CN110223165A - A kind of anti-fraud and credit risk forecast method and system based on related network - Google Patents
A kind of anti-fraud and credit risk forecast method and system based on related network Download PDFInfo
- Publication number
- CN110223165A CN110223165A CN201910515296.3A CN201910515296A CN110223165A CN 110223165 A CN110223165 A CN 110223165A CN 201910515296 A CN201910515296 A CN 201910515296A CN 110223165 A CN110223165 A CN 110223165A
- Authority
- CN
- China
- Prior art keywords
- credit
- user
- tested
- tested user
- collage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The anti-fraud and credit risk forecast method and system that the present invention relates to a kind of based on related network, which comprises judge whether tested user is fraudulent user that blacklist is on the list；If tested user is not fraudulent user, obtains and the relationship group of data interaction occurs with the tested user, and related network is gone out by the relationship informative population；Node object in the related network is analyzed, determines the credit scoring of the tested user, to carry out Risk-warning.The present invention is tested the related network of user by constructing, and the credit risk forecast of tested user is carried out by the related network, it can more accurately determine the credit scoring of tested user, improve the accuracy of prediction, when credit scoring is not up to standard, Risk-warning is carried out, is conducive to avoid risk, guarantees the economic interests of bank and other financial mechanism.
Description
Technical field
The present invention relates to financial risks assessment technology fields, and in particular to a kind of anti-fraud and credit based on related network
Risk Forecast Method and system.
Background technique
With the development of economy, financial circles are more and more flourishing, wherein an important composition portion of the loan as financial business
Point, loan transaction type is more and more flourishing, and loan channel is also more and more abundant.It is small to individual in people's lives, production activity
Current consumption, the big production and operation for arriving enterprise all be unable to do without loan transaction.Offer a loan service financial institution provide borrow
Before money, generally all can carry out assessing credit risks to this loan transaction can just ratify to borrow only when risk meets the requirements
Money application.Existing credit risk forecast method is the identity that first confirm creditor mostly, verifies the true of creditor's identity
Property, the personal reference information of creditor is then obtained, then assess the credit grade of creditor, finally decides whether to ratify
Loan application.Also have in the prior art by establishing credit risk forecast model and predicts the credit risk of creditor.
Existing credit risk forecast method is although varied, but still has many fraud banks to borrow in actual life
The event of money occurs, and brings economic loss to bank.Existing credit risk forecast method has only investigated of loan application people
People's situation, do not fully take into account with the applicant there are interests interactive relation other people, for example loan application people has a connection
It is very frequent contact person, and the contact person is a swindler, in this case, the applicant is probably by the connection
It is that shadow sound is swindled.In addition, existing credit risk forecast method only carries out credit risk before loan application is ratified
Assessment, but after confirmation request, the credit risk of creditor would not be tracked and be predicted.It is multiple especially for needing
The business of lending, such as credit card, bank only predict in credit risk of the credit card application stage to applicant, once hair
Credit card has been put, within the scope of amount, user can arbitrarily be used, this there is hidden danger, for example be that other people usurp, or
In credit card effective period, the significant problem that will affect its credit is had occurred in holder, for example swindles, to these behavior credits card
Issuing bank will not all be tracked credit evaluation again, this defect is possible to will lead to the economic damage of holder or bank
It loses.
Summary of the invention
In view of this, it is an object of the invention to overcome the deficiencies of the prior art and provide a kind of based on the anti-of related network
Fraud and credit risk forecast method and system.
In order to achieve the above object, the present invention adopts the following technical scheme: a kind of anti-fraud and credit based on related network
Risk Forecast Method, comprising:
Judge whether tested user is fraudulent user that blacklist is on the list；
If tested user is not fraudulent user, the relationship group that data interaction occurs with the tested user is obtained, and
Go out related network by the relationship informative population；
Node object in the related network is analyzed, determines the credit scoring of the tested user, so as to
Carry out Risk-warning.
Optionally, the relationship group that data interaction occurs with the tested user includes:
In communication medium with this be tested user can occur data interaction one or more levels contact person and circle of friends it is good
Friend.
Optionally, the prediction technique further include:
Before approval application, the personally identifiable information and a variety of collage-credit datas of tested user are obtained；
The credit scoring of the tested user is determined according to a variety of collage-credit datas；
According to the credit score of the tested user, it is determined whether ratify the application of the tested user；
After ratifying application, within a preset period of time, the corresponding user's operation behavioral data of account and the quilt are obtained
Survey a variety of collage-credit datas of user；Wherein, the account is to distribute after application goes through for the tested user；
The credit scoring of the tested user is updated according to the user's operation behavioral data and a variety of collage-credit datas.
Optionally, the personally identifiable information includes at least:
Name, effective identity certificate, facial image, fingerprint and iris information.
Optionally, the credit scoring that the tested user is determined according to a variety of collage-credit datas, comprising:
Digitized processing is carried out to a variety of collage-credit datas, determines the corresponding credit score of every kind of collage-credit data；
Determining credit risk coefficient corresponding with a variety of collage-credit datas；
The quilt is calculated according to the corresponding credit score of every kind of collage-credit data and corresponding credit risk coefficient
Survey the credit scoring of user.
Optionally, the credit score according to the tested user, it is determined whether ratify the application of the tested user, packet
It includes:
When the credit scoring is lower than the first preset threshold, determine that the tested user is high risk user, rejecting should
Application；
When the credit scoring is higher than the second preset threshold, determines that the tested user is normal users, ratify the Shen
Please；
Wherein, first preset threshold is less than or equal to second preset threshold.
Optionally, the user's operation behavioral data includes: consumer consumption behavior data and refund behavioral data.
Optionally, the method also includes:
Before carrying out withdrawal or delivery operation by the account, authentication is carried out to operator.
Optionally, include: to the detailed process of operator's progress authentication
Operating terminal acquire operator effective identity certificate information, facial image, fingerprint and iris information, and will more than
Information is uploaded to cloud server, so that cloud server is by corresponding of the information received and the account application people that prestores
People's identity information is compared, and generates comparison result；
Operating terminal receives the comparison result that the cloud server issues, and when comparison result be by when, approval should
The withdrawal or delivery operation that operator executes；
The withdrawal or delivery operation and corresponding operating time and debt number that cloud server executes the operator
It is saved as a user's operation behavior.
The present invention also provides a kind of anti-fraud and credit risk forecast system based on related network, comprising:
Judgment module, for judging whether tested user is fraudulent user that blacklist is on the list；
Related network constructs module, and number occurs with the tested user for obtaining when tested user is not fraudulent user
Go out related network according to interactive relationship group, and by the relationship informative population；
Credit scoring determining module determines the quilt for analyzing the node object in the related network
The credit scoring of user is surveyed, to carry out Risk-warning.
Optionally, the forecasting system further include:
First data acquisition module, for obtaining the personally identifiable information for being tested user and a variety of signs before approval application
Letter data, so that the credit scoring determining module analyzes the node object in the related network, and according to described
A variety of collage-credit datas determine the credit scoring of the tested user；
Approval module, for the credit score according to the tested user, it is determined whether ratify the application of the tested user；
Second data acquisition module, within a preset period of time, obtaining the user's operation behavioral data of account, Yi Jisuo
State a variety of collage-credit datas of tested user；Wherein, the account is to be tested user's distribution after approval application for this；
Credit scoring update module, for updating the quilt according to the user's operation behavioral data and a variety of collage-credit datas
Survey the credit scoring of user.
Optionally, the credit scoring that the tested user is determined according to a variety of collage-credit datas, comprising:
Digitized processing is carried out to a variety of collage-credit datas, determines the corresponding credit score of every kind of collage-credit data；
Determining credit risk coefficient corresponding with a variety of collage-credit datas；
The quilt is calculated according to the corresponding credit score of every kind of collage-credit data and corresponding credit risk coefficient
Survey the credit scoring of user.
Optionally, the system also includes:
Authentication module, for carrying out identity to operator and recognizing before carrying out withdrawal or delivery operation by the account
Card.
The invention adopts the above technical scheme, the anti-fraud and credit risk forecast method packet based on related network
It includes: judging whether tested user is fraudulent user that blacklist is on the list；If tested user is not fraudulent user, obtains and be somebody's turn to do
The relationship group of data interaction occurs for tested user, and goes out related network by the relationship informative population；To the related network
In node object analyzed, the credit scoring of the tested user is determined, to carry out Risk-warning.The present invention passes through
The related network of tested user is constructed, and carries out the credit risk forecast of tested user by the related network, it can be more acurrate
The credit scoring for determining tested user, improve the accuracy of prediction, when credit scoring is not up to standard, carry out Risk-warning,
Be conducive to avoid risk, guarantee the economic interests of bank and other financial mechanism.In addition, prediction technique of the present invention is not only being borrowed
Assessing credit risks is carried out before money confirmation request, after confirmation request, can also the user's operation behavior to the account track,
And the credit scoring of tested user is updated according to the user's operation behavioral data and a variety of collage-credit datas, it can be realized to tested
The credit risk of user is tracked the prediction of formula, avoids risk.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is that the present invention is based on the processes of the anti-fraud of related network and the offer of credit risk forecast embodiment of the method one to show
It is intended to；
Fig. 2 is that the present invention is based on the processes of the anti-fraud of related network and the offer of credit risk forecast embodiment of the method two to show
It is intended to；
Fig. 3 is that the present invention is based on the structures of the anti-fraud of related network and the offer of credit risk forecast system embodiment one to show
It is intended to；
Fig. 4 is that the present invention is based on the structures of the anti-fraud of related network and the offer of credit risk forecast system embodiment two to show
It is intended to.
In figure: 1, judgment module；2, related network constructs module；3, credit scoring determining module；4, the first data acquisition
Module；5, approval module；6, the second data acquisition module；7, credit scoring update module；8, authentication module.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, technical solution of the present invention will be carried out below
Detailed description.Obviously, described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Base
Embodiment in the present invention, those of ordinary skill in the art are obtained all without making creative work
Other embodiment belongs to the range that the present invention is protected.
Fig. 1 is that the present invention is based on the processes of the anti-fraud of related network and the offer of credit risk forecast embodiment of the method one to show
It is intended to.
As shown in Figure 1, method described in the present embodiment includes:
S11: judge whether tested user is fraudulent user that blacklist is on the list；
Further, the relationship group that data interaction occurs with the tested user includes:
In communication medium with this be tested user can occur data interaction one or more levels contact person and circle of friends it is good
Friend.
S12: if tested user is not fraudulent user, the relationship group that data interaction occurs with the tested user is obtained
Body, and related network is gone out by the relationship informative population；
S13: analyzing the node object in the related network, determines the credit scoring of the tested user,
To carry out Risk-warning.
The present embodiment is tested the related network of user by constructing, and the credit of tested user is carried out by the related network
Risk profile can more accurately determine the credit scoring of tested user, the accuracy of prediction be improved, when credit scoring does not reach
When mark, Risk-warning is carried out, is conducive to avoid risk, guarantees the economic interests of bank and other financial mechanism.
Fig. 2 is that the present invention is based on the processes of the anti-fraud of related network and the offer of credit risk forecast embodiment of the method two to show
It is intended to.
As shown in Fig. 2, method described in the present embodiment includes:
S21: before approval application, the personally identifiable information and a variety of collage-credit datas of tested user are obtained, and is judged tested
Whether user is fraudulent user that blacklist is on the list；
Further, the personally identifiable information includes at least:
Name, effective identity certificate, facial image, fingerprint and iris information.
S22: if tested user is not fraudulent user, the relationship group that data interaction occurs with the tested user is obtained
Body, and related network is gone out by the relationship informative population；
S23: analyzing the node object in the related network, and determines institute according to a variety of collage-credit datas
State the credit scoring of tested user；
Further, the credit scoring that the tested user is determined according to a variety of collage-credit datas, comprising:
Digitized processing is carried out to a variety of collage-credit datas, determines the corresponding credit score of every kind of collage-credit data；
Determining credit risk coefficient corresponding with a variety of collage-credit datas；Wherein, which can be
It is obtained according to risk data sample training, is also possible to the table according to previous lending experience combination related network interior joint object
Now determine.
The quilt is calculated according to the corresponding credit score of every kind of collage-credit data and corresponding credit risk coefficient
Survey the credit scoring of user.Wherein, the credit scoring of the tested user is equal to the corresponding credit score of collage-credit data and its phase
The adduction of the product for the credit risk coefficient answered.
S24: according to the credit score of the tested user, it is determined whether ratify the application of the tested user；
Further, the credit score according to the tested user, it is determined whether ratify the application of the tested user,
Include:
When the credit scoring is lower than the first preset threshold, determine that the tested user is high risk user, rejecting should
Application；
When the credit scoring is higher than the second preset threshold, determines that the tested user is normal users, ratify the Shen
Please；
Wherein, first preset threshold is less than or equal to second preset threshold.
S25: after ratifying application, before carrying out withdrawal or delivery operation by account, authentication is carried out to operator；Its
In, the account is to distribute after application goes through for the tested user；
Further, include: to the detailed process of operator's progress authentication
Operating terminal acquire operator effective identity certificate information, facial image, fingerprint and iris information, and will more than
Information is uploaded to cloud server, so that cloud server is by corresponding of the information received and the account application people that prestores
People's identity information is compared, and generates comparison result；
Operating terminal receives the comparison result that the cloud server issues, and when comparison result be by when, approval should
The withdrawal or delivery operation that operator executes；
The withdrawal or delivery operation and corresponding operating time and debt number that cloud server executes the operator
It is saved as a user's operation behavior.
S26: after ratifying application, within a preset period of time, the corresponding user's operation behavioral data of account, Yi Jisuo are obtained
State a variety of collage-credit datas of tested user；
Further, the user's operation behavioral data includes: consumer consumption behavior data and refund behavioral data.
S27: the credit scoring of the tested user is updated according to the user's operation behavioral data and a variety of collage-credit datas.
Method described in the present embodiment is when actually executing, for example, user proposes to provide a loan to finance services such as banks
Application, before approval application, bank obtains the personally identifiable information and a variety of collage-credit datas of tested user, and judges tested user
It whether is fraudulent user that blacklist is on the list；If tested user is not fraudulent user, obtains and number occurs with the tested user
Go out related network according to interactive relationship group, and by the relationship informative population, to the node object in the related network into
Row is analyzed, and the credit scoring of the tested user is determined according to a variety of collage-credit datas, further according to the tested user
Credit score, it is determined whether ratify the application of the tested user: if the credit scoring is lower than the first preset threshold, really
The fixed tested user is high risk user, rejects this application；If the credit scoring is higher than the second preset threshold, determine
The tested user is normal users, ratifies this application.After ratifying application, user is tested for this and distributes account；In approval Shen
Please after preset time period in, obtain the user's operation behavioral data of the account and a variety of reference numbers of the tested user
According to the preset time period can be fixed the period, such as the monthly No. 1 user's operation behavior number that will obtain the account
According to and the tested user a variety of collage-credit datas, be also possible to obtain daily primary, specific time interval can basis
Business needs to set.I.e. after approval application, the credit risk that bank still can be tested user to this is tracked, should with prediction
The following credit risk of tested user.It is updated according to the newest user's operation behavioral data got and a variety of collage-credit datas
The credit scoring of the tested user.Bank can decide whether also to continue to keep user's according to updated credit scoring
Permission, or the permission (for example the amount of the credit card of approved is turned up or is turned down) of adjustment user.
User withdrawn the money by the account or delivery operation before, will also to user carry out authentication, with guarantee work as
Preceding operator must be the holder in due course of the account.Effective identity of operating terminal (can be mobile phone terminal) acquisition operator
Certificate information, facial image, fingerprint and iris information, and information above is uploaded to cloud server, so that cloud server
The information received is compared with the corresponding personally identifiable information of the account application people prestored, generates comparison result；Behaviour
Receive the comparison result that the cloud server issues as terminal, and when comparison result be by when, ratify operator execution
Withdrawal or delivery operation；The withdrawal or delivery operation and corresponding operating time that cloud server executes the operator
It is saved with debt number as a user's operation behavior.Such as predicted time section be monthly No. 1 progress credit scoring more
Newly, user in the month before have three consumer records, then when being updated to credit scoring, the user of the account of acquisition is grasped
It include above three consumer records as behavioral data, a variety of collage-credit datas of the tested user of acquisition are also real by networking
When the current newest collage-credit data that gets.Finally according to the user's operation behavioral data and the update of a variety of collage-credit datas
The credit scoring of tested user.
The present embodiment carries out authentication before execute delivery operation, to operator, common guarantee account holder and
The interests of bank finance service organization.It is verified by a variety of identity characteristic informations to operator, ensure that authentication
Reliability.The present embodiment updates the credit of the tested user according to the user's operation behavioral data and a variety of collage-credit datas
Scoring, in actual use, specifically may is that such as monthly No. 1 can be updated the credit scoring of user, May 1 in 2019
The credit scoring day determined is compared with determining credit scoring on April 1 in 2019, determining credit scoring meeting on May 1st, 2019
The user's operation behavioral data in April, 2019 and collage-credit data are included, carry out recalculating tested user's
Credit scoring, to predict following credit risk.The present embodiment can the operation behavior data to user analyze, for example, should
The date of start of calculation of the every bill of user will all consume away all amounts, and the fund shape of user can be speculated according to this behavior
Condition may be more nervous, if recurring more phases, bank can turn down the credit risk of the user accordingly.
Prediction technique described in the present embodiment is not merely with the relationship network of tested user before loan application approval
To tested user carry out assessing credit risks, after confirmation request, can also the user's operation behavior to the account track, and
The credit scoring that tested user is updated according to the user's operation behavioral data and a variety of collage-credit datas, can be realized to tested use
The credit risk at family is tracked the prediction of formula, is conducive to avoid risk, and guarantees the economic interests of bank and other financial mechanism.
Fig. 3 is that the present invention is based on the structures of the anti-fraud of related network and the offer of credit risk forecast system embodiment one to show
It is intended to.
As shown in figure 3, forecasting system described in the present embodiment, comprising:
Judgment module 1, for judging whether tested user is fraudulent user that blacklist is on the list；
Related network constructs module 2, and number occurs with the tested user for obtaining when tested user is not fraudulent user
Go out related network according to interactive relationship group, and by the relationship informative population；
Credit scoring determining module 3 determines the quilt for analyzing the node object in the related network
The credit scoring of user is surveyed, to carry out Risk-warning.
The working principle of forecasting system described in the present embodiment is identical as the working principle of prediction technique embodiment one above,
This is repeated no more.
Forecasting system described in the present embodiment is carried out by constructing the related network of tested user by the related network
The credit risk forecast of tested user can more accurately determine the credit scoring of tested user, improve the accuracy of prediction,
When credit scoring is not up to standard, Risk-warning is carried out, is conducive to avoid risk, guarantees the economic interests of bank and other financial mechanism.
Fig. 4 is that the present invention is based on the structures of the anti-fraud of related network and the offer of credit risk forecast system embodiment two to show
It is intended to.
As shown in figure 4, forecasting system described in the present embodiment, comprising:
Judgment module 1, for judging whether tested user is fraudulent user that blacklist is on the list；
Related network constructs module 2, and number occurs with the tested user for obtaining when tested user is not fraudulent user
Go out related network according to interactive relationship group, and by the relationship informative population；
First data acquisition module 4, for obtaining the personally identifiable information for being tested user and a variety of signs before approval application
Letter data；
Credit scoring determining module 3, for analyzing the node object in the related network, and according to described more
Kind collage-credit data determines the credit scoring of the tested user；
Approval module 5, for the credit score according to the tested user, it is determined whether ratify the Shen of the tested user
Please；
Second data acquisition module 6 is used within a preset period of time, obtain the user's operation behavioral data of account, and
A variety of collage-credit datas of the tested user；Wherein, the account is to be tested user's distribution after approval application for this；
Credit scoring update module 7, for according to the user's operation behavioral data and the update of a variety of collage-credit datas
The credit scoring of tested user.
Further, the credit scoring that the tested user is determined according to a variety of collage-credit datas, comprising:
Digitized processing is carried out to a variety of collage-credit datas, determines the corresponding credit score of every kind of collage-credit data；
Determining credit risk coefficient corresponding with a variety of collage-credit datas；
The quilt is calculated according to the corresponding credit score of every kind of collage-credit data and corresponding credit risk coefficient
Survey the credit scoring of user.
Further, the system also includes:
Authentication module 8, for carrying out identity to operator and recognizing before carrying out withdrawal or delivery operation by the account
Card.
The working principle of forecasting system described in the present embodiment is identical as the working principle of prediction technique embodiment two above,
This is repeated no more.
Forecasting system described in the present embodiment not only carries out assessing credit risks before loan application is ratified, in confirmation request
Afterwards, can also the user's operation behavior to the account track, and according to the user's operation behavioral data and a variety of reference numbers
According to the credit scoring for updating tested user, it can be realized the prediction for being tracked formula to the credit risk of tested user, be conducive to
It avoids risk, guarantees the economic interests of bank and other financial mechanism.
It is understood that same or similar part can mutually refer in the various embodiments described above, in some embodiments
Unspecified content may refer to the same or similar content in other embodiments.
It should be noted that in the description of the present invention, term " first ", " second " etc. are used for description purposes only, without
It can be interpreted as indication or suggestion relative importance.In addition, in the description of the present invention, unless otherwise indicated, the meaning of " multiple "
Refer at least two.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium
In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing module
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiment or examples in can be combined in any suitable manner.
Although the embodiments of the present invention has been shown and described above, it is to be understood that above-described embodiment is example
Property, it is not considered as limiting the invention, those skilled in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, modifies, replacement and variant.
Claims (10)
1. a kind of anti-fraud and credit risk forecast method based on related network characterized by comprising
Judge whether tested user is fraudulent user that blacklist is on the list；
If tested user is not fraudulent user, obtains and the relationship group of data interaction occurs with the tested user, and pass through
The relationship informative population goes out related network；
Node object in the related network is analyzed, determines the credit scoring of the tested user, to carry out
Risk-warning.
2. prediction technique according to claim 1, which is characterized in that the pass that data interaction occurs with the tested user
It is that group includes:
One or more levels contact person and circle of friends good friend of data interaction can be occurred by being tested user with this in communication medium.
3. prediction technique according to claim 1, which is characterized in that further include:
Before approval application, the personally identifiable information and a variety of collage-credit datas of tested user are obtained；
The credit scoring of the tested user is determined according to a variety of collage-credit datas；
According to the credit score of the tested user, it is determined whether ratify the application of the tested user；
After ratifying application, within a preset period of time, the corresponding user's operation behavioral data of account and the tested use are obtained
A variety of collage-credit datas at family；Wherein, the account is to distribute after application goes through for the tested user；
The credit scoring of the tested user is updated according to the user's operation behavioral data and a variety of collage-credit datas.
4. prediction technique according to claim 3, which is characterized in that described to determine institute according to a variety of collage-credit datas
State the credit scoring of tested user, comprising:
Digitized processing is carried out to a variety of collage-credit datas, determines the corresponding credit score of every kind of collage-credit data；
Determining credit risk coefficient corresponding with a variety of collage-credit datas；
The tested use is calculated according to the corresponding credit score of every kind of collage-credit data and corresponding credit risk coefficient
The credit scoring at family.
5. prediction technique according to claim 4, which is characterized in that the credit score according to the tested user,
Determine whether to ratify the application for being tested user, comprising:
When the credit scoring is lower than the first preset threshold, determines that the tested user is high risk user, reject this application；
When the credit scoring is higher than the second preset threshold, determines that the tested user is normal users, ratify this application；
Wherein, first preset threshold is less than or equal to second preset threshold.
6. according to the described in any item prediction techniques of claim 3 to 5, which is characterized in that further include:
Before carrying out withdrawal or delivery operation by the account, authentication is carried out to operator.
7. prediction technique according to claim 6, which is characterized in that carry out the detailed process packet of authentication to operator
It includes:
Operating terminal acquires effective identity certificate information, facial image, fingerprint and the iris information of operator, and by information above
It is uploaded to cloud server, so that cloud server is personal by corresponding of the information received and the account application people prestored
Part information is compared, and generates comparison result；
Operating terminal receives the comparison result that the cloud server issues, and when comparison result be by when, ratify the operation
The withdrawal or delivery operation that people executes；
Withdrawal or delivery operation and corresponding operating time that cloud server executes the operator and debt number as
One user's operation behavior is saved.
8. a kind of anti-fraud and credit risk forecast system based on related network characterized by comprising
Judgment module, for judging whether tested user is fraudulent user that blacklist is on the list；
Related network constructs module, hands over for obtaining when tested user is not fraudulent user with tested user's generation data
Mutual relationship group, and related network is gone out by the relationship informative population；
Credit scoring determining module determines the tested use for analyzing the node object in the related network
The credit scoring at family, to carry out Risk-warning.
9. forecasting system according to claim 8, which is characterized in that further include:
First data acquisition module, for obtaining the personally identifiable information and a variety of reference numbers of tested user before approval application
According to so that the credit scoring determining module analyzes the node object in the related network, and according to described a variety of
Collage-credit data determines the credit scoring of the tested user；
Approval module, for the credit score according to the tested user, it is determined whether ratify the application of the tested user；
Second data acquisition module, within a preset period of time, obtaining the user's operation behavioral data and the quilt of account
Survey a variety of collage-credit datas of user；Wherein, the account is to be tested user's distribution after approval application for this；
Credit scoring update module, for updating the tested use according to the user's operation behavioral data and a variety of collage-credit datas
The credit scoring at family.
10. forecasting system according to claim 8 or claim 9, which is characterized in that further include:
Authentication module, for carrying out authentication to operator before carrying out withdrawal or delivery operation by the account.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910515296.3A CN110223165A (en) | 2019-06-14 | 2019-06-14 | A kind of anti-fraud and credit risk forecast method and system based on related network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910515296.3A CN110223165A (en) | 2019-06-14 | 2019-06-14 | A kind of anti-fraud and credit risk forecast method and system based on related network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110223165A true CN110223165A (en) | 2019-09-10 |
Family
ID=67817103
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910515296.3A Pending CN110223165A (en) | 2019-06-14 | 2019-06-14 | A kind of anti-fraud and credit risk forecast method and system based on related network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110223165A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110633804A (en) * | 2019-09-12 | 2019-12-31 | 深圳众赢维融科技有限公司 | Financial product incoming item evaluation method, server and storage medium |
| CN110648670A (en) * | 2019-10-22 | 2020-01-03 | 中信银行股份有限公司 | Fraud identification method and device, electronic equipment and computer-readable storage medium |
| CN110718228A (en) * | 2019-10-22 | 2020-01-21 | 中信银行股份有限公司 | Voice separation method and device, electronic equipment and computer readable storage medium |
| CN111062808A (en) * | 2019-12-24 | 2020-04-24 | 深圳市信联征信有限公司 | Credit card limit evaluation method, device, computer equipment and storage medium |
| CN111861669A (en) * | 2020-07-23 | 2020-10-30 | 上海中通吉网络技术有限公司 | Method, device and terminal for calculating unijunction |
| CN112001785A (en) * | 2020-07-21 | 2020-11-27 | 小花网络科技(深圳)有限公司 | Network credit fraud identification method and system based on image identification |
| CN112561685A (en) * | 2020-12-15 | 2021-03-26 | 建信金融科技有限责任公司 | Client classification method and device |
| CN112700321A (en) * | 2020-12-31 | 2021-04-23 | 重庆富民银行股份有限公司 | Multi-rule anti-fraud prediction method and system based on user behavior data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140067650A1 (en) * | 2012-08-28 | 2014-03-06 | Clearmatch Holdings (Singapore) PTE. LTD. | Methods and systems for consumer lending |
| CN105976236A (en) * | 2016-04-28 | 2016-09-28 | 中国建设银行股份有限公司 | Loan transaction monitoring early warning method and apparatus thereof |
| CN107292424A (en) * | 2017-06-01 | 2017-10-24 | 四川新网银行股份有限公司 | A kind of anti-fraud and credit risk forecast method based on complicated social networks |
| CN109584048A (en) * | 2018-11-30 | 2019-04-05 | 上海点融信息科技有限责任公司 | The method and apparatus that risk rating is carried out to applicant based on artificial intelligence |
| CN109670937A (en) * | 2018-09-26 | 2019-04-23 | 平安科技（深圳）有限公司 | Risk subscribers recognition methods, user equipment, storage medium and device |
-
2019
- 2019-06-14 CN CN201910515296.3A patent/CN110223165A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140067650A1 (en) * | 2012-08-28 | 2014-03-06 | Clearmatch Holdings (Singapore) PTE. LTD. | Methods and systems for consumer lending |
| CN105976236A (en) * | 2016-04-28 | 2016-09-28 | 中国建设银行股份有限公司 | Loan transaction monitoring early warning method and apparatus thereof |
| CN107292424A (en) * | 2017-06-01 | 2017-10-24 | 四川新网银行股份有限公司 | A kind of anti-fraud and credit risk forecast method based on complicated social networks |
| CN109670937A (en) * | 2018-09-26 | 2019-04-23 | 平安科技（深圳）有限公司 | Risk subscribers recognition methods, user equipment, storage medium and device |
| CN109584048A (en) * | 2018-11-30 | 2019-04-05 | 上海点融信息科技有限责任公司 | The method and apparatus that risk rating is carried out to applicant based on artificial intelligence |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110633804A (en) * | 2019-09-12 | 2019-12-31 | 深圳众赢维融科技有限公司 | Financial product incoming item evaluation method, server and storage medium |
| CN110633804B (en) * | 2019-09-12 | 2022-06-24 | 简链科技(广东)有限公司 | Financial product incoming evaluation method, server and storage medium |
| CN110648670A (en) * | 2019-10-22 | 2020-01-03 | 中信银行股份有限公司 | Fraud identification method and device, electronic equipment and computer-readable storage medium |
| CN110718228A (en) * | 2019-10-22 | 2020-01-21 | 中信银行股份有限公司 | Voice separation method and device, electronic equipment and computer readable storage medium |
| CN110648670B (en) * | 2019-10-22 | 2021-11-26 | 中信银行股份有限公司 | Fraud identification method and device, electronic equipment and computer-readable storage medium |
| CN111062808A (en) * | 2019-12-24 | 2020-04-24 | 深圳市信联征信有限公司 | Credit card limit evaluation method, device, computer equipment and storage medium |
| CN111062808B (en) * | 2019-12-24 | 2023-06-09 | 深圳市信联征信有限公司 | Credit card limit evaluation method, credit card limit evaluation device, computer equipment and storage medium |
| CN112001785A (en) * | 2020-07-21 | 2020-11-27 | 小花网络科技(深圳)有限公司 | Network credit fraud identification method and system based on image identification |
| CN111861669A (en) * | 2020-07-23 | 2020-10-30 | 上海中通吉网络技术有限公司 | Method, device and terminal for calculating unijunction |
| CN112561685A (en) * | 2020-12-15 | 2021-03-26 | 建信金融科技有限责任公司 | Client classification method and device |
| CN112561685B (en) * | 2020-12-15 | 2023-10-17 | 建信金融科技有限责任公司 | Customer classification method and device |
| CN112700321A (en) * | 2020-12-31 | 2021-04-23 | 重庆富民银行股份有限公司 | Multi-rule anti-fraud prediction method and system based on user behavior data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110223165A (en) | A kind of anti-fraud and credit risk forecast method and system based on related network | |
| Paleologo et al. | Subagging for credit scoring models | |
| CN106803168A (en) | A kind of abnormal transfer accounts method for detecting and device | |
| Chang et al. | Rational herding and the spatial clustering of bank branches: an empirical analysis | |
| CN109242673A (en) | Hawkeye is counter to cheat big data air control assessment system | |
| Gowrisankaran et al. | Entry and pricing in a differentiated products industry: Evidence from the ATM market | |
| KR102024377B1 (en) | Method for providing blockchian based loan service using credit scoring to group inclduing individual | |
| CN110443694A (en) | Financing method and device on little Wei enterprise line | |
| Gong et al. | A dedication-constraint model of consumer switching behavior in mobile payment applications | |
| CN111932268A (en) | Enterprise risk identification method and device | |
| CN112232947A (en) | Loan risk prediction method and device | |
| CN107180384A (en) | One kind is based on internet entrusted loan solution | |
| CN109345371A (en) | Personal reference report backtracking method and system | |
| Choi et al. | Strategic management of new products: Ex-ante simulation and market segmentation | |
| Burdekin et al. | Chinese influences on inflation determination in Australia and the ASEAN group: A Markov-switching analysis | |
| Ikpefan et al. | Fast tracking business transactions through a cashless economy in Nigeria: Benefits and challenges | |
| Onay et al. | Why banks adopt mobile banking? The case of Turkey | |
| US20230092126A1 (en) | Banking operation support system, banking operation support method, and banking operation support program | |
| Achsan et al. | The Demographic and Behavior Determinant of Credit Card Default in Indonesia | |
| CN102609876B (en) | System and method for processing consumption credit investigation information | |
| Ennew | Product strategy | |
| KR101960074B1 (en) | Method of estimating credit statis, server performing the same and system performing the same | |
| Witoelar et al. | Binding constraints on digital financial inclusion in Indonesia: An analysis using the decision tree approach | |
| Boscia et al. | The theory and experience of cooperative banking | |
| Werema et al. | Factors affecting clients on loan repayment for microfinance institutions: A case study of pride Arusha, Tanzania |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190910 |
|
| RJ01 | Rejection of invention patent application after publication |