Stock transaction point prediction method and system based on minimum entropy score, and storage medium

Abstract

The invention discloses a stock transaction point prediction method and system based on a minimum entropy score, and a storage medium. The method comprises the steps: obtaining stock data, obtaining the technical indexes of a plurality of transaction days according to the stock data, and constructing an index matrix according to the obtained technical indexes; calculating a future return rate according to the stock data, obtaining a trend grade according to the future return rate, and obtaining a data matrix in combination with the trend grade and the index matrix; mining a stock trend mode ofthe data matrix by adopting a biclustering algorithm based on a minimum entropy score to obtain a transaction rule; and predicting transaction operations in combination with the transaction rules anda preset neural network, wherein the transaction operations include selling, no operation and buying. According to the method, the biclustering algorithm based on the minimum entropy score can effectively help to find transaction information and rules hidden behind stock historical data, transaction prediction information with high reference value can be provided for investors, and the method canbe widely applied to prediction of stock market transaction operation.

Description

technical field [0001] The invention relates to a forecasting technology for stock market trading operations, in particular to a stock trading point forecasting method, system and storage medium based on minimum entropy scores. Background technique [0002] Affected by macroeconomic factors, investor psychology, company operating conditions, government policies, supply and demand, and other factors, stock prices often have greater volatility. When investors carry out such high-risk and high-yield stock transactions, they are more likely to suffer economic damage due to the uncertainty of the stock market. Stock forecasting is based on the factors that affect stock price fluctuations to predict the development direction of the stock market and the trend of stock price changes. With the increasing improvement of the stock market, scientific and reasonable stock forecasting methods can guide investors to trade stocks and obtain the highest returns with the least risk; at the s...

AI Technical Summary

Problems solved by technology

The basic analysis method estimates the investment value of listed companies by analyzing massive data, and makes a decision after comparing and analyzing the current company stock prices. This method requires a comprehensive understanding of the investment company, and the algorithm is more difficult. Large and not sensitive to the stock market; technical analysis methods include K-line chart method, wave theory, etc., such methods can only predict the stock price change trend within a period of time, with a certain degree of lag; time series method Including autoregressive moving average model, generalized autoregressive conditional heteroscedastic model, etc., by using the correlation between stock data to predict the stock market, because the stock market has strong nonlinearity and large fluctuations, its internal laws are often difficult to use Simple representation of time series, thus poor forecasting performance

Images