Credit evaluation model based on breadth learning

A credit evaluation and model technology, applied in the computer field, can solve the problems of single evaluation data and difficult promotion of models, and achieve the effect of solving the single evaluation data

Active Publication Date: 2020-05-05
HENGRUITONG FUJIAN INFORMATION TECH CO LTD
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the above problems in the prior art, the present invention provides a credit evaluation model based on breadth learning, which can solve the problem that the existing evaluation model has single evaluation data and the model is difficult to promote

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 evaluation model based on breadth learning
  • Credit evaluation model based on breadth learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0019] Please refer to Figures 1 to 2 , a credit evaluation model based on extensive learning, including steps:

[0020] S1. Obtain credit data of natural persons in N source domains;

[0021] The credit data includes data on the basic situation of natural persons, social situation, occupational situation, financial situation, political style, illegal situation and public welfare situation.

[0022] S2. Perform dimension reduction processing and feature extraction on the credit data to obtain processed data;

[0023] Step S2 includes:

[0024] S21. Perform preprocessing on the credit data to obtain preprocessed credit data;

[0025] Described pretreatment comprises:

[0026] Uniform data types;

[0027] normalized processing;

[0028] Missing value handling.

[0029] S22. Calculate the feature weight value through the random forest and the preset feature weight, and establish a feature importance ranking table, perform dimensionality reduction processing on the preproc...

Embodiment 2

[0046] The difference between this embodiment and Embodiment 1 is that this embodiment will further illustrate how the above-mentioned credit evaluation model based on breadth learning in the present invention is realized in combination with specific application scenarios:

[0047] A: Obtain the credit data of natural persons in N source domains based on breadth learning. The credit data includes the basic information of natural persons, social information, occupational information, financial information, political style, illegal activities and public welfare information;

[0048] B: Preprocessing the credit data to obtain the preprocessed credit data;

[0049] Described pretreatment comprises:

[0050] Unify the data type, convert the percentage data of N source domains into floating-point data, and unify the number of effective digits;

[0051] The storage information in the database is converted into 0, 1 representation. (For example, if there is housing, it is 1, and if ...

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 provides a credit evaluation model based on breadth learning. The credit evaluation model comprises the steps of obtaining credit data of natural persons in N source domains; performingdimension reduction processing and feature extraction on the credit data to obtain processed data; and constructing an initial model, and training the initial model according to the processed data toobtain a trained credit evaluation model, thereby solving the problems of single evaluation data and difficult model popularization of an existing evaluation model.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a credit evaluation model based on breadth learning. Background technique [0002] In recent years, with the rapid development of big data and artificial intelligence industries, data analysis and machine learning have been applied to all aspects of people's lives, but some new challenges have followed. For big data analysis, there is insufficient amount of required data, but data overflow with low or no correlation; most models can only meet a single type of data processing and analysis, and cannot handle the complex situation of multi-source domain data entanglement. For general machine learning, there are related learning problems such as training that takes a lot of time but can only be applied to a single scene; data that is too single leads to overfitting. [0003] Existing credit evaluation models are generally only applied to bank credit loans, mainly to evaluate perso...

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): G06K9/62G06N3/04G06N3/08G06Q40/02
CPCG06N3/08G06N3/045G06Q40/03G06F18/213G06F18/24323Y02D10/00
Inventor 张美跃范章华程少锋周业俞传情周定云
Owner HENGRUITONG FUJIAN INFORMATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products