APP risk assessment method and device based on factorization machine and electronic equipment

A factor decomposition and risk assessment technology, applied in machine learning, instruments, calculation models, etc., can solve problems such as inability to accurately predict financial risks, and achieve resource saving, good stability, and remarkable results

Pending Publication Date: 2020-08-25
上海淇毓信息科技有限公司
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to solve the technical problem in the prior art that financial risks cannot be accurately predicted when there is less data, the present invention provides an APP risk assessment method, device, electronic equipment and computer-readable medium based on a factorization machine

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
  • APP risk assessment method and device based on factorization machine and electronic equipment
  • APP risk assessment method and device based on factorization machine and electronic equipment
  • APP risk assessment method and device based on factorization machine and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0108] According to a preferred embodiment of the present invention, the types include any one of the following: financial, loan, wealth management, social, game, and work.

[0109] Feature extraction module 202 further includes:

[0110] The second feature setting unit is used to set corresponding features for the user according to the APP installation list information of the user;

[0111] The second feature combining unit is configured to combine any two features of the user to obtain the combined feature.

[0112] Information encoding module 203 further includes:

[0113] A coverage acquisition unit, configured to acquire user coverage of multiple APPs;

[0114] A set establishment unit, configured to establish an APP set, so that the user coverage of each APP in the APP set is greater than a predetermined value;

[0115] A comparing unit, configured to compare the user's APP installation list with the APP set to obtain the one-hot encoded features associated with the u...

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 APP risk assessment method and device based on a factorization machine, and electronic equipment. The method comprises the steps of obtaining APP installation list information of a mobile terminal associated with a user; extracting APP features and APP combination features according to the APP installation list information; performing one-hot coding on the APP features and the APP combination features to obtain one-hot coding features associated with the user; and inputting the one-hot coding features into a trained machine learning model, and calculating a risk score of the user. According to the invention, the one-hot coding characteristics converted from the APP installation list information of the user mobile terminal are substituted into the preset machine learning model for training; the method and device are simple to operate and easy to implement, the accuracy of an assessed credit risk result is high, meanwhile, the contribution degree to the creditrisk when multiple feature combinations exist can be assessed under the condition of a sparse data set, the stability is good, in the aspects of modeling and feature maintenance, the input manpower issmall, resources are saved, and the effect is remarkable.

Description

technical field [0001] The present invention relates to the field of computer information processing, in particular to a factorization machine-based APP risk assessment method, device, electronic equipment and computer-readable medium. Background technique [0002] It is a common practice in the field of consumer finance to obtain information related to customer terminal applications (APP) for risk control under the condition of full authorization by customers. For the mining of customer APP information, the common practice is to classify APPs, and then make customer portraits by counting customers' installation and usage preferences for a certain type of APP. The disadvantage of this approach is that the classification of APPs is very difficult to maintain, because many APPs themselves have multiple functions, and it is difficult to classify these APPs into a certain category. For example, an APP has both social attributes and financial management, payment and other functi...

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): G06Q10/06G06N20/00
CPCG06Q10/0635G06N20/00
Inventor 聂婷婷张蓉姚王照
Owner 上海淇毓信息科技有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap