Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Stock rise and fall prediction technical method combining LSTM and attention mechanism

A forecasting technology and attention technology, applied in forecasting, neural learning methods, data processing applications, etc., can solve the problems of not considering the reliability of stock evaluation opinions, not capturing the time sensitivity of news information in a timely manner, and achieving intuitive and comprehensive information. , enhance interpretability, the effect of interpretability enhancement

Pending Publication Date: 2022-07-05
GUILIN UNIV OF ELECTRONIC TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The stock review information released on social media platforms also has a guiding effect on the rise and fall of stocks. Previous studies have used the overall market sentiment as a predictor. These methods neither capture the time sensitivity of news information in time, nor take into account the stock review opinions. Reliability, so it needs to be further improved

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Stock rise and fall prediction technical method combining LSTM and attention mechanism
  • Stock rise and fall prediction technical method combining LSTM and attention mechanism
  • Stock rise and fall prediction technical method combining LSTM and attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0029] refer to figure 1 , a technical method for stock fluctuation prediction combining LSTM and attention mechanism, including the following steps:

[0030] Step 1: Make a stock dataset:

[0031] Step 11: Data collection: collect the raw data of stock factors, such as market capitalization factor, profit factor, growth factor, leverage factor, momentum factor, risk factor, style factor, industry factor, etc., and use the daily closing price of the stock as the stock price change to calculate Raw data, stock news information is used as the raw data of news features for the prediction of stock ups and downs;

[0032] Step 12: Make a stock factor data set: Divide the factor data according to a fixed duration, namely daily, weekly and monthly, and calculate the factor data values ​​within the fixed time interval as the index value, denoted as X r , to judge the rise and fall of the stock price in a fixed time, that is, the ratio of the closing price difference between the initia...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a stock rise and fall prediction technical method combining LSTM and an attention mechanism. The method comprises the following steps: step 1, making a stock data set; 2, stock factor data processing; 3, extracting features of the stock news text; step 4, feature fusion output; 5, training a stock rising and falling prediction model; and step 6, predicting. According to the method, the interpretability of a prediction result is enhanced, and information is visual and comprehensive.

Description

technical field [0001] The invention relates to LSTM and attention mechanism technology of deep learning, in particular to a technology method for stock price fluctuation prediction combining LSTM and attention mechanism. Background technique [0002] With the development of artificial intelligence technology, deep learning models represented by neural networks are widely used in financial asset price prediction and play an important role in investment decisions. At the same time, the financial investment industry, as an efficient industry in the economy and society, attaches great importance to the combination of the latest technology and financial practices, and strives for precise and intelligent high-tech operation models that are also favored by financial institutions. Therefore, the application of deep learning in the financial field also become a new research hotspot. [0003] The stock prediction technology based on deep learning liberates investors from the arduous...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q40/06G06Q10/04G06N3/04G06N3/08
CPCG06Q40/06G06Q10/04G06N3/049G06N3/08
Inventor 丁勇苏子秋梁海
Owner GUILIN UNIV OF ELECTRONIC TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com