CN110119980A - A kind of anti-fraud method, apparatus, system and recording medium for credit - Google Patents
A kind of anti-fraud method, apparatus, system and recording medium for credit Download PDFInfo
- Publication number
- CN110119980A CN110119980A CN201910330420.9A CN201910330420A CN110119980A CN 110119980 A CN110119980 A CN 110119980A CN 201910330420 A CN201910330420 A CN 201910330420A CN 110119980 A CN110119980 A CN 110119980A
- Authority
- CN
- China
- Prior art keywords
- data
- affiliated person
- debit user
- fraud
- credit
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- 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
Abstract
The invention discloses anti-fraud method, apparatus, system and the computer-readable mediums for credit.The method includes obtaining Debit User data and establish the anti-fraud scoring model based on label, according to the Debit User data and affiliated person's information of Debit User, it obtains Debit User and is associated with personal data, and by the Debit User data and Debit User affiliated person data creating at inputting the anti-fraud scoring model after label, the fraud scoring of Debit User is obtained, and corresponding anti-fraud measure is taken according to the fraud scoring.The present invention can accurately and efficiently carry out the identification of fraud people, reduce erroneous judgement, improve the experience of Debit User.
Description
Technical field
The invention belongs to technical field of data processing, and in particular to for business, finance the purpose of data processing system
And method, especially it is used for anti-fraud method, apparatus, system and the recording medium of credit.
Background technique
The credit mode provided a loan by internet application has obtained tremendous development.However, compared to traditional credit mode,
Online application loan is bringing people's convenience simultaneously, and the increase for cheating risk of cheating loan also is brought to credit operation department.Such as
Fruit cannot carry out the identification and processing of fraud well, it will bring damage difficult to the appraisal to internet financial platform
It loses.
In order to reduce credit risk, can directly be scored using existing credit scoring model credit applications people,
Quantify the credit risk or loan repayment capacity of loan applicant according to scoring.But this for exclusively by fraudulent mean come into
It swindles for the people of operations such as loan, practical function may not had, because they may be by forging or shielding the modes such as data
To obtain higher credit scoring.
Herewith, in order to carry out effective anti-fraud, the prior art is by establishing special anti-fraud model to credit applications
People carries out fraud scoring, and still, since the probability that fraud occurs is less, data volume is insufficient, therefore current anti-fraud mould
Type based on data it is more single, lack a large amount of sample data usually to carry out the optimization of model, this makes current counter take advantage of
Swindleness method cannot accurately and efficiently carry out the identification of fraud people, cause the experience property of user poor.
Summary of the invention
The technical problem to be solved by the present invention is to current internet lending platforms for fraud recognition accuracy
It is low or the problem of can not effectively identify.
In order to solve the above technical problems, the first aspect of the present invention proposes a kind of anti-fraud method for credit, including
Following steps: Debit User data are obtained and establish the anti-fraud scoring model based on label;According to the Debit User data
And affiliated person's information of Debit User, it obtains Debit User and is associated with personal data;By the Debit User data and Debit User
Affiliated person's data creating obtains the fraud scoring of Debit User, and according to this at the anti-fraud scoring model is inputted after label
Fraud scoring takes corresponding anti-fraud measure.
A preferred embodiment of the invention, the method also includes to the anti-fraud scoring model training
Step, training sample include that Debit User data with Debit User are associated with personal data.
A preferred embodiment of the invention, the Debit User affiliated person data include affiliated person's number of individuals
According to.
A preferred embodiment of the invention, the Debit User affiliated person data include affiliated person's statistical number
According to.
A preferred embodiment of the invention, affiliated person's statistical data include at least the one of following data
Kind: affiliated person's number, the affiliated person's number for having record of rejecting loans, the affiliated person's accounting for having record of rejecting loans, the association for having overdue record
Everybody counts, affiliated person's accounting for having overdue record, the affiliated person's number for having collection to record, the affiliated person's accounting for having collection to record.
The second aspect of the present invention proposes a kind of anti-rogue device for credit, comprising: Debit User data acquisition mould
Block, for obtaining Debit User data;Debit User affiliated person's data acquisition module, for according to the Debit User data with
And affiliated person's information of Debit User, it obtains Debit User and is associated with personal data;Fraud scoring computing module, for establishing based on mark
The anti-fraud scoring model of label, and by the Debit User data and Debit User affiliated person data creating at inputting institute after label
Anti- fraud scoring model is stated, the fraud scoring of Debit User is obtained.
A preferred embodiment of the invention, the fraud scoring computing module include: model foundation unit, are used
In anti-fraud scoring model of the foundation based on label;Model training unit, for being trained to the anti-fraud scoring model,
Training sample includes that Debit User data with Debit User are associated with personal data.
A preferred embodiment of the invention, the Debit User affiliated person data include affiliated person's number of individuals
According to.
A preferred embodiment of the invention, the Debit User affiliated person data include affiliated person's statistical number
According to.
A preferred embodiment of the invention, affiliated person's statistical data include at least the one of following data
Kind: affiliated person's number, the affiliated person's number for having record of rejecting loans, the affiliated person's accounting for having record of rejecting loans, the association for having overdue record
Everybody counts, affiliated person's accounting for having overdue record, the affiliated person's number for having collection to record, the affiliated person's accounting for having collection to record.
The third aspect of the present invention proposes a kind of anti-fake system for credit, comprising: memory is calculated for storing
Machine executable program;Data processing equipment, for reading the computer executable program in the memory, described with execution
Anti- fraud method for credit.
The fourth aspect of the present invention proposes a kind of computer-readable medium, for storing computer-readable program, the meter
Calculation machine readable program is used to execute the anti-fraud method for credit.
The present invention is that anti-fraud scoring model introduces or calculates Debit User and is associated with personal data, solves current counter take advantage of
The problem of data source for cheating Rating Model is single, and sample data lacks.Anti- fraud of the invention comments method accurate, efficient
Ground carries out the identification of fraud people, reduces erroneous judgement, improves the experience property of Debit User.
Detailed description of the invention
Fig. 1 is flow diagram of the present invention for the anti-fraud method of credit;
The step of Fig. 2 is the acquisition Debit User association personal data of the anti-fraud method for credit of the invention signal
Figure;
Fig. 3 is the schematic diagram of the acquisition fraud scoring step of the anti-fraud method for credit of the invention;
Fig. 4 is the module architectures schematic diagram of the anti-rogue device for credit of the invention;
Fig. 5 is the structural framing schematic diagram of the anti-fake system for credit of the invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with specific embodiment, and reference
Attached drawing, the present invention is described in further detail.
Fig. 1 is flow diagram of the present invention for the anti-fraud method of credit.As shown in Figure 1, method of the invention has
It has the following steps:
S1, firstly, the present invention obtain Debit User data and establish the anti-fraud scoring model based on label.
The present invention identifies the potentially Debit User there may be fraud using anti-fraud scoring model.And credit
Rating Model is similar, and anti-fraud scoring model ultimately generates a fraud scoring.For example, can with a number between 0 and 1 come
It indicates, 1 represents high probability of cheating, is represented with 0 without probability of cheating.
Anti- fraud scoring model of the invention is based on label, and so-called " label " refers to the variable of model, label value
That is variate-value." label " is sometimes referred to as characterized.Anti- fraud scoring model of the invention can be implemented as parameter model, can also be with
It is non-moduli type, parameter model includes linear regression model (LRM), Logic Regression Models etc., and non-moduli type includes decision tree, nerve net
Network, linear programming etc..
Label be generally divided into classification standard, two metatags, nominal label, sequence tags, numeric label, continuous label, from
Dissipate label etc..Tag along sort indicates the grouping situation that is determined by qualitative features, such as gender (male, female) or color (yellow, red,
It is blue);Two metatags are only made of two categories, such as " Yes/No ", or other a pair of of antonyms;Nominal label refers to use
The variable that name or code indicate, does not represent relative rank;Sequence tags then indicate relative position in a sequence, but do not indicate
Relative distance size is usually related with subjective assessment such as outstanding, good, general or poor.Numeric label usually use integer or
Real number representation has relative size meaning, can be carried out mathematical operation.Continuous label is present in continuous sequence, probable value
Endless number, there are maximum values and minimum value, such as time, distance etc.;Discrete variable is separation or discontinuous numerical value.This
Invention is not limited to the type of label, i.e., any possible tag types may be applied in the present invention.
The label data of general credit scoring includes personal information, income information, liability information, history reference note
Record, company and trade information etc., these information can be collectively referred to as Debit User data.Anti- fraud scoring model of the invention equally needs
Want Debit User data.But, it is contemplated that Debit User data are able to reflect certain credit level, but are not enough to reflect user
Whether it is that there may be fraud " bad persons ", i.e., cannot reflects that user can be carried out fraud and cheat loan behavior well, therefore,
The present invention proposes, also needs to introduce other labels when establishing anti-fraud scoring model, referred to herein as credit is associated with personal data mark
Label.
So-called credit affiliated person, which refers to, in the present invention with Debit User there is Identity Association, behavior to be associated with, Attribute Association
People.A kind of its embodiment refers to the social relationships affiliated person of Debit User, as kinsfolk, colleague, friend or other
The more close people of social relationships.Another embodiment, which refers to, has the associated people of behavior with Debit User, such as therebetween
It is recorded with message registration, short message.Another embodiment refers to that the two has Attribute Association, for example, the two band of position weight
Right higher, the two is located at same IP address section, etc..
S2, secondly, the present invention according to the Debit User data and affiliated person's information of Debit User, obtains credit uses
Family is associated with personal data.
The step of Fig. 2 is the acquisition Debit User association personal data of the anti-fraud method for credit of the invention signal
Figure.As shown in Fig. 2, in general, Debit User data can be directly acquired from the existing database for credit scoring, this hair
Bright method needs are directly extracted or are calculated for the anti-label data cheated from these databases.However, for letter
The association personal data for borrowing user, can not usually directly obtain, and therefore, the present invention proposes, according to Debit User data, from existing
Association personal data is obtained in database or external data base, here, these databases are referred to as linked database by us.
Currently, can obtain through a variety of ways to obtain affiliated person's information of Debit User, affiliated person's letter how is obtained
Breath is not the problem of present invention discusses.But, by way of example, it can be by inquiring the data comprising social relationships data
Library can get the social relationships affiliated person of Debit User, by inquiring database (message registration, online shopping comprising user behavior
Record, APP address list etc.), it can get the behavior relation affiliated person of Debit User.
It, can be according to the data for credit scoring comprising affiliated person's information after obtaining Debit User affiliated person information
Association personal data is obtained in library or other databases, and is made and be used for the anti-affiliated person's data label cheated.For example, can be from letter
With obtained in score data library affiliated person provide a loan number, the amount of the loan, the time of providing a loan, number of rejecting loans, overdue number, by collection time
Number, the record being rejected with the presence or absence of credit, with the presence or absence of by the record of collection.Alternatively, being obtained in the telecommunications databases that can go on an expedition
The collage-credit data of affiliated person.Alternatively, can also obtain whether affiliated person is marked as intermediary from the behavior database of affiliated person,
Etc..
Furthermore the Debit User association personal data other than including above-mentioned affiliated person's individual data items, may be used also by the present invention
To calculate the affiliated person's statistical data for being directed to some Debit User according to the individual data items of affiliated person, these data are, for example, to be associated with
Everybody counts, affiliated person's number for having record of rejecting loans, the affiliated person's accounting for having record of rejecting loans, the affiliated person's number for having overdue record,
There are affiliated person's accounting of overdue record, the affiliated person's number for thering is collection to record, the affiliated person's accounting for thering is collection to record etc..Have
These data, so that it may make affiliated person's individual data items label and affiliated person's statistical data label.
S3, finally, the present invention by the Debit User data and Debit User affiliated person data creating at label after it is defeated
Enter the anti-fraud scoring model, obtains the fraud scoring of Debit User, and corresponding anti-fraud is taken according to the fraud scoring
Measure.
Fig. 3 is the schematic diagram of the acquisition fraud scoring step of the anti-fraud method for credit of the invention.Such as Fig. 3 institute
Show, after obtaining the association personal data of Debit User data and Debit User, these data are input to counter take advantage of by the present invention
It is calculated in swindleness Rating Model.As previously mentioned, the model can be existing any model, but the present invention is preferably pair
Model is trained with sample using neural network model, and in advance.Root is their ability to using the advantages of neural network model
It makes adjustment according to the variation of fraud mode.
After the anti-fraud scoring model receives the association personal data of Debit User data and Debit User, it will calculate
Obtain the fraud scoring of a certain Debit User.Thus, it is possible to the threshold value of a fraud scoring be set, according to the height of fraud scoring
To be performed corresponding processing to different Debit Users, such as be marked, refuse, reducing loan limit etc..
Fig. 4 is configuration diagram of the present invention for the anti-rogue device of credit.As shown in figure 4, the device of the invention packet
Include Debit User data acquisition module, Debit User affiliated person data acquisition module and fraud scoring computing module.Generally speaking,
Debit User data acquisition module is for obtaining Debit User data, and Debit User affiliated person's data acquisition module is then used to obtain
It wins the confidence and borrows user-association personal data, Debit User data are associated with personal data with Debit User and are admitted to fraud scoring computing module,
Fraud scoring computing module is described anti-at inputting after label by the Debit User data and Debit User affiliated person data creating
Fraud scoring model obtains the fraud scoring of Debit User.
As previously mentioned, common Debit User data include personal information, income information, liability information, history reference note
Record, company and trade information etc..Debit User affiliated person data acquisition module is then according to the Debit User data and credit
Affiliated person's information of user obtains Debit User and is associated with personal data.Debit User data can be used for credit scoring from existing
Database in directly acquire, the device of the invention need from these databases directly extract or be calculated for instead cheat
Label data.However, can not usually directly obtain for the association personal data of Debit User, therefore, the present invention is proposed, root
It is believed that borrowing user data, association personal data (linked database) is obtained from existing database or external data base.
After obtaining Debit User affiliated person information, fraud scoring computing module can be according to the use comprising affiliated person's information
Association personal data is obtained in the database of credit scoring or other databases, and is made and be used for the anti-association personal data mark cheated
Label.For example, can be obtained from credit scoring database affiliated person provide a loan number, the amount of the loan, the time of providing a loan, number of rejecting loans,
Overdue number, the record being rejected by collection number, with the presence or absence of credit, with the presence or absence of by the record of collection.Alternatively, can be from
The collage-credit data of affiliated person is obtained in collage-credit data library.Alternatively, affiliated person can also be obtained from the behavior database of affiliated person
Whether intermediary, etc. is marked as.Furthermore Debit User association personal data in addition to include above-mentioned affiliated person's individual data items it
Outside, the present invention can also calculate the affiliated person's statistical data for being directed to some Debit User according to the individual data items of affiliated person, these
Data are, for example, affiliated person's number, the affiliated person's number for having record of rejecting loans, the affiliated person's accounting for having record of rejecting loans, have overdue record
Affiliated person's number, have overdue record affiliated person's accounting, have collection record affiliated person's number, have collection record affiliated person
Accounting etc..There are these data, so that it may make affiliated person's individual data items label and affiliated person's statistical data label.
Certainly, fraud scoring computing module is firstly the need of including for establishing the anti-fraud scoring model based on label.Tool
For body, referring to fig. 2, the fraud scoring computing module includes model foundation unit and model instruction unit, is respectively used to build
Be based on label anti-fraud scoring model and the anti-fraud scoring model is trained.Training sample includes Debit User
Data are associated with personal data with Debit User.
The anti-fraud scoring model described in fraud scoring computing module receives the association of Debit User data and Debit User
After personal data, the fraud scoring of a certain Debit User is calculated., fraud scoring computing module can set a fraud and comment
The threshold value divided, performs corresponding processing different Debit Users according to the height of fraud scoring, such as be marked, refuse
Absolutely, loan limit etc. is reduced.
In addition, the present invention also proposes the anti-fake system for credit.Fig. 5 is that the anti-fraud for credit of the invention is
The structural framing schematic diagram of system is deposited as shown in figure 5, the anti-fake system for credit includes memory and data processing equipment
For reservoir for storing computer executable program, data processing equipment is executable for reading the computer in the memory
Program, to execute the anti-fraud method for credit.System can be local system in the present invention, be also possible to be distributed
Formula system.Memory of the invention can be local storage, be also possible to distributed memory system, such as cloud storage system.
And data processor then includes the device of at least one tool number word information processing capability, such as CPU, GPU, multicomputer system
Or cloud processor.
Furthermore the present invention also proposes computer-readable medium, described computer-readable for storing computer-readable program
Program is used to execute the anti-fraud method for credit.
It should be appreciated that in order to simplify the present invention and help it will be understood by those skilled in the art that various aspects of the invention,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is retouched in a single embodiment sometimes
It states, or is described referring to single figure.But should not be by the feature that the present invention is construed to include in exemplary embodiment
The essential features of patent claims.
It should be appreciated that can be to progress such as module, unit, the components for including in the equipment of one embodiment of the present of invention certainly
It adaptively changes so that they are arranged in equipment unlike this embodiment.The difference that can include the equipment of embodiment
Module, unit or assembly are combined into module, a unit or assembly, also they can be divided into multiple submodule, subelement or
Sub-component.Module, unit or assembly in the embodiment of the present invention can realize in hardware, can also be with one or more
The software mode run on a processor is realized, or is implemented in a combination thereof.
Particular embodiments described above has carried out further in detail the purpose of the present invention, technical scheme and beneficial effects
Describe in detail bright, it should be understood that the above is only a specific embodiment of the present invention, is not intended to restrict the invention, it is all
Within the spirit and principles in the present invention, any modification, equivalent substitution, improvement and etc. done should be included in protection of the invention
Within the scope of.
Claims (12)
1. a kind of anti-fraud method for credit, includes the following steps:
It obtains Debit User data and establishes the anti-fraud scoring model based on label;
According to the Debit User data and affiliated person's information of Debit User, obtains Debit User and be associated with personal data;
By the Debit User data and Debit User affiliated person data creating at inputting the anti-fraud scoring model after label,
The fraud scoring of Debit User is obtained, and corresponding anti-fraud measure is taken according to the fraud scoring.
2. being used for the anti-fraud method of credit as described in claim 1, it is characterised in that:
Further include the steps that the anti-fraud scoring model training, training sample includes that Debit User data and Debit User close
Join personal data.
3. being used for the anti-fraud method of credit as described in claim 1, it is characterised in that: the Debit User is associated with personal data
Including affiliated person's individual data items.
4. being used for the anti-fraud method of credit as described in claim 1, it is characterised in that: the Debit User is associated with personal data
Including affiliated person's statistical data.
5. being used for the anti-fraud method of credit as claimed in claim 4, it is characterised in that: affiliated person's statistical data includes
At least one of following data: affiliated person's number, the affiliated person's number for having record of rejecting loans, the affiliated person's accounting for having record of rejecting loans,
There is affiliated person's number of overdue record, the affiliated person's accounting for having overdue record, the affiliated person's number for thering is collection to record, have collection note
Affiliated person's accounting of record.
6. a kind of anti-rogue device for credit, comprising:
Debit User data acquisition module, for obtaining Debit User data;
Debit User affiliated person's data acquisition module, for being believed according to the affiliated person of the Debit User data and Debit User
Breath obtains Debit User and is associated with personal data;
Fraud scoring computing module, for establishing the anti-fraud scoring model based on label, and by the Debit User data and
Debit User affiliated person data creating obtains the fraud scoring of Debit User at the anti-fraud scoring model is inputted after label.
7. being used for the anti-rogue device of credit as claimed in claim 6, it is characterised in that:
The fraud scoring computing module includes:
Model foundation unit, for establishing the anti-fraud scoring model based on label;
Model training unit, for being trained to the anti-fraud scoring model, training sample include Debit User data and
Debit User is associated with personal data.
8. being used for the anti-rogue device of credit as claimed in claim 6, it is characterised in that: the Debit User is associated with personal data
Including affiliated person's individual data items.
9. being used for the anti-rogue device of credit as claimed in claim 6, it is characterised in that: the Debit User is associated with personal data
Including affiliated person's statistical data.
10. being used for the anti-rogue device of credit as claimed in claim 9, it is characterised in that: affiliated person's statistical data packet
Include at least one of following data: affiliated person's number, has the affiliated person for record of rejecting loans to account at the affiliated person's number for having record of rejecting loans
Than, affiliated person's number for having overdue record, the affiliated person's accounting for having overdue record, the affiliated person's number for thering is collection to record, urge
Receive affiliated person's accounting of record.
11. a kind of anti-fake system for credit characterized by comprising
Memory, for storing computer executable program;
Data processing equipment is required in 1 to 5 for reading the computer executable program in the memory with perform claim
Described in any item anti-fraud methods for credit.
12. a kind of computer-readable medium, for storing computer-readable program, which is characterized in that the computer-readable journey
Sequence is for the anti-fraud method for credit described in any one of perform claim requirement 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910330420.9A CN110119980A (en) | 2019-04-23 | 2019-04-23 | A kind of anti-fraud method, apparatus, system and recording medium for credit |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910330420.9A CN110119980A (en) | 2019-04-23 | 2019-04-23 | A kind of anti-fraud method, apparatus, system and recording medium for credit |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110119980A true CN110119980A (en) | 2019-08-13 |
Family
ID=67521316
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910330420.9A Pending CN110119980A (en) | 2019-04-23 | 2019-04-23 | A kind of anti-fraud method, apparatus, system and recording medium for credit |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110119980A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110795466A (en) * | 2019-09-18 | 2020-02-14 | 平安银行股份有限公司 | Anti-fraud method based on big data processing, server and computer-readable storage medium |
CN111192045A (en) * | 2019-12-16 | 2020-05-22 | 北京淇瑀信息科技有限公司 | Anti-cheating method, device and system based on transaction record information |
CN111199473A (en) * | 2019-12-16 | 2020-05-26 | 北京淇瑀信息科技有限公司 | Anti-cheating method, device and system based on transaction record information |
CN112419040A (en) * | 2020-10-31 | 2021-02-26 | 国家电网有限公司 | Credit anti-fraud identification method, credit anti-fraud identification device and storage medium |
CN116151965A (en) * | 2023-04-04 | 2023-05-23 | 成都新希望金融信息有限公司 | Risk feature extraction method and device, electronic equipment and storage medium |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105701706A (en) * | 2016-01-28 | 2016-06-22 | 北京量科邦信息技术有限公司 | A method for determining the credit rating of a user according to credit standing of contact persons |
CN107220867A (en) * | 2017-04-20 | 2017-09-29 | 北京小度信息科技有限公司 | object control method and device |
CN107248114A (en) * | 2017-06-01 | 2017-10-13 | 世纪禾光科技发展(北京)有限公司 | Electric business loan administration method and system |
CN109035003A (en) * | 2018-07-04 | 2018-12-18 | 北京玖富普惠信息技术有限公司 | Anti- fraud model modelling approach and anti-fraud monitoring method based on machine learning |
CN109165840A (en) * | 2018-08-20 | 2019-01-08 | 平安科技(深圳)有限公司 | Risk profile processing method, device, computer equipment and medium |
CN109166030A (en) * | 2018-08-01 | 2019-01-08 | 深圳微言科技有限责任公司 | A kind of anti-fraud solution and system |
CN109272396A (en) * | 2018-08-20 | 2019-01-25 | 平安科技(深圳)有限公司 | Customer risk method for early warning, device, computer equipment and medium |
CN109522317A (en) * | 2018-09-05 | 2019-03-26 | 深圳市佰仟金融服务有限公司 | A kind of anti-fraud method for early warning and system |
CN109636565A (en) * | 2018-10-16 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Processing method, device, equipment and the computer readable storage medium of risk data |
-
2019
- 2019-04-23 CN CN201910330420.9A patent/CN110119980A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105701706A (en) * | 2016-01-28 | 2016-06-22 | 北京量科邦信息技术有限公司 | A method for determining the credit rating of a user according to credit standing of contact persons |
CN107220867A (en) * | 2017-04-20 | 2017-09-29 | 北京小度信息科技有限公司 | object control method and device |
CN107248114A (en) * | 2017-06-01 | 2017-10-13 | 世纪禾光科技发展(北京)有限公司 | Electric business loan administration method and system |
CN109035003A (en) * | 2018-07-04 | 2018-12-18 | 北京玖富普惠信息技术有限公司 | Anti- fraud model modelling approach and anti-fraud monitoring method based on machine learning |
CN109166030A (en) * | 2018-08-01 | 2019-01-08 | 深圳微言科技有限责任公司 | A kind of anti-fraud solution and system |
CN109165840A (en) * | 2018-08-20 | 2019-01-08 | 平安科技(深圳)有限公司 | Risk profile processing method, device, computer equipment and medium |
CN109272396A (en) * | 2018-08-20 | 2019-01-25 | 平安科技(深圳)有限公司 | Customer risk method for early warning, device, computer equipment and medium |
CN109522317A (en) * | 2018-09-05 | 2019-03-26 | 深圳市佰仟金融服务有限公司 | A kind of anti-fraud method for early warning and system |
CN109636565A (en) * | 2018-10-16 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Processing method, device, equipment and the computer readable storage medium of risk data |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110795466A (en) * | 2019-09-18 | 2020-02-14 | 平安银行股份有限公司 | Anti-fraud method based on big data processing, server and computer-readable storage medium |
CN111192045A (en) * | 2019-12-16 | 2020-05-22 | 北京淇瑀信息科技有限公司 | Anti-cheating method, device and system based on transaction record information |
CN111199473A (en) * | 2019-12-16 | 2020-05-26 | 北京淇瑀信息科技有限公司 | Anti-cheating method, device and system based on transaction record information |
CN112419040A (en) * | 2020-10-31 | 2021-02-26 | 国家电网有限公司 | Credit anti-fraud identification method, credit anti-fraud identification device and storage medium |
CN116151965A (en) * | 2023-04-04 | 2023-05-23 | 成都新希望金融信息有限公司 | Risk feature extraction method and device, electronic equipment and storage medium |
CN116151965B (en) * | 2023-04-04 | 2023-07-18 | 成都新希望金融信息有限公司 | Risk feature extraction method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI712981B (en) | Risk identification model training method, device and server | |
CN110119980A (en) | A kind of anti-fraud method, apparatus, system and recording medium for credit | |
WO2019196546A1 (en) | Method and apparatus for determining risk probability of service request event | |
US20200090268A1 (en) | Method and apparatus for determining level of risk of user, and computer device | |
CN108665159A (en) | A kind of methods of risk assessment, device, terminal device and storage medium | |
US8838499B2 (en) | Methods and systems for life stage modeling | |
CN110717816A (en) | Artificial intelligence technology-based global financial risk knowledge graph construction method | |
CN106600369A (en) | Real-time recommendation system and method of financial products of banks based on Naive Bayesian classification | |
CN106651570A (en) | System and method for real-time loan approval | |
CN112150298B (en) | Data processing method, system, device and readable medium | |
CN113989019A (en) | Method, device, equipment and storage medium for identifying risks | |
CN109472626B (en) | Intelligent financial risk control method and system for mobile phone leasing service | |
US20160180264A1 (en) | Retention risk determiner | |
CN113205093A (en) | Data asset analysis method, system and medium based on XGboost regression and convolution network | |
CN112232950A (en) | Loan risk assessment method and device, equipment and computer-readable storage medium | |
CN114971294A (en) | Data acquisition method, device, equipment and storage medium | |
CN109614496B (en) | Low security identification method based on knowledge graph | |
CN111047092A (en) | Dispute case victory rate prediction method and device, computer equipment and storage medium | |
JP2020173742A (en) | Information processor, information processing method, and program | |
CN110570301B (en) | Risk identification method, device, equipment and medium | |
CN109635289A (en) | Entry classification method and audit information abstracting method | |
CN114463119A (en) | Credit assessment method and device and electronic equipment | |
CN114880663A (en) | Black product cheating identification method and system based on anomaly detection | |
CN106570531A (en) | Payment device similarity calculation method and payment device similarity calculation system | |
CN111539834A (en) | Pre-check method and device |
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 |