Market prediction method based on news corpus

A prediction method and news technology, applied in the field of information processing, can solve problems such as slow development, weak ability to extract emotional features of complex information, and inability to effectively eliminate noise

Active Publication Date: 2018-11-09
ZHONGAN INFORMATION TECH SERVICES CO LTD +1
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these existing technologies have the following disadvantages: On the one hand, traditional financial market investment methods lack the quantitative measurement of market sentiment, and lack the means to use market sentiment factors to predict the future trend of the market
On the other hand, the method of quantitative measurement of market sentiment is developing slowly. In the existing corpus sentiment judgment method, the feature tensor may be a very large sparse matrix, resulting in a very slow operation speed, and the ability to extract emotional features from complex information Relatively weak, can not effectively eliminate some noise
or not yet flexible enough to reflect specific market sentiments

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
  • Market prediction method based on news corpus
  • Market prediction method based on news corpus
  • Market prediction method based on news corpus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] Such as figure 1 Shown is a schematic flow chart of a basic implementation of a news corpus-based market forecasting method of the present invention, the method comprising the following steps:

[0075] S1: Obtain news corpus information, and preprocess the news corpus information;

[0076] S2: According to the news corpus information processed in S1, the first feature tensor is constructed in the form of two-dimensional information dimensions including news subjects and subject attitudes, and the second feature tensor is obtained in combination with the preset keyword dictionary;

[0077] S3: Extract emotional information according to the second feature tensor, and then calculate the public opinion factor α through several pieces of emotional information;

[0078] S4: Obtain the corresponding lagged T-period rate of return R according to the obtained public opinion factor α T , to predict the fluctuation range of future returns.

[0079] In this technical solution, o...

Embodiment 2

[0081] This embodiment is an enumeration of several preferred implementations based on the above-mentioned Example 1, and the following implementations can be implemented alone or in combination.

[0082] In some embodiments, the keyword dictionary is established by using historical corpus or manual operation. The keyword dictionary can be implemented in a preset manner, which can improve the efficiency of subsequent judgment processing steps. In some specific implementation manners, the input of keywords can be formed by acquiring historical corpus or by manual input.

[0083] For example, in some practical operations, when performing sentiment analysis on the corpus, it is necessary to extract K-order feature tensors from the corpus The dimension K of the feature tensor and the element value of each dimension are determined according to the algorithm adopted by the sentiment analysis module. The keyword dictionary is used to store the keywords and the logical relationship ...

Embodiment 3

[0103] This embodiment is an enumeration of several preferred implementations based on the above-mentioned embodiments, and the following implementations can be implemented individually or in combination.

[0104] In some embodiments, the construction method of the first feature tensor includes:

[0105] Obtaining the news corpus information, and dividing the news corpus information into news subjects and subject attitudes;

[0106] Construct the first feature tensor as where D 1 =[d 11 , d 12 ,...,d 1i ] represents the news subject vector, Represents the subject attitude vector, and each element d in the vector represents a news subject or subject attitude.

[0107] This process also includes establishing the corresponding relationship between news subjects and subject attitudes M 1 ={d 1i :[d 2* ]} and M 2 ={d 2j :[d 1* ]}, where d 2* means D 2 One or more elements in ; d 1* means D 1 One or more elements; that is, a news subject can contain one or several ...

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 market prediction method based on news corpus. The market prediction method based on the news corpus comprises the steps of: S1, obtaining news corpus information, and pre-processing the news corpus information; S2, according to the news corpus information obtained in the step S1, constructing a first characteristic tensor in the form of two-dimensional information dimension including a news subject and a subject attitude, and furthermore, in combination with a pre-set keyword dictionary, obtaining a second characteristic tensor; S3, extracting emotional information according to the second characteristic tensor, and then, calculating a public opinion factor alpha through a plurality of pieces of emotional information; and S4, obtaining the lagging T-stage yield rate RT corresponding to the obtained public opinion factor alpha, and predicting the future yield rate market. By means of the technical scheme in the invention, the market emotional calculation efficiency and the accuracy rate can be increased; and thus, relative accurate market prediction can be realized.

Description

technical field [0001] The invention relates to the technical field of information processing, in particular to a market prediction method based on news corpus. Background technique [0002] In the financial investment market, the ups and downs of the market are determined by the buying and selling decisions of each trader involved. The trading decisions of traders and their own value judgments on financial targets, the market sentiment created by all traders, and the liquidity of market funds and other factors closely related. However, for some markets with frequent hype or emerging markets with uncertain values, the intrinsic value of financial targets may often deviate from the market price, and even its intrinsic value itself is difficult to accurately estimate, and the market sentiment dominated by news and public opinion often exacerbates the price volatility. fluctuation. Some existing technical analysis methods based on volume and price information and fundamental ...

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): G06F17/27G06F17/22
CPCG06F40/151G06F40/242G06F40/289G06F40/30
Inventor 曹一新徐照晔吴小川
Owner ZHONGAN INFORMATION TECH SERVICES CO LTD
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