Risk determination method and device and electronic equipment

A risk determination and risk technology, applied in the field of information processing, can solve problems such as risk leakage and low accuracy of credit anti-fraud scoring, achieving high accuracy and reducing business risks

Inactive Publication Date: 2020-04-21
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF8 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Since credit anti-fraud will rely on a large amount of data for model calculation, due to the increase of business scenarios, when the existing model is applied to different business scenarios, the accuracy of credit anti-fraud scores obtained is low, which leads to Specific risks are missed

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
  • Risk determination method and device and electronic equipment
  • Risk determination method and device and electronic equipment
  • Risk determination method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0084]

[0085] This embodiment provides a risk determination method, for example, the method can be implemented by a server, and the server can be as follows Figure 1a or Figure 1b Server 1100 is shown. Such as figure 2 As shown, the method includes the following steps S2000-S2020:

[0086] Step 2000, acquiring multiple scene sample features and multiple user sample features.

[0087] Wherein, the scene sample features at least include: transaction data features, transaction type features, and transaction mode features. The user sample features at least include: user transaction data features, user account data features, and user behavior data features.

[0088] Step 2200, input the multiple scene sample features and the multiple user sample features into a multi-task learning algorithm, and train to obtain a general risk assessment model.

[0089] Specifically, such as Image 6 As shown, in the micro-loan business scenario, it is possible to learn the scene sample ...

no. 2 example

[0119]

[0120] This embodiment provides a risk determination method, for example, the method can be implemented by a server, and the server can be as follows Figure 1a or Figure 1b Server 1100 is shown. Such as Figure 5 As shown, the method includes the following steps 5000-5400:

[0121] Step 5000: Responding to the risk determination request of the business system for the user operation, acquire the scenario feature of the business scenario to which the user operation belongs and the user feature of the user information.

[0122] The business system may be a system for submitting user applications. For example, the business system may be a loan system, a loan system, a reserve fund application system, etc., which are not limited here. The service system can be installed in the terminal device 1200, and for example, an icon of the service system can be displayed on the display interface of the terminal device 1200, so that the user can enter the corresponding service ...

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

One or more embodiments of the invention relate to a risk determination method and device, and an electronic device. The method comprises the steps of obtaining a plurality of scene sample features and a plurality of user sample features; inputting the plurality of scene sample features and the plurality of user sample features into a multi-task learning algorithm, and training to obtain a generalrisk evaluation model; obtaining a target scene feature and a target user feature of the target service scene, taking the target scene feature and the target user feature as input of the general riskevaluation model, and training to obtain a target risk evaluation model; obtaining a to-be-evaluated user operation in the target service scene; and outputting a risk determination result of the to-be-evaluated user operation based on the target risk evaluation model.

Description

technical field [0001] The present invention relates to the field of information processing, and more specifically, to a risk determination method, a risk determination device, an electronic device, and a computer-readable storage medium. Background technique [0002] Credit loan (referred to as credit) is a loan that the borrower applies for with credit, and does not need to provide guarantee. At present, credit products are becoming more and more diversified. According to different customer groups, many business scenarios have been derived, such as Huabei loan, Jiebei loan, etc. [0003] When the lender receives the credit application, in order to prevent risk capital loss, the borrower will be given a credit anti-fraud score based on the borrower's account letter transaction information and other information. Among them, credit anti-fraud refers to the prevention and control of non-credit risk capital loss caused by abnormalities in the borrower's account or subjective 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): G06Q40/02
CPCG06Q40/03
Inventor 黄宇寰汲小溪赵闻飙
Owner ALIPAY (HANGZHOU) 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

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