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

Information theory learning-based stock market fluctuation section prediction method

A forecasting method and information theory technology, applied in the field of stock market fluctuation range forecasting based on information theory learning, can solve problems such as unsatisfactory forecasting performance, and achieve the effect of wide application, good accuracy and robustness

Active Publication Date: 2018-02-16
ZHEJIANG UNIV
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a stock market fluctuation interval prediction method based on information theory learning to solve the problem of unsatisfactory prediction performance under non-Gaussian noise conditions when the existing neural network model is applied to the stock market fluctuation interval 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
  • Information theory learning-based stock market fluctuation section prediction method
  • Information theory learning-based stock market fluctuation section prediction method
  • Information theory learning-based stock market fluctuation section prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0087] In order to verify the performance of the stock market fluctuation interval prediction method based on information theory learning described in the present invention, and the effect comparison with the MSE-based interval neural network prediction method, the method is applied in the prediction of my country's Shanghai Composite Index below. We selected the highest and lowest prices of the Shanghai Composite Index (code 000001) for a total of 539 days from January 1, 2015 to March 21, 2017 as the data set, of which a total of 428 111 days from October 10, 2016 to March 21, 2017 are used as the test set. The number of input layer units n=8, the number of hidden layer units h=15, the number of output layer units m=1, the sample batch size p=5, the weight of the cost function of the center and radius β=0.5, and the width of the relevant entropy kernel function is taken as σ = 0.3. The predicted results and actual interval values ​​on the test set are attached image 3 As ...

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 an information theory learning-based stock market fluctuation section prediction method. The method comprises the following steps of: obtaining and sectioning stock index data;establishing a section neural network prediction model; designing an information theory learning-based cost function; and training the section neural network prediction model through maximizing the cost price, and applying the trained model to predicting stock market fluctuation sections. The method has the effects of realizing the modeling and prediction of stock index fluctuation sections and overcoming the boundedness that the common minimum mean square error criterion depends on Gaussian assumptions, has relatively good correctness and robustness, and is wider in application range.

Description

technical field [0001] The invention relates to the fields of machine learning, data forecasting and finance, in particular to a stock market volatility interval forecasting method based on information theory learning. Background technique [0002] Modeling and forecasting of stock market returns and volatility is a key problem in applications such as portfolio management, derivative security pricing, and risk management. At present, the main economic forecasting models are based on point data, such as selecting the opening price or closing price of the stock market in a day for analysis. However, the stock index in a day is constantly changing. With the rapid development of electronic trading and data storage technology, we can obtain more accurate intraday transaction data, which are generally summarized as the highest price and lowest price in the day, thus forming a stock index. A stock index interval. Numerous studies have proven that such ranges are an effective way ...

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): G06Q10/04G06Q40/04G06N3/04G06N3/08
CPCG06N3/08G06Q10/04G06Q40/04G06N3/048
Inventor 李春光翟一帆
Owner ZHEJIANG UNIV
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