Stock trend prediction method based on multiple characteristic indexes

A trend prediction and multi-feature technology, applied in the field of data analysis, can solve problems such as less consideration of different text weights and fuzzy criteria for network news classification, and achieve the effect of improving accuracy

Pending Publication Date: 2022-07-01
CAPITAL UNIV OF ECONOMICS & BUSINESS
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the existing research, there is still less consideration of the weight between different texts, and the criteria for the classification of online news are also relatively vague.

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 trend prediction method based on multiple characteristic indexes
  • Stock trend prediction method based on multiple characteristic indexes
  • Stock trend prediction method based on multiple characteristic indexes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] This embodiment discloses a stock trend prediction method based on multi-feature indicators, such as figure 1 ,include:

[0033] S100. Obtain stock historical data and technical indicator data sets, stock bar comment data sets and news text data sets; specifically, such as figure 2 , this embodiment is based on a multi-feature system for stock trend prediction, and all features can be divided into two aspects: financial market and investor sentiment. According to the degree of structuring of features, financial market data is a structured feature, including stock price data and technical indicator data; investor sentiment is an unstructured feature, including news text data and stock bar text data.

[0034] S200. Process the stock historical data and technical indicator data set, stock bar comment data set and news text data set according to different preset rules respectively, and obtain the processed stock historical data and technical indicator data set, investor s...

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 trend prediction method based on multi-feature indexes. The method comprises the following steps: acquiring stock historical data and technical index data sets, stock bar comment data sets and news text data sets; processing the stock historical data and technical index data set, the stock bar comment data set and the news text data set according to different preset rules to obtain a processed stock historical data and technical index data set, an investor emotion index and a news emotion quantity index; and inputting the processed stock historical data, the technical index data set, the investor emotion index and the news emotion quantity index into an AT-LSTM model to predict the stock trend. According to the stock trend prediction method, a weighted emotion index construction method is provided through an SKEP emotion analysis technology, a news classification criterion is formulated, and the accuracy of stock trend prediction at the present stage is improved.

Description

technical field [0001] The invention relates to the field of data analysis, in particular to a stock trend prediction method based on multi-feature indicators. Background technique [0002] From the perspective of behavioral finance, numerous studies have demonstrated that investor sentiment can affect the stock market. Shiller et al. even found that emotional influence on investor behavior was the main cause of the October 1987 stock market crash. Chaffai et al. explored the influence of investors' emotional and psychological factors on the Tunisian stock market. From the perspective of investment returns, there are numerous studies proving that investor sentiment indices can be used to predict stock returns. Wurgal et al. found that new stocks, small-cap stocks, lower-yielding stocks, high-volatility stocks and distressed stocks have higher follow-up returns when initial sentiment indicators are low, and proposed a 12-point prediction of stock returns from an investment ...

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): G06Q10/04G06Q40/04G06F16/35G06N3/04G06N3/08
CPCG06Q10/04G06Q40/04G06F16/35G06N3/08G06N3/044
Inventor 邱月陈炜陈振松宋哲玮
Owner CAPITAL UNIV OF ECONOMICS & BUSINESS
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap