reasonable transaction decision is made in a stock transaction environment, and a reference is provided for real stock transaction related personnel.

Description

technical field [0001] The invention relates to the fields of deep reinforcement learning and financial quantitative trading, and in particular to a stock trading method and system based on reinforcement learning algorithms and time series models. Background technique [0002] In recent years, with the widespread popularization of financial knowledge and the rapid promotion of financial products, people's awareness of financial investment has increased, and their participation in financial product investment has increased. Many of them are investors or related practitioners who conduct stock transactions. Since the rate of return of financial products, especially stock trading, is higher than that of general investment products, investors need to bear higher investment risks. Therefore, making reasonable and effective decisions in the process of stock trading, that is, performing appropriate operations at the right time, such as buying or selling a certain percentage of stoc...

AI Technical Summary

Problems solved by technology

[0003] However, the current Internet financial websites and terminal programs provide stock information such as the current stock price, the highest and lowest price of the trading day, the opening and closing prices of the trading day, trading volume, price-earnings ratio and other basic data, Historical information, without statistical integration of information, has limited use value, and it is difficult for investors to obtain sufficient information value from it

In addition, the qualitative analysis provided by self-media and economic analysts related to financial products, and the quality of stock trend forecasts vary, so investors are easily influenced by their subjectivity, and it is difficult to make reasonable trading decisions

Images