Stock prediction method, device and apparatus based on depth learning and storage medium

Abstract

The invention discloses a stock prediction method based on depth learning, which includes: obtaining the latest transaction data for the target stock and associated stock, generating a multi-dimensional feature matrix corresponding to the latest transaction data, inputting a multi-dimensional characteristic matrix corresponding to the latest transaction data into a composite neural network for processing, obtaining a prediction result of the target stock. The invention also discloses a stock prediction device based on depth learning, stock prediction apparatus and storage medium based on in-depth learning; the invention firstly utilizes the convolution neural network of the composite neural network to learn the characteristics of the transaction data of the target stock and the associatedstock, Features are input into the composite neural network of short-term and long-term memory network for processing, and the prediction of the stock price rise and fall is obtained. A stock forecastmethod based on depth learning and swarm intelligence is provided, which can accurately forecast the stock price rise and fall.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a deep learning-based stock forecasting method, a deep learning-based stock forecasting device, a deep learning-based stock forecasting device, and a computer storage medium. Background technique [0002] Stock forecasting refers to the use of stock-related information to predict its ups and downs in the future; deep neural networks have been widely used in image processing or natural language processing, but the research and application in the field of stock forecasting has just started. start. [0003] LSTM is a long-term short-term memory network, which is a special RNN structure, which is used to solve the long-term dependence problem in sequence problems. In the prior art, there is a stock forecasting algorithm based on the LSTM model, which extracts key features of market information, is suitable for sequential data with strong periodicity, and solves the problem...

AI Technical Summary

Problems solved by technology

[0006] The main purpose of the present invention is to provide a stock forecasting method based on deep learning, a stock forecasting device based on deep learning, a stock forecasting device and a computer storage medium based on deep learning, aiming at solving the problem of using only market information in the prior art instead of Real transaction data predicts stocks, its accuracy is not high, and technical problems with low practical application value

Images