Stock price fluctuation prediction model and device based on media information tensor supervised learning

A technology of supervised learning and media information, applied in the field of stock price fluctuation prediction models and devices, which can solve the problems of low stock price fluctuation prediction accuracy and achieve good stock price prediction results

Pending Publication Date: 2021-08-13
SOUTHWESTERN UNIV OF FINANCE & ECONOMICS
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention provides a stock price fluctuation prediction model and device based on media information tensor supervised learning, and builds a model based on people's social behavior and psychological information to solve the problem of low accuracy in the existing stock price fluctuation prediction

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 price fluctuation prediction model and device based on media information tensor supervised learning
  • Stock price fluctuation prediction model and device based on media information tensor supervised learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Embodiments of the present invention provide a method for predicting (and displaying) stock price fluctuations based on media information tensor supervised learning, such as figure 1 shown, including:

[0043] S1. Collect market transaction information, media news information, and investor emotional information;

[0044] Further, the market transaction information comes from the basic data of the company, such as the transaction price of the stock, the size of the company, the number of transactions and other information, which can reflect the current operation of the company from the perspective of data. News media information comes from daily stock news, which includes the basic situation of the company, allowing investors to obtain rich information and a comprehensive understanding of the company's situation, including negative or positive content, which can easily affect investors' irrational investment. Investor sentiment information comes from social media such a...

Embodiment 2

[0062] Another embodiment of the present invention provides a stock price fluctuation prediction device based on media information tensor supervised learning, such as figure 2 shown, including:

[0063] memory for storing any of the instructions required to enable the apparatus to execute a predictive model;

[0064] Processors, at least one processor, configured to execute executable instructions stored in the memory.

[0065] The display is based on the ergonomic principles related to visualization to display the market information collected by the device and the results predicted by the model.

[0066] The background of the page displaying the collected market transaction information, media news information, and investor sentiment information is mainly black, and the font color is blue. The black background is less irritating to the eyes, and it is more conducive to preventing myopia when doing a lot of reading work. And blue gives people a sense of calmness, wisdom and...

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 provides a stock price fluctuation prediction model based on media information tensor supervised learning. The stock price fluctuation prediction model comprises the following steps: S1, collecting market transaction information, media news information and shareholder emotion information; s2, preprocessing the collected information; s3, constructing a tensor based on the preprocessed information; s4, performing tensor decomposition and reconstruction on the constructed tensor; s5, based on the market transaction information and the reconstructed tensor, utilizing a tensor supervised learning algorithm to train and predict share price fluctuation; s6, basic information visualization: displaying the collected market transaction information, media news information and shareholder emotion information by taking a black background and blue fonts as main parts, wherein the stock price fluctuation prediction result is visualized, the background of a result page predicted by the display model is mainly white, the color of a curve of a rising part in stock price fluctuation is red, and the color of a curve of a falling part in the price is blue.

Description

technical field [0001] The invention relates to the fields of natural language processing, quantitative analysis and ergonomics, in particular to a stock price fluctuation prediction model and device based on media information tensor supervised learning. Background technique [0002] With the development of information technology, Internet media has gradually become the mainstream media form. Especially with the rise of social media such as blogs, Weibo, social news, Wikipedia and online forums, their media influence is increasing day by day. Massive information and fissile communication make Internet media have a decisive impact on the stock market. [0003] In the prior art, when predicting stock price fluctuations, most of them consider structured information, such as stock trading prices, while ignoring unstructured information, such as company news, etc., resulting in inaccurate stock price fluctuation predictions. This is because words often reflect a person's emotio...

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): G06Q40/04G06Q30/02G06N20/00
CPCG06Q30/0201G06Q30/0203G06Q40/04G06N20/00
Inventor 李庆王俊谭晶桦蒋李灵
Owner SOUTHWESTERN UNIV OF FINANCE & ECONOMICS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products