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

User loan willingness prediction method and device and computer system

A prediction method and user technology, applied in the field of machine learning, can solve the problems of uncertain accuracy, limited learning ability, high labor cost, etc., and achieve the effect of improving accuracy and efficiency, avoiding inaccurate prediction, and shortening the time period

Pending Publication Date: 2021-02-05
南京星云数字技术有限公司
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these models have limited learning ability and require manual pre-screening of features, and a large number of feature process pre-analysis is required to make predictions based on the determined effective features and feature combinations, which takes a long time and requires labor costs. High and does not necessarily guarantee predictive accuracy

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
  • User loan willingness prediction method and device and computer system
  • User loan willingness prediction method and device and computer system
  • User loan willingness prediction method and device and computer system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0071] Corresponding to the above examples, such as image 3 As shown, this application provides a method for predicting the user's willingness to lend, the method comprising:

[0072] 310. Acquire user data of the user to be predicted, where the user data includes user attributes and historical consumption behavior of the user to be predicted;

[0073] 320. Using a plurality of preset classifiers of the first preset model to respectively generate prediction results of the category to which the user to be predicted belongs to according to the user data, the preset classifiers are used to classify the user;

[0074] 330. Integrate the prediction results of each of the preset classifiers to generate prediction features;

[0075] 340. According to the prediction feature, use a second preset model to predict whether the user to be predicted needs a loan.

[0076] Preferably, the method comprises:

[0077] 350. When it is predicted that the user to be predicted needs a loan, det...

Embodiment 3

[0091] Corresponding to the above method embodiment, such as Figure 4 As shown, the present application provides a device for predicting a user's willingness to lend, which includes:

[0092] An acquisition module 410, configured to acquire user data of the user to be predicted, the user data including user attributes and historical consumption behavior of the user to be predicted;

[0093] The processing module 420 is configured to use a plurality of preset classifiers of the first preset model to respectively generate a prediction result of the category to which the user to be predicted belongs to according to the user data, and the preset classifier is used to classify the user ; Integrating the prediction results of each of the preset classifiers to generate a prediction feature; according to the prediction feature, using a second preset model to predict whether the user to be predicted needs a loan.

[0094] Preferably, the device includes a training module 430, configu...

Embodiment 4

[0102] Corresponding to the above method, device, and system, Embodiment 4 of the present application provides a computer system, including: one or more processors; and a memory associated with the one or more processors, and the memory is used to store program instructions , when the program instructions are read and executed by the one or more processors, the following operations are performed:

[0103] Obtaining user data of the user to be predicted, the user data including user attributes and historical consumption behavior of the user to be predicted;

[0104] Using a plurality of preset classifiers of the first preset model to respectively generate prediction results for the category to which the user to be predicted belongs according to the user data, the preset classifiers are used to classify the user;

[0105] Integrating the prediction results of each of the preset classifiers to generate prediction features;

[0106] According to the prediction feature, a second p...

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 user loan willingness prediction method and device and a computer system, and the method comprises the steps: obtaining the user data of a to-be-predicted user, wherein the user data comprises the user attributes and historical consumption behaviors of the to-be-predicted user; using a plurality of preset classifiers of a first preset model to generate prediction resultsof classifications to which the users belong according to the user data, wherein the preset classifiers are used for classifying the users; integrating the prediction result of each preset classifierto generate a prediction feature; and according to the prediction features, predicting whether the user to be predicted needs a loan or not by using a second preset model, so that the loan willingnessof the user can be predicted according to the obtained user data, the process of manually screening the user data is avoided, and inaccurate prediction caused by inaccurate manual screening is avoided. The time period required by a characteristic experiment is shortened, and the accuracy and efficiency of model prediction are improved.

Description

technical field [0001] The invention relates to the field of machine learning, in particular to a method, device and computer system for predicting a user's willingness to lend. Background technique [0002] In recent years, the use of data mining technology in the financial industry has become more and more in-depth and extensive. Data mining technology can help the financial industry to analyze and evaluate customers, and help the financial industry to better mine potential information, rules and use them to provide customers with more suitable products. [0003] For the financial industry, how to make full use of existing data index resources and mine customers with loan needs and loan willingness through effective algorithm models is an urgent problem in this field. In the prior art, linear models such as scorecard models are often used to evaluate and predict whether users have loan demand and loan willingness. However, these models have limited learning ability and r...

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): G06F16/9535G06K9/62G06Q30/06G06Q40/02
CPCG06F16/9535G06Q30/0631G06Q40/03G06F18/214G06F18/24323
Inventor 黎倩文
Owner 南京星云数字技术有限公司
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