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

Credit score integrated classification system and method based on deep learning

A credit scoring and deep learning technology, applied in the field of credit scoring integrated classification system, can solve the problems of complex feature engineering and low accuracy, and achieve the effect of low misclassification rate, high accuracy, and improved performance

Pending Publication Date: 2019-12-17
NORTHWEST UNIV
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a credit scoring integrated classification system and method based on deep learning to solve the problem that most of the existing credit scoring models in the prior art are constructed by shallow architectures and require complex feature engineering. low accuracy problem

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
  • Credit score integrated classification system and method based on deep learning
  • Credit score integrated classification system and method based on deep learning
  • Credit score integrated classification system and method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] In this embodiment, a credit score integrated classification system based on deep learning is disclosed, including a data acquisition and preprocessing unit, an integrated classification training unit and a voting unit;

[0037] The data acquisition and preprocessing unit is used to obtain the credit data set, and perform data preprocessing on the credit data set to obtain a sample data set, and divide the sample data set into a sample training set and a sample test set;

[0038] The integrated classification training unit includes an RNN subunit, an LR subunit and an XGBoost subunit, and the integrated classification training unit is used to pass the sample training set obtained by the data acquisition and the preprocessing unit through the RNN subunit, the LR subunit and the XGBoost respectively. The subunits are trained to obtain the predicted credit probability obtained by the sample test set passing through each subunit respectively;

[0039] The voting unit is use...

Embodiment 2

[0046] Disclosed in this embodiment is a credit scoring integrated classification method based on deep learning, including the following sub-steps:

[0047] Step 1: Obtain the credit data set, and perform data preprocessing on the credit data set to obtain a sample data set;

[0048] Step 2: Divide the sample data set into a sample training set and a sample test set;

[0049] Step 3: According to the RNN method, the LR method and the XGBoost method, the sample training set is trained to obtain an integrated classification model, and the integrated classification model includes parallel RNN submodules, LR submodules and XGBoost submodules; select the integrated classification model When sub-modeling, refer to a variety of single classifiers including: decision tree DT, support vector machine SVM, logistic regression LR, linear discriminant analysis LDA, random forest RF, extreme gradient decision tree XGBoost, cyclic neural network RNN, and carry out these classifiers For perf...

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 credit score integrated classification system and method based on deep learning, and the system comprises a data obtaining and preprocessing unit which is used for obtaininga credit data set, carrying out the data preprocessing to obtain a sample data set, and dividing the sample data set into a sample training set and a sample testing set; an integrated classification training unit which is used for training the sample training set through the RNN sub-unit, the LR sub-unit and the XGBoost sub-unit to obtain predicted credit probability of the sample training set through each sub-unit; and a voting unit which is used for carrying out majority voting on the three predicted credit probabilities obtained by the integrated classification training unit, if two or morepredicted credit probabilities are higher than 0.5, the customer credit is good, and otherwise, the customer credit is poor. According to the method, the deep learning algorithm recurrent neural network RNN is applied to the credit scoring problem, the logistic regression LR, the extreme gradient boosting tree XGBoost and the recurrent neural network RNN are integrated in parallel, the diversityand accuracy of the model are considered, and the performance of the model is improved.

Description

technical field [0001] The invention belongs to the technical field of data mining, and in particular relates to a deep learning-based credit scoring integrated classification system. Background technique [0002] In recent years, the credit market has developed rapidly, and financial institutions are facing more and more challenges. As an important part of the financial industry, credit risk assessment plays an important role in selecting credit customers and measuring risks. Personal credit scoring is usually a binary classification problem. A classifier is developed based on customer credit data and related features, and a decision system is built to classify customers into two categories: good credit and bad credit, and provide decision support to financial institutions. [0003] At present, there are mainly two classification methods applied to credit scoring: statistical methods and artificial intelligence methods. These methods are more accurate and reliable than pas...

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): G06F16/28G06N3/04G06Q10/04G06Q40/02
CPCG06F16/285G06Q10/04G06N3/045G06Q40/03
Inventor 侯榆青贺心畋贺小伟王宾李思奇王文强张翔
Owner NORTHWEST 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