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

A credit risk monitoring method integrating a deep belief network and an isolated forest algorithm

A technology of deep belief network and forest algorithm, applied in the field of computer software, can solve the problems of less related research and achieve the effect of improving classification performance

Inactive Publication Date: 2019-04-26
BEIJING UNIV OF TECH
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In the existing credit risk monitoring research literature, there are few related studies on the use of deep 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
  • A credit risk monitoring method integrating a deep belief network and an isolated forest algorithm
  • A credit risk monitoring method integrating a deep belief network and an isolated forest algorithm
  • A credit risk monitoring method integrating a deep belief network and an isolated forest algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The invention uses a deep belief network to perform feature learning on high-dimensional data, obtains dimensionally reduced data as an input of an isolated forest algorithm, and improves the classification performance of the isolated forest algorithm for abnormal detection on high-dimensional data.

[0021] figure 1 It is a scheme diagram of the isolation forest algorithm classification method integrated with the deep belief network. First, data cleaning, missing value filling and data normalization are performed on the original financial transaction data, and finally the required data set is randomly sampled for the experiment, and finally standardized training subsets and test subsets are formed. The second part is the DBN data dimensionality reduction part and the optimized isolation forest algorithm, namely step 2, step 3 and step 4. The implementation of these two parts will be introduced in detail below.

[0022] Regarding step 2, construct a deep belief network...

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 isolated forest classification method used for credit risk monitoring and integrated with a deep belief network, and the method comprises the steps: employing the deep belief network to achieve the feature learning of high-dimensional data, and obtaining the optimal low-dimensional representation of an original data set; combined with linear time complexity, an unsupervised learning algorithm-Isolated forest algorithm for anomaly detection; And finally, achieving optimization of important parameters of the isolated Sensen algorithm through a particle swarm optimization algorithm and a simulated annealing algorithm, and forming a final DBN- iForst model for credit risk monitoring, And identifying the loan default.

Description

technical field [0001] The invention belongs to the field of computer software, and relates to a credit risk monitoring method integrating a deep belief network and an isolated forest algorithm (DBN-iForest). Background technique [0002] With the development of science and technology, the characteristics of financial market data are becoming more and more complex. Traditional machine learning methods are difficult to mine complex data features and cannot accurately reflect the characteristics of financial markets. Shallow neural networks have poor generalization ability for complex problems. However, the rule-based system usually cannot be updated in time, so the financial field needs to use advanced technology to build a new credit risk monitoring model. Deep learning is more suitable for the data characteristics of large data scale, high latitude and streaming data characteristics in the financial market, which has brought about an increase in its analysis requirements. T...

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): G06Q40/02G06K9/62G06N3/00G06N3/04G06N3/08
CPCG06N3/006G06N3/084G06N3/045G06Q40/03G06F18/24323
Inventor 王丹温丽娜赵文兵杜金莲付利华杜晓琳苏航
Owner BEIJING UNIV 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

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