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

An enterprise finance crisis prediction method based on maximized variance projection subspace multi-core learning

A technology of multi-core learning and forecasting method, applied in the field of enterprise financial crisis, can solve the problems of high difficulty of multi-core forecasting and low forecasting accuracy, and achieve the effect of reducing existing complex multi-core forecasting problems, improving forecasting accuracy and improving forecasting accuracy.

Inactive Publication Date: 2019-06-14
HEILONGJIANG INST OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the existing complex multi-core forecasting problem, which is difficult and has low forecasting accuracy, and proposes an enterprise financial crisis forecasting method based on maximizing variance projection subspace multi-kernel learning

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
  • An enterprise finance crisis prediction method based on maximized variance projection subspace multi-core learning
  • An enterprise finance crisis prediction method based on maximized variance projection subspace multi-core learning
  • An enterprise finance crisis prediction method based on maximized variance projection subspace multi-core learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0030] Specific implementation mode 1: The specific process of the enterprise financial crisis prediction method based on the maximum variance projection subspace multi-core learning in this implementation mode is as follows:

[0031] Step 1: Select the financial indicators of listed companies;

[0032] Financial indicators in financial crisis prediction mainly come from six aspects: profitability, solvency, development ability, asset management, cash flow, and financial flexibility. normally,

[0033] For a sample X of listed companies, sample X contains t financial indicator features (financial indicators), namely

[0034] in Represents the value corresponding to the λth financial indicator feature in sample X, and the superscript F represents the feature (the superscript F represents the feature feature, and the superscript used as a mark is represented by an uppercase English letter and separated by an underscore _, the same as below ), t is the total number of finan...

specific Embodiment approach 2

[0050] Specific embodiment 2: The difference between this embodiment and specific embodiment 1 is that in the step 1, usually, the number of financial indicators used to characterize the financial status of listed companies in the financial crisis prediction is about 20-30, and usually the characteristics of financial indicators are mainly Including: net profit margin, main business profit margin, return on total assets, return on net assets, non-recurring profit and loss ratio, price-earnings ratio, price-to-book ratio, current ratio, quick ratio, asset-liability ratio, equity ratio, interest protection Multiples, tangible net debt ratio, operating cash flow ratio, main business income growth rate, net profit growth rate, net asset growth rate, total asset growth rate, earnings per share growth rate, operating income per share growth rate, net per share Asset Growth Rate, EBITDA Growth Rate, Accounts Receivable Turnover Ratio, Inventory Turnover Ratio, Current Assets Turnover ...

specific Embodiment approach 3

[0052] Specific embodiment three: the difference between this embodiment and specific embodiment one or two is that in step 3, data normalization processing is performed on the total sample set of ST samples and non-ST samples in step 2;

[0053] The data normalization process adopts the following method:

[0054]

[0055] in Represents the normalized sample features (the superscript N stands for normalization normalization), X n for S ALL A sample of companies in (X n ∈ S ALL ); for X n The value corresponding to the mth feature, t is the total number of financial index features, m=1,2...,t.

[0056] Other steps and parameters are the same as those in Embodiment 1 or Embodiment 2.

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 enterprise financial crisis prediction method based on maximized variance projection subspace multi-kernel learning, and relates to an enterprise financial crisis predictionmethod. The objective of the invention is to solve the problems of high difficulty and low prediction precision of a complex multi-core prediction problem in the prior art. The method comprises the steps of 1, selecting financial indexes of listed companies; 2, determining an ST sample set and a non-ST sample set of the listed company; 3, performing data normalization processing on the total sample set of the ST samples and the non-ST samples; 4, constructing a training sample set base kernel matrix based on the normalized data; 5, performing vectorization operation on the basis kernel matrixto obtain a vectorized basis kernel set; 6, based on the vectorized basis kernel set, performing subspace learning to obtain an optimal basis kernel linear combination under maximum variance projection; and 7, constructing a multi-core support vector regression predictor by using the optimal basis kernel linear combination, and carrying out unknown sample financial condition prediction. The method is applied to the field of enterprise finance crisis prediction.

Description

technical field [0001] The invention relates to an enterprise financial crisis method. Background technique [0002] Financial crisis is an important threat to the development of enterprises. In 2015, when the world economy is in a period of deep adjustment, enterprises are facing more severe tests and are more likely to fall into financial crisis. In the process of rapid changes in the market environment, a financial crisis early warning system with good real-time performance and strong predictive ability is essential for strengthening the prevention of corporate financial crises and taking countermeasures, protecting the economic interests of investors and creditors, strengthening the state's supervision of the industry and It is of great significance in terms of macro-control and stabilizing the capital market. In recent years, scholars at home and abroad have continued to carry out more research on the theory, model and method of financial crisis early warning of listed...

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): G06Q10/04G06Q10/06G06Q40/00G06N20/10
Inventor 张向荣
Owner HEILONGJIANG INST OF TECH
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