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

Financial data prediction method based on improved long-short term memory network

A technology of long and short-term memory and prediction method, which is applied in the fields of finance, prediction, data processing and other fields, and can solve the problems of accelerated convergence speed and complex structure of memory network.

Inactive Publication Date: 2018-10-23
SOUTHWEST PETROLEUM UNIV
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But unfortunately, the structure of LSTM is very complicated, and there are still some shortcomings when predicting financial data: (1) The accuracy of the long-short-term memory network prediction results needs to be further improved; (2) The convergence speed of the long-short-term memory network To be further accelerated

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
  • Financial data prediction method based on improved long-short term memory network
  • Financial data prediction method based on improved long-short term memory network
  • Financial data prediction method based on improved long-short term memory network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0106] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further elaborated below in conjunction with the accompanying drawings and specific embodiments.

[0107] In this example, if Figure 1-6 As shown, a financial data prediction method based on an improved long-short-term memory network, the method includes the following steps:

[0108] (1) Input the financial time series data to be processed, and set the value of each moment in the data as a sample;

[0109] (2) Normalize the input financial time series data to obtain the normalized financial time series data;

[0110] (3) From the preprocessed data set, determine the training sample set and test sample set:

[0111] From the preprocessed data set, select the first 90% of the data as the training sample set, and select the remaining 10% of the data as the test sample set;

[0112] (4) Initialize the improved long short-term memory network param...

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 financial data prediction method based on an improved long-short term memory network, and relates to the field of in-depth learning and financial data prediction. According to the method, when an input squeezing element, an input gate unit, a forgetting gate unit and an output gate unit are calculated, hidden layer information at more moments are added, a forward propagation algorithm and a back propagation along time algorithm are redesigned on this basis, and the improved long-short term memory network algorithm is used to predict the financial time series data, which improves the prediction accuracy of financial time series data and accelerates the convergence speed of the algorithms.

Description

technical field [0001] The invention relates to the technical field of deep learning and financial data prediction, in particular to a financial data prediction method based on an improved long-short-term memory network. Background technique [0002] Financial time series refers to a series of price data obtained in chronological order from the prices of financial products in the financial market (such as the stock market, foreign exchange market, etc.), which is the basis of financial market analysis. At present, there are many methods for financial time series forecasting, such as the method based on the least squares support vector machine and the piecewise regression approximation (PRA) method, etc., which have obvious shortcomings, that is, with the different test data sets, the method There will be very different experimental results in terms of effectiveness and accuracy, and even some prediction methods cannot be used at all for certain data sets. [0003] In the th...

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
IPC IPC(8): G06Q10/04G06Q40/04
CPCG06Q10/04G06Q40/04
Inventor 宋国杰左亚洲赵芳
Owner SOUTHWEST PETROLEUM 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