CN106971338A - The method and apparatus of data assessment - Google Patents
The method and apparatus of data assessment Download PDFInfo
- Publication number
- CN106971338A CN106971338A CN201710284124.0A CN201710284124A CN106971338A CN 106971338 A CN106971338 A CN 106971338A CN 201710284124 A CN201710284124 A CN 201710284124A CN 106971338 A CN106971338 A CN 106971338A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- model
- assessment
- destination object
- 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
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a kind of method and apparatus of data assessment.Wherein, this method includes：Receive the data level assessment request of destination object；Risk assessment is carried out to data level assessment request according to pre-stored data Grade Model, the corresponding risk probability of destination object is obtained and loss late occurs for promise breaking；Occur loss late according to risk probability and promise breaking to be estimated, obtain the corresponding data level of destination object.The present invention is solved due to estimating user's loan limit defect empirically with expert's subjective judgement, the technical problem for causing data estimation precision low in correlation technique.
Description
Technical field
The present invention relates to Internet technology application field, in particular to a kind of method and apparatus of data assessment.
Background technology
With the high speed development of internet financial industry, the consumer finance is no longer the exclusive business of traditional financial, more next
More electric business platforms obtain consumer finance licence plate, possess the qualification for providing a user consumptive loan amount.
Traditional bank or third party financial institution (rear abbreviation fund side) are generally existed when offering a loan service with user
Transaction record and the credit card record of bank are as primary user data, and the credit situation to the user that provides a loan is estimated and with this
Assess the loan limit of user.But it is due to that the user that the own transaction record in fund side and credit card record are covered has very much
Limit, it is desirable to which the information dimension of the user actively information filled in or the proof of offer is very limited and authenticity is difficult to ensure that, therefore
The loan limit that the method for conventional money side is assessed can cause the problem of credit risk is high.
During some current electric business Platform evaluation user's loan limits, the history row with reference to user on platform is used as benefit
Fill, still, what user's loan limit appraisal procedure was used is still the method based on experience or expert estimation card, gives specific credit
The loan limit that the user of degree of risk specifies, the above method excessively dependence expert experience and subjective judgement, objectivity and
Accuracy is not enough, ageing to be also difficult to ensure that, while also not accounting for the loan transaction income of fund side.
For above-mentioned due to estimating user's loan limit defect empirically with expert's subjective judgement in correlation technique,
Cause the problem of data estimation precision is low, effective solution is not yet proposed at present.
The content of the invention
The embodiments of the invention provide a kind of method and apparatus of data assessment, at least to solve due to right in correlation technique
The defect of user's loan limit estimation empirically with expert's subjective judgement, the technical problem for causing data estimation precision low.
One side according to embodiments of the present invention there is provided a kind of method of data assessment, including：Receive destination object
Data level assessment request；Risk assessment is carried out to data level assessment request according to pre-stored data Grade Model, mesh is obtained
Mark the corresponding risk probability of object and loss late occurs for promise breaking；Occur loss late according to risk probability and promise breaking to be estimated, obtain
To the corresponding data level of destination object.
Optionally, risk assessment is carried out to data level assessment request according to pre-stored data Grade Model, obtains target pair
Include as loss late occurs for corresponding risk probability and promise breaking：Include in pre-stored data Grade Model：Credit Rating Model, user
Loss late model and data level occur for promise breaking with the case of expected revenus regression model, being disobeyed according to credit Rating Model, user
About occur loss late model and data level and set up data level model with expected revenus regression model；According to what is be previously received
The user data of destination object, occurs loss late model by credit Rating Model and user's promise breaking and is calculated, obtain target
Loss late occurs for the corresponding risk probability of object and promise breaking.
Further, optionally, user data includes：Subscriber identity information, user credit data and user behavior data.
Optionally, the user data according to the destination object being previously received, is broken a contract by credit Rating Model and user
Generation loss late model is calculated, and obtains the corresponding risk probability of destination object and promise breaking occurs loss late and included：According to letter
Calculated with rating model and user data, obtain user credit grading；The use graded and obtained in advance according to user credit
Family promise breaking prior probability is calculated, and obtains risk probability；The amount of money that acquisition destination object finally loses after promise breaking accounts for target
The ratio for the data level that object requests are obtained, occurs loss late model by user's promise breaking and is calculated, obtain promise breaking
Loss late.
Optionally, data level and expected revenus regression model, for prediction data approval object in preset time window
Interior income, and the data level of destination object is assessed, wherein, assessing the data level of destination object includes：According to assessment
Data approval object Profit Assessment destination object data level.
Another aspect according to embodiments of the present invention, additionally provides a kind of device of data assessment, including：Receiving module,
Data level assessment request for receiving destination object；First evaluation module, for according to pre-stored data Grade Model logarithm
Risk assessment is carried out according to grade assessment request, the corresponding risk probability of destination object is obtained and loss late occurs for promise breaking；Second comments
Estimate module, be estimated for occurring loss late according to risk probability and promise breaking, obtain the corresponding data level of destination object.
Optionally, the first evaluation module includes：Model sets up unit, for including in pre-stored data Grade Model：Credit
Rating model, user's promise breaking occur in the case of loss late model and data level and expected revenus regression model, are commented according to credit
Level model, user's promise breaking generation loss late model and data level and expected revenus regression model set up data level model；Comment
Estimate unit, for the user data according to the destination object being previously received, occur by credit Rating Model and user's promise breaking
Loss late model is calculated, and obtains the corresponding risk probability of destination object and loss late occurs for promise breaking.
Further, optionally, user data includes：Subscriber identity information, user credit data and user behavior data.
Optionally, assessment unit includes：First computation subunit, for according to credit Rating Model and user data progress
Calculate, obtain user credit grading；Second computation subunit, the user for grading and obtaining in advance according to user credit breaks a contract
Prior probability is calculated, and obtains risk probability；3rd computation subunit, finally loses for obtaining destination object after promise breaking
The amount of money account for destination object acquisition request data level ratio, by user promise breaking occur loss late model calculated,
Obtain promise breaking and occur loss late.
Optionally, data level and expected revenus regression model, for prediction data approval object in preset time window
Interior income, and the data level of destination object is assessed, wherein, assessing the data level of destination object includes：According to assessment
Data approval object Profit Assessment destination object data level.
Another aspect according to embodiments of the present invention, additionally provides a kind of storage medium, including：Storage medium includes storage
Program, wherein, the method that equipment where controlling storage medium when program is run performs above-mentioned data assessment.
Another aspect according to embodiments of the present invention, additionally provides a kind of processor, and processor is used for operation program, its
In, the method that program performs above-mentioned data assessment when running.
In embodiments of the present invention, by receiving the data level assessment request of destination object；According to pre-stored data grade
Model carries out risk assessment to data level assessment request, obtains the corresponding risk probability of destination object and promise breaking is lost
Rate；Occur loss late according to risk probability and promise breaking to be estimated, obtain the corresponding data level of destination object, reached synthesis
The purpose of destination object various dimensions information evaluation destination object data level, it is achieved thereby that the technology of lifting data estimation precision
Effect, and then solve due to estimating user's loan limit defect empirically with expert's subjective judgement in correlation technique,
The technical problem for causing data estimation precision low.
Brief description of the drawings
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, this hair
Bright schematic description and description is used to explain the present invention, does not constitute inappropriate limitation of the present invention.In the accompanying drawings：
Fig. 1 is the schematic flow sheet of the method for data assessment according to embodiments of the present invention；
Fig. 2 is the structural representation of the device of data assessment according to embodiments of the present invention.
Embodiment
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, rather than whole embodiments.Based on the embodiment in the present invention, ordinary skill people
The every other embodiment that member is obtained under the premise of creative work is not made, should all belong to the model that the present invention is protected
Enclose.
It should be noted that term " first " in description and claims of this specification and above-mentioned accompanying drawing, "
Two " etc. be for distinguishing similar object, without for describing specific order or precedence.It should be appreciated that so using
Data can exchange in the appropriate case, so as to embodiments of the invention described herein can with except illustrating herein or
Order beyond those of description is implemented.In addition, term " comprising " and " having " and their any deformation, it is intended that cover
Lid is non-exclusive to be included, for example, the process, method, system, product or the equipment that contain series of steps or unit are not necessarily limited to
Those steps or unit clearly listed, but may include not list clearly or for these processes, method, product
Or the intrinsic other steps of equipment or unit.
Embodiment one
According to embodiments of the present invention there is provided a kind of embodiment of the method for data assessment, it is necessary to illustrate, in accompanying drawing
The step of flow is illustrated can perform in the computer system of such as one group computer executable instructions, and, although
Logical order is shown in flow chart, but in some cases, can be to perform shown different from order herein or retouch
The step of stating.
Fig. 1 is the schematic flow sheet of the method for data assessment according to embodiments of the present invention, as shown in figure 1, this method bag
Include following steps：
Step S102, receives the data level assessment request of destination object；
Step S104, carries out risk assessment to data level assessment request according to pre-stored data Grade Model, obtains target
Loss late occurs for the corresponding risk probability of object and promise breaking；
Step S106, occurs loss late according to risk probability and promise breaking and is estimated, obtain the corresponding data of destination object
Grade.
Specifically, with reference to step S102 to step S106, the method for the data assessment that the present embodiment passes through receives mesh first
Mark the data level assessment request that object is initiated；Second, the data level assessment request is entered according to pre-stored data Grade Model
Row risk assessment, obtains the corresponding risk probability of the destination object and loss late occurs for promise breaking, finally according to the risk probability and
Promise breaking occurs loss late and is estimated, and obtains the corresponding data level of destination object (that is, the loan limit of the destination object).
Wherein, the method for the data assessment that the present embodiment is provided goes for the process that electric business platform is made loans to user
In, either bank loan or personalized lending, by the network platform, user's (that is, this implementation to each application loan requests
Destination object in example) risk assessment of aptitude checking and lender (for example, bank) is carried out, finally giving the user can borrow
The loan limit of money, the method for the data assessment provided in the embodiment of the present application is by pre-stored data Grade Model to user's
User profile is learnt, and automatically generates user risk probability that may be present and loss late occurs for promise breaking, can be somebody's turn to do
The loan limit of user, moreover it is possible to assess credit risk and investment return for lender, in estimation of the lifting to user's loan limit
While precision, more references are provided for lender.
In embodiments of the present invention, by receiving the data level assessment request of destination object；According to pre-stored data grade
Model carries out risk assessment to data level assessment request, obtains the corresponding risk probability of destination object and promise breaking is lost
Rate；Occur loss late according to risk probability and promise breaking to be estimated, obtain the corresponding data level of destination object, reached synthesis
The purpose of destination object various dimensions information evaluation destination object data level, it is achieved thereby that the technology of lifting data estimation precision
Effect, and then solve due to estimating user's loan limit defect empirically with expert's subjective judgement in correlation technique,
The technical problem for causing data estimation precision low.
Optionally, risk assessment is carried out to data level assessment request according to pre-stored data Grade Model in step S104,
Obtain the corresponding risk probability of destination object and promise breaking occurs loss late and included：
Step1, includes in pre-stored data Grade Model：Loss late model sum occurs for credit Rating Model, user's promise breaking
In the case of grade and expected revenus regression model, occur loss late model and data according to credit Rating Model, user's promise breaking
Grade sets up data level model with expected revenus regression model；
Step2, according to the user data for the destination object being previously received, is sent out by credit Rating Model and user's promise breaking
Raw loss late model is calculated, and obtains the corresponding risk probability of destination object and loss late occurs for promise breaking.
Further, optionally, user data includes：Subscriber identity information, user credit data and user behavior data.
Optionally, the user data for the destination object that the foundation in step S104 in Step2 is previously received, passes through credit
Rating model and user's promise breaking occur loss late model and calculated, and obtain the corresponding risk probability of destination object and promise breaking occurs
Loss late includes：
Step A, is calculated according to credit Rating Model and user data, obtains user credit grading；
Step B, the user's promise breaking prior probability graded and obtained in advance according to user credit is calculated, and obtains risk general
Rate；
Step C, the amount of money that acquisition destination object finally loses after promise breaking accounts for the data level of destination object acquisition request
Ratio, by user promise breaking occur loss late model calculated, obtain promise breaking generation loss late.
Optionally, data level and expected revenus regression model, for prediction data approval object in preset time window
Interior income, and the data level of destination object is assessed, wherein, assessing the data level of destination object includes：According to assessment
Data approval object Profit Assessment destination object data level.
To sum up, the method for the data assessment that the present embodiment is provided is specific as follows：
The method for the data assessment that the present embodiment is provided goes for loan limit appraisal procedure, applied to electric business platform
The consumptive credit amount of user is assessed, including：The credit of user is set up previously according to subscriber identity information and user behavior data
Loss late model occurs for rating model and user's promise breaking；The number for user's utilization of a loan amount generation income of being provided a loan previously according to history
According to the regression model for setting up loan limit and expected revenus, (that is, credit Rating Model, user's promise breaking in the present embodiment are damaged
Mistake rate model and data level and expected revenus regression model)；Damaged previously according to user credit rating model, user's promise breaking
Mistake rate model and loan limit set up user's loan limit model (that is, data in the present embodiment with expected revenus regression model
Grade Model)；Loss late model is occurred based on above-mentioned user credit rating model and user's promise breaking, and according to the above-mentioned use of user
User data obtains the credit default risk probability (that is, the risk probability in the present embodiment) of the user respectively and promise breaking is lost
Rate；Based on user's line of credit model, and loss late occurs for user's default risk probability according to acquisition and promise breaking to assess use
The available line of credit (that is, the data level in the present embodiment) at family.
The risk of Debit User is considered in the method for the data assessment that the present embodiment is provided, cost, it is contemplated that income is built
Vertical expected revenus equation, the loan value angle value for credit operation maximum revenue of sening as an envoy to is calculated by optimal method.
It is specific as follows：(1) user credit rating model is pre-established, including：With machine learning GBDT algorithms, by learning
The user data of history promise breaking user is practised, to learn user credit rating model.Wherein promise breaking user refers to letter is awarded
Borrow amount but the user not refunded on schedule.Wherein user data, including subscriber identity information, user credit data, Yong Huhang
For data.Wherein user credit data include：User credit card usage record, user's loan documentation.Wherein user behavior data
Including：History Order consumption data that user produces on electric business platform, history bank card payment data, using terminal data,
Internet behavior data.
(2) user's default risk probability is calculated based on user credit rating model and user data, in addition to：Based on user
Credit Rating Model and user data calculate user credit grading, general based on the grading of above-mentioned user credit and user's promise breaking priori
Rate calculates user's default risk probability, specific above-mentioned calculation formula：
Wherein, p (G) represents user's promise breaking prior probability, and p (B) represents the non-promise breaking prior probability of user, NGRepresent history letter
Borrow the quantity that user does not break a contract, NBRepresent the quantity that history Debit User is broken a contract；P (g | G) represent non-promise breaking user
The probability for being rated g, p (g | B) represents that promise breaking user is rated g probability, and p (B | g) represents the correspondence when user is rated g
Default Probability, PD represents the default risk probability of user.
(3) user's promise breaking is obtained in advance occur loss late, including：Obtain loan limit user loan break a contract after most
The amount of money of loss takes the ratio of family loan limit eventually, wherein the loan that loan generation promise breaking specifically refers to user is refunded finally
Day expire after it is overdue exceed specify time span be designated as loan break a contract.
(4) regression model of loan limit and expected revenus is pre-established, including：Obtain Debit User in preset time
In the range of loan income, based on above-mentioned user provide a loan income calculation specify line of credit under expectation provide a loan income；It is based on
Above-mentioned user's loan limit sets up regression equation with the expectation loan income under specified line of credit, and mathematic(al) representation is as follows：
E(R；L)=∑ p (R | L) R
E(R；L)=f (L)=aL2+b·L+c
Wherein, R represents the loan income in preset time range of Debit User, E (R；L) represent in specified line of credit
The expectation loan income spent under L, a represents the secondary term coefficient of regression equation, and b represents the Monomial coefficient of regression equation, and c is represented
The constant term of regression equation.
(5) regression equation and use are set up based on the expectation loan income under above-mentioned user's loan limit and specified line of credit
Loan avail data is expected at family, utilizes the value of the quadratic term in least-squares algorithm accounting equation, first order and constant term.
(6) the loan income in preset time range of Debit User is obtained, calculation formula is as follows：
R=Ri+Rc+Rp-C
Wherein, R represents the loan income in preset time range of Debit User, RiRepresent presetting for Debit User
Loan interest income in time range, RcRepresent the saving payment channel expense in preset time range of Debit User, Rp
Represent Debit User in preset time range loan consumption interest rate lifting, C represent Debit User in preset time model
Enclose interior loan fund cost.
(7) loan limit assessment models are pre-established, in addition to the income produced according to historic user sets up loan limit
With the regression model of expected revenus, income of the prediction user in preset time window；Assess the loan limit of loan user
Evaluation scheme, in addition to, assess the income of loan user；Assess loan user can loan limit, in addition to：According to assessment
The profit of loan user can loan limit come assess loan user.
(8) loan limit assessment models can be using prime minister as following mathematic(al) representations：
Wherein, L is loan limit；E(R；L it is) regression equation of loan limit and expected revenus；PD is user's promise breaking wind
Dangerous probability, LGD is user's loss given default, and T is user credit risk threshold value, and argmax, which represents to calculate, causes whole formula value most
Big L is result of calculation.
The present embodiment provide data assessment method in go for loan limit appraisal procedure, due to mainly with
Family collage-credit data and internet behavioral data are data basis, therefore both the risk situation of user can accurately be estimated,
Again supplemented with a large amount of high-dimensional internet behavioral datas, so as to finally provide the loan limit for more reasonably assessing user.
In addition, the loan limit appraisal procedure based on change networking behavioral data not only obtain user credit rating have also obtained promise breaking damage
Mistake rate, because loss given default is to influence the key factor of credit risk, factor is closed based on the credit scoring and loss given default
Loan limit is assessed on reason ground, so as to the credit risk of further reduction loan.
Embodiment two
Fig. 2 is the structural representation of the device of data assessment according to embodiments of the present invention, as shown in Fig. 2 the device bag
Include：
Receiving module 21, the data level assessment request for receiving destination object；First evaluation module 22, for foundation
Pre-stored data Grade Model carries out risk assessment to data level assessment request, obtains the corresponding risk probability of destination object and disobeys
About occurs loss late；Second evaluation module 23, is estimated for occurring loss late according to risk probability and promise breaking, obtains target
The corresponding data level of object.
In embodiments of the present invention, by receiving the data level assessment request of destination object；According to pre-stored data grade
Model carries out risk assessment to data level assessment request, obtains the corresponding risk probability of destination object and promise breaking is lost
Rate；Occur loss late according to risk probability and promise breaking to be estimated, obtain the corresponding data level of destination object, reached synthesis
The purpose of destination object various dimensions information evaluation destination object data level, it is achieved thereby that the technology of lifting data estimation precision
Effect, and then solve due to estimating user's loan limit defect empirically with expert's subjective judgement in correlation technique,
The technical problem for causing data estimation precision low.
Optionally, the first evaluation module 22 includes：Model sets up unit, for including in pre-stored data Grade Model：Letter
In the case of rating model, user's promise breaking generation loss late model and data level and expected revenus regression model, according to credit
Rating model, user's promise breaking generation loss late model and data level and expected revenus regression model set up data level model；
Assessment unit, for the user data according to the destination object being previously received, is sent out by credit Rating Model and user's promise breaking
Raw loss late model is calculated, and obtains the corresponding risk probability of destination object and loss late occurs for promise breaking.
Further, optionally, user data includes：Subscriber identity information, user credit data and user behavior data.
Optionally, assessment unit includes：First computation subunit, for according to credit Rating Model and user data progress
Calculate, obtain user credit grading；Second computation subunit, the user for grading and obtaining in advance according to user credit breaks a contract
Prior probability is calculated, and obtains risk probability；3rd computation subunit, finally loses for obtaining destination object after promise breaking
The amount of money account for destination object acquisition request data level ratio, by user promise breaking occur loss late model calculated,
Obtain promise breaking and occur loss late.
Optionally, data level and expected revenus regression model, for prediction data approval object in preset time window
Interior income, and the data level of destination object is assessed, wherein, assessing the data level of destination object includes：According to assessment
Data approval object Profit Assessment destination object data level.
Embodiment three
Another aspect according to embodiments of the present invention, additionally provides a kind of storage medium, including：Storage medium includes storage
Program, wherein, the method that equipment where controlling storage medium when program is run performs above-mentioned data assessment.
Example IV
Another aspect according to embodiments of the present invention, additionally provides a kind of processor, and processor is used for operation program, its
In, the method that program performs above-mentioned data assessment when running.
The embodiments of the present invention are for illustration only, and the quality of embodiment is not represented.
In the above embodiment of the present invention, the description to each embodiment all emphasizes particularly on different fields, and does not have in some embodiment
The part of detailed description, may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed technology contents, others can be passed through
Mode is realized.Wherein, device embodiment described above is only schematical, such as division of described unit, Ke Yiwei
A kind of division of logic function, can there is other dividing mode when actually realizing, such as multiple units or component can combine or
Person is desirably integrated into another system, or some features can be ignored, or does not perform.Another, shown or discussed is mutual
Between coupling or direct-coupling or communication connection can be the INDIRECT COUPLING or communication link of unit or module by some interfaces
Connect, can be electrical or other forms.
The unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On unit.Some or all of unit therein can be selected to realize the purpose of this embodiment scheme according to the actual needs.
In addition, each functional unit in each embodiment of the invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If the integrated unit is realized using in the form of SFU software functional unit and as independent production marketing or used
When, it can be stored in a computer read/write memory medium.Understood based on such, technical scheme is substantially
The part contributed in other words to prior art or all or part of the technical scheme can be in the form of software products
Embody, the computer software product is stored in a storage medium, including some instructions are to cause a computer
Equipment (can for personal computer, server or network equipment etc.) perform each embodiment methods described of the invention whole or
Part steps.And foregoing storage medium includes：USB flash disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic disc or CD etc. are various can be with store program codes
Medium.
Described above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (12)
1. a kind of method of data assessment, it is characterised in that including：
Receive the data level assessment request of destination object；
Risk assessment is carried out to the data level assessment request according to pre-stored data Grade Model, the destination object pair is obtained
Loss late occurs for the risk probability and promise breaking answered；
Occur loss late according to the risk probability and the promise breaking to be estimated, obtain corresponding data of the destination object etc.
Level.
2. the method for data assessment according to claim 1, it is characterised in that described according to pre-stored data Grade Model pair
The data level assessment request carries out risk assessment, obtains the corresponding risk probability of the destination object and promise breaking is lost
Rate includes：
Include in the pre-stored data Grade Model：Loss late model and data level occur for credit Rating Model, user's promise breaking
In the case of expected revenus regression model, occur loss late model and institute according to the credit Rating Model, user promise breaking
State data level and set up data level model with expected revenus regression model；
According to the user data for the destination object being previously received, broken a contract by the credit Rating Model and the user
Generation loss late model is calculated, and obtains the corresponding risk probability of the destination object and the promise breaking is lost
Rate.
3. the method for data assessment according to claim 2, it is characterised in that the user data includes：User identity
Information, user credit data and user behavior data.
4. the method for data assessment according to claim 2, it is characterised in that the mesh that the foundation is previously received
The user data of object is marked, occurring loss late model by the credit Rating Model and user promise breaking is calculated, and is obtained
Occurring loss late to the corresponding risk probability of the destination object and the promise breaking includes：
Calculated according to the credit Rating Model and the user data, obtain user credit grading；
The user's promise breaking prior probability graded and obtained in advance according to the user credit is calculated, and obtains the risk general
Rate；
Obtain the data level that the amount of money that the destination object finally loses after promise breaking accounts for the destination object acquisition request
Ratio, occurs loss late model by user promise breaking and is calculated, and obtains the promise breaking and occurs loss late.
5. the method for data assessment according to claim 2, it is characterised in that the data level is returned with expected revenus
Model, for income of the prediction data approval object in preset time window, and assess the data of the destination object etc.
Level, wherein, the data level for assessing the destination object includes：According to the receipts of the data approval object of assessment
Benefit assesses the data level of the destination object.
6. a kind of device of data assessment, it is characterised in that including：
Receiving module, the data level assessment request for receiving destination object；
First evaluation module, for carrying out risk assessment to the data level assessment request according to pre-stored data Grade Model,
Obtain the corresponding risk probability of the destination object and loss late occurs for promise breaking；
Second evaluation module, is estimated for occurring loss late according to the risk probability and the promise breaking, obtains the mesh
Mark the corresponding data level of object.
7. the device of data assessment according to claim 6, it is characterised in that first evaluation module includes：
Model sets up unit, for including in the pre-stored data Grade Model：Credit Rating Model, user's promise breaking are lost
Rate model and data level according to the credit Rating Model, user promise breaking with the case of expected revenus regression model, sending out
Raw loss late model and the data level set up data level model with expected revenus regression model；
Assessment unit, for the user data according to the destination object being previously received, passes through the credit Rating Model
Occur loss late model with user promise breaking to be calculated, obtain the corresponding risk probability of the destination object and described
Loss late occurs for promise breaking.
8. the device of data assessment according to claim 7, it is characterised in that the user data includes：User identity
Information, user credit data and user behavior data.
9. the device of data assessment according to claim 7, it is characterised in that the assessment unit includes：
First computation subunit, for being calculated according to the credit Rating Model and the user data, obtains user's letter
With grading；
Second computation subunit, based on the user's promise breaking prior probability progress graded and obtained in advance according to the user credit
Calculate, obtain the risk probability；
3rd computation subunit, for obtain the amount of money that the destination object finally loses after promise breaking account for the destination object please
The ratio of the data level of acquisition is sought, occurring loss late model by user promise breaking is calculated, obtain the promise breaking hair
Raw loss late.
10. the device of data assessment according to claim 7, it is characterised in that the data level is returned with expected revenus
Return model, for income of the prediction data approval object in preset time window, and assess the data of the destination object
Grade, wherein, the data level for assessing the destination object includes：According to the data approval object of assessment
The data level of destination object described in Profit Assessment.
11. a kind of storage medium, it is characterised in that the storage medium includes the program of storage, wherein, in described program operation
When control the storage medium where data assessment in equipment perform claim requirement 1 to 5 described in any one method.
12. a kind of processor, it is characterised in that the processor is used for operation program, wherein, right of execution when described program is run
The method that profit requires the data assessment described in any one in 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710284124.0A CN106971338A (en) | 2017-04-26 | 2017-04-26 | The method and apparatus of data assessment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710284124.0A CN106971338A (en) | 2017-04-26 | 2017-04-26 | The method and apparatus of data assessment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106971338A true CN106971338A (en) | 2017-07-21 |
Family
ID=59332827
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710284124.0A Pending CN106971338A (en) | 2017-04-26 | 2017-04-26 | The method and apparatus of data assessment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106971338A (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108280762A (en) * | 2018-01-19 | 2018-07-13 | 平安科技（深圳）有限公司 | Customer risk ranking method, server and computer readable storage medium |
| CN108346096A (en) * | 2018-02-23 | 2018-07-31 | 岭尚（上海）科技发展有限公司 | Air control system and air control method |
| CN108510350A (en) * | 2017-11-30 | 2018-09-07 | 腾讯科技（深圳）有限公司 | Merge reference analysis method, device and the terminal of multi-platform collage-credit data |
| CN108564286A (en) * | 2018-04-19 | 2018-09-21 | 天合泽泰（厦门）征信服务有限公司 | A kind of artificial intelligence finance air control credit assessment method and system based on big data reference |
| CN109583687A (en) * | 2018-10-15 | 2019-04-05 | 平安科技（深圳）有限公司 | Automatic control method, device, computer equipment and the storage medium for calculating promise breaking contract |
| CN109785122A (en) * | 2019-01-21 | 2019-05-21 | 深圳萨摩耶互联网金融服务有限公司 | The Risk Forecast Method and system of fund side, electronic equipment |
| CN109816234A (en) * | 2019-01-17 | 2019-05-28 | 北京三快在线科技有限公司 | Service access method, service access device, electronic equipment and storage medium |
| CN110020862A (en) * | 2018-01-10 | 2019-07-16 | 中国移动通信有限公司研究院 | A kind of business risk appraisal procedure, device and computer readable storage medium |
| CN110197074A (en) * | 2018-04-11 | 2019-09-03 | 腾讯科技（深圳）有限公司 | A kind of user authority control method and device |
| CN110555148A (en) * | 2018-05-14 | 2019-12-10 | 腾讯科技（深圳）有限公司 | user behavior evaluation method, computing device and storage medium |
| CN110610412A (en) * | 2019-09-02 | 2019-12-24 | 深圳中兴飞贷金融科技有限公司 | Credit risk assessment method and device, storage medium and electronic equipment |
| WO2020000694A1 (en) * | 2018-06-25 | 2020-01-02 | 平安科技（深圳）有限公司 | Financial product rating method, system, computer device and storage medium |
| CN110689425A (en) * | 2019-09-30 | 2020-01-14 | 上海淇玥信息技术有限公司 | Method and device for pricing quota based on income and electronic equipment |
| CN110807527A (en) * | 2019-09-30 | 2020-02-18 | 北京淇瑀信息科技有限公司 | Line adjusting method and device based on guest group screening and electronic equipment |
| CN111524002A (en) * | 2020-04-27 | 2020-08-11 | 中国银行股份有限公司 | Method and device for determining credit line of joint name card |
| CN111583010A (en) * | 2019-02-18 | 2020-08-25 | 北京奇虎科技有限公司 | Data processing method, device, equipment and storage medium |
| CN111695982A (en) * | 2019-03-13 | 2020-09-22 | 上海麦子资产管理集团有限公司 | Credit investigation data processing method and device of credit system, storage medium and terminal |
| CN112308294A (en) * | 2020-10-10 | 2021-02-02 | 北京贝壳时代网络科技有限公司 | Default probability prediction method and device |
| CN113095928A (en) * | 2021-04-08 | 2021-07-09 | 中国工商银行股份有限公司 | Real estate loan service risk assessment method and device |
| CN113240304A (en) * | 2021-05-20 | 2021-08-10 | 北京百度网讯科技有限公司 | Feature construction method, device, equipment and storage medium |
| CN113298640A (en) * | 2021-05-17 | 2021-08-24 | 浙江惠瀜网络科技有限公司 | Data processing method and device for vehicle credit admission evaluation |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1987919A (en) * | 2006-10-30 | 2007-06-27 | 孙启亮 | Exciting method and system for enterprise credit in electronic business |
| CN102081781A (en) * | 2009-11-26 | 2011-06-01 | 陈晓明 | Finance modeling optimization method based on information self-circulation |
| CN102393839A (en) * | 2011-11-30 | 2012-03-28 | 中国工商银行股份有限公司 | Parallel data processing system and method |
| CN103413223A (en) * | 2013-07-24 | 2013-11-27 | 通联支付网络服务股份有限公司 | Personal-reputation and financing-credit evaluation system for non-face-to-face trading |
| CN103886502A (en) * | 2014-04-14 | 2014-06-25 | 中国人民银行征信中心 | Personal credit status acquisition and integration method |
| CN106127576A (en) * | 2016-07-01 | 2016-11-16 | 武汉泰迪智慧科技有限公司 | A kind of bank risk based on user behavior assessment system |
-
2017
- 2017-04-26 CN CN201710284124.0A patent/CN106971338A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1987919A (en) * | 2006-10-30 | 2007-06-27 | 孙启亮 | Exciting method and system for enterprise credit in electronic business |
| CN102081781A (en) * | 2009-11-26 | 2011-06-01 | 陈晓明 | Finance modeling optimization method based on information self-circulation |
| CN102393839A (en) * | 2011-11-30 | 2012-03-28 | 中国工商银行股份有限公司 | Parallel data processing system and method |
| CN103413223A (en) * | 2013-07-24 | 2013-11-27 | 通联支付网络服务股份有限公司 | Personal-reputation and financing-credit evaluation system for non-face-to-face trading |
| CN103886502A (en) * | 2014-04-14 | 2014-06-25 | 中国人民银行征信中心 | Personal credit status acquisition and integration method |
| CN106127576A (en) * | 2016-07-01 | 2016-11-16 | 武汉泰迪智慧科技有限公司 | A kind of bank risk based on user behavior assessment system |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108510350A (en) * | 2017-11-30 | 2018-09-07 | 腾讯科技（深圳）有限公司 | Merge reference analysis method, device and the terminal of multi-platform collage-credit data |
| CN110020862A (en) * | 2018-01-10 | 2019-07-16 | 中国移动通信有限公司研究院 | A kind of business risk appraisal procedure, device and computer readable storage medium |
| CN108280762A (en) * | 2018-01-19 | 2018-07-13 | 平安科技（深圳）有限公司 | Customer risk ranking method, server and computer readable storage medium |
| CN108346096A (en) * | 2018-02-23 | 2018-07-31 | 岭尚（上海）科技发展有限公司 | Air control system and air control method |
| CN110197074A (en) * | 2018-04-11 | 2019-09-03 | 腾讯科技（深圳）有限公司 | A kind of user authority control method and device |
| CN110197074B (en) * | 2018-04-11 | 2023-02-28 | 腾讯科技（深圳）有限公司 | User authority control method and device |
| CN108564286B (en) * | 2018-04-19 | 2021-01-22 | 天合泽泰（厦门）征信服务有限公司 | Artificial intelligent financial wind-control credit assessment method and system based on big data credit investigation |
| CN108564286A (en) * | 2018-04-19 | 2018-09-21 | 天合泽泰（厦门）征信服务有限公司 | A kind of artificial intelligence finance air control credit assessment method and system based on big data reference |
| CN110555148A (en) * | 2018-05-14 | 2019-12-10 | 腾讯科技（深圳）有限公司 | user behavior evaluation method, computing device and storage medium |
| CN110555148B (en) * | 2018-05-14 | 2022-12-02 | 腾讯科技（深圳）有限公司 | User behavior evaluation method, computing device and storage medium |
| WO2020000694A1 (en) * | 2018-06-25 | 2020-01-02 | 平安科技（深圳）有限公司 | Financial product rating method, system, computer device and storage medium |
| CN109583687A (en) * | 2018-10-15 | 2019-04-05 | 平安科技（深圳）有限公司 | Automatic control method, device, computer equipment and the storage medium for calculating promise breaking contract |
| CN109816234A (en) * | 2019-01-17 | 2019-05-28 | 北京三快在线科技有限公司 | Service access method, service access device, electronic equipment and storage medium |
| CN109785122A (en) * | 2019-01-21 | 2019-05-21 | 深圳萨摩耶互联网金融服务有限公司 | The Risk Forecast Method and system of fund side, electronic equipment |
| CN111583010A (en) * | 2019-02-18 | 2020-08-25 | 北京奇虎科技有限公司 | Data processing method, device, equipment and storage medium |
| CN111695982A (en) * | 2019-03-13 | 2020-09-22 | 上海麦子资产管理集团有限公司 | Credit investigation data processing method and device of credit system, storage medium and terminal |
| CN110610412A (en) * | 2019-09-02 | 2019-12-24 | 深圳中兴飞贷金融科技有限公司 | Credit risk assessment method and device, storage medium and electronic equipment |
| CN110689425A (en) * | 2019-09-30 | 2020-01-14 | 上海淇玥信息技术有限公司 | Method and device for pricing quota based on income and electronic equipment |
| CN110807527A (en) * | 2019-09-30 | 2020-02-18 | 北京淇瑀信息科技有限公司 | Line adjusting method and device based on guest group screening and electronic equipment |
| CN110807527B (en) * | 2019-09-30 | 2023-11-14 | 北京淇瑀信息科技有限公司 | Credit adjustment method and device based on guest group screening and electronic equipment |
| CN111524002A (en) * | 2020-04-27 | 2020-08-11 | 中国银行股份有限公司 | Method and device for determining credit line of joint name card |
| CN112308294A (en) * | 2020-10-10 | 2021-02-02 | 北京贝壳时代网络科技有限公司 | Default probability prediction method and device |
| CN113095928A (en) * | 2021-04-08 | 2021-07-09 | 中国工商银行股份有限公司 | Real estate loan service risk assessment method and device |
| CN113298640A (en) * | 2021-05-17 | 2021-08-24 | 浙江惠瀜网络科技有限公司 | Data processing method and device for vehicle credit admission evaluation |
| CN113240304A (en) * | 2021-05-20 | 2021-08-10 | 北京百度网讯科技有限公司 | Feature construction method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106971338A (en) | The method and apparatus of data assessment | |
| US20210056569A1 (en) | Detecting and reducing bias (including discrimination) in an automated decision making process | |
| US20150228014A1 (en) | Automated customer characterization | |
| CN108389120B (en) | Method, system and device for automatically rating internet credit assets | |
| US20040111363A1 (en) | Method and system for enhancing credit line management, price management and other discretionary levels setting for financial accounts | |
| CN104965844A (en) | Information processing method and apparatus | |
| WO2003107135A2 (en) | A system and method for portfolio valuation using an age adjusted delinquency rate | |
| US20040083163A1 (en) | System and method for purchasing increased efficiency items | |
| WO2014004675A1 (en) | Novel systems and processes for enhanced microlending | |
| CN110503564B (en) | Security case processing method, system, equipment and storage medium based on big data | |
| US11687936B2 (en) | System and method for managing chargeback risk | |
| CN112801529B (en) | Financial data analysis method and device, electronic equipment and medium | |
| US20130226784A1 (en) | System and method for credit balance transfer offer optimization | |
| US20140344019A1 (en) | Customer centric system for predicting the demand for purchase loan products | |
| US20140344018A1 (en) | Customer centric system for predicting the demand for loan refinancing products | |
| CN114782169A (en) | Customer attrition rate early warning method and device | |
| CN107924537A (en) | Assess credit risk | |
| CN108492169A (en) | Risk Modeling method and system based on credit card approval scene are realized | |
| KR20200068069A (en) | Apparatus for predicting loan defaults based on machine learning and method thereof | |
| CN109345376A (en) | A kind of e-bank is counter to cheat method and system | |
| CN117151871A (en) | Multi-dimensional data analysis-based performance risk assessment method and system | |
| CN108256667A (en) | Asset data processing method, device, storage medium and computer equipment | |
| JP7298286B2 (en) | Model providing program, model providing method and model providing apparatus | |
| Ryan et al. | FinTech isn’t so different from traditional banking: trading off aggregation of soft information for transaction processing efficiency | |
| Courchane et al. | Differential access to and pricing of home mortgages: 2004 through 2009 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20181211 Address after: Room 1615, Floor 16, Vivian Building, 29 Suzhou Street, Haidian District, Beijing Applicant after: Beijing Mutual Gold New Finance Technology Co., Ltd. Address before: 100080 17th Floor, Yuanwei Building, 29 Suzhou Street, Haidian District, Beijing Applicant before: BEIJING QUNAR SOFTWARE TECHNOLOGY CO., LTD. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170721 |