CN109146132A - Field miss rate method for early warning, server, storage medium and computer program - Google Patents
Field miss rate method for early warning, server, storage medium and computer program Download PDFInfo
- Publication number
- CN109146132A CN109146132A CN201810760345.5A CN201810760345A CN109146132A CN 109146132 A CN109146132 A CN 109146132A CN 201810760345 A CN201810760345 A CN 201810760345A CN 109146132 A CN109146132 A CN 109146132A
- Authority
- CN
- China
- Prior art keywords
- field
- miss rate
- client
- credit scoring
- scoring card
- 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.)
- Withdrawn
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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the invention discloses a kind of field miss rate method for early warning, server, storage medium and computer programs, and wherein method includes: to obtain the essential information of M client, and generate M credit scoring card according to the essential information of M client；Wherein, each credit scoring card in M credit scoring card includes N number of field, and M, N are positive integer, and credit scoring card predicts the approval results of client for server by prediction model；Detect the practical miss rate of the first field in M credit scoring card；If the practical miss rate of the first field is greater than preset first miss rate threshold value, the missing information of the first field is sent to default mailing address；Wherein, the practical miss rate of the first field is accounting of the practical missing quantity S of the first field in the total quantity M of the first field.Implement the embodiment of the present invention, prediction model can be improved for the accuracy of the approval results of client.
Description
Technical field
The present invention relates to financial technology field more particularly to a kind of field miss rate method for early warning, server, storage medium
And computer program.
Background technique
The fast development of Internet technology brings earth-shaking variation to financial industry.By taking lending and borrowing business as an example, pass
The bank credit examination & approval mode of system be credit approving person by interview, telephone verification, check applicant's material etc. come to client
Carry out the evaluation based on subjective credit risk grade, and according to client overall impression and related working experience come to visitor
The corresponding accrediting amount in one, family.This mode not only lacks scientific basis, in the case where customer quantity is huge, is easy to bring
The problems such as poor in timeliness, human cost are high, evaluation precision is not high.Then, Internet bank credit has been emerged.Specifically,
Existing Internet bank credit may include following link: firstly, the essential information of user is obtained, for example, the user
Essential information may include user identifier, credit line, education degree, marital status, age etc.；Then, according to above-mentioned use
The essential information at family establishes credit scoring card, inherently from the point of view of, credit scoring card be quantization borrower promise breaking possibility；
Later, borrower on time and is pressed about according to above-mentioned credit scoring card by prediction model (for example, Logistic regression model)
Surely a possibility that refunding makes the prediction seen very clearly, for example, determine that Xiao Ming is good person according to credit scoring card, it is small it is black be bad person
Deng, then, this also means that financial institution can make loans to Xiao Ming, and refusal black is made loans to small.However, in practical applications may be used
Cause prediction model to put bad person into since missing occur in certain fields in credit scoring card with discovery, accidentally refuse good person, shadow
Percent of pass has been rung, has been damaged so as to cause the income of financial institution.It is possible thereby to know how to improve the accurate of prediction model
The technical issues of rate is urgent need to resolve.
Summary of the invention
The embodiment of the present invention provides a kind of field miss rate method for early warning, server, storage medium and computer program, can
To improve prediction model for the accuracy rate of the approval results of client.
In a first aspect, the embodiment of the invention provides a kind of field miss rate method for early warning, this method comprises:
The essential information of M client is obtained, and M credit scoring card is generated according to the essential information of the M client；Its
In, each credit scoring card in the M credit scoring card includes N number of field, and M, N are positive integer, the credit scoring card
The approval results of the client are predicted by prediction model for server；
Detect the practical miss rate of the first field in the M credit scoring card；
If the practical miss rate of first field is greater than preset first miss rate threshold value, by first field
Missing information is sent to default mailing address；Wherein, the practical miss rate of first field is the reality of first field
Lack accounting of the quantity S in the total quantity M of first field.
By implementing the embodiment of the present invention, server can detecte the practical miss rate of the field in credit scoring card,
In the case that practical miss rate is greater than preset threshold, early warning is sent, so that server improves the standard of the approval results for client
True property.
Optionally, the essential information for obtaining M client includes:
The essential information of the M client is obtained by big data platform, the essential information of the client includes characterization institute
State the credit information of client.
Optionally, the essential information for obtaining M client, and M letter is generated according to the essential information of the M client
After scorecard, in the detection M credit scoring card before the practical miss rate of the first field, further includes:
According to preset rules, N number of corresponding miss rate threshold value of field described in the credit scoring card is set.
Optionally, the essential information for obtaining M client, and M letter is generated according to the essential information of the M client
After scorecard, in the detection M credit scoring card before the practical miss rate of the first field, further includes:
Judge first field whether with other fields in N number of field in addition to first field to be associated with
Field；
If so, reducing the preset first miss rate threshold value of the first field.
Optionally, the essential information for obtaining M client, and M letter is generated according to the essential information of the M client
After scorecard, in the detection M credit scoring card before the practical miss rate of the first field, further includes:
Judge first field whether with other fields in N number of field in addition to first field to couple
Field；
If so, reducing the preset first miss rate threshold value of the first field.
Optionally, the essential information for obtaining M client, and M letter is generated according to the essential information of the M client
After scorecard, in the detection M credit scoring card before the practical miss rate of the first field, further includes:
Determine whether first field is critical field according to the parameter of the prediction model；
If so, reducing the preset first miss rate threshold value of the first field；
If it is not, then increasing the preset first miss rate threshold value of first field.
By implementing the embodiment of the present invention, each of credit scoring card word can be arranged in server according to preset rules
The miss rate threshold value of section, and the miss rate threshold value set is adjusted according to the characteristic of field, in detecting credit scoring card
Field practical miss rate when, it is compared with preset miss rate threshold value, practical miss rate be greater than it is preset lack
In the case where mistake rate threshold value, early warning is sent, so that server improves the accuracy of the approval results for client.
Second aspect, the embodiment of the invention provides a kind of server, which includes:
Acquiring unit, for obtaining the essential information of M client；
Generation unit, for generating M credit scoring card according to the essential information of the M client；Wherein, the M
Each credit scoring card in credit scoring card includes N number of field, and M, N are positive integer, and the credit scoring card is used for server
The approval results of the client are predicted by prediction model；
Detection unit, for detecting the practical miss rate of the first field in the M credit scoring card；
Processing unit, for the practical miss rate in first field be greater than preset first miss rate threshold value the case where
Under, then the missing information of first field is sent to default mailing address；Wherein, the practical miss rate of first field
For accounting of the practical missing quantity S in the total quantity M of first field of first field.
Optionally, the acquiring unit is specifically used for obtaining the essential information of the M client, institute by big data platform
The essential information for stating client includes the credit information for characterizing the client.
Optionally, the server further includes the first judging unit, the first adjustment unit；
Wherein, first judging unit is used to generate M according to the essential information of the M client in the generation unit
After a credit scoring card, the detection unit is detected in the M credit scoring card before the practical miss rate of the first field,
Judge first field whether with other fields in N number of field in addition to first field for associate field；
The first adjustment unit, for judging first field and N number of field in first judging unit
In in the case that other fields in addition to first field are associate field, reduce first field preset described the
One miss rate threshold value.
Optionally, the server further includes second judgment unit, second adjustment unit；
Wherein, the second judgment unit is used to generate M according to the essential information of the M client in the generation unit
After a credit scoring card, the detection unit is detected in the M credit scoring card before the practical miss rate of the first field,
Judge first field whether with other fields in N number of field in addition to first field to couple field；Institute
Second adjustment unit is stated, for judge to remove described the in first field and N number of field in the second judgment unit
In the case that other fields except one field are coupling field, reduce the preset first miss rate threshold of the first field
Value.
Optionally, the server further includes determination unit, third adjustment unit and the 4th adjustment unit；
Wherein, the determination unit is used to generate M letter according to the essential information of the M client in the generation unit
After scorecard, the detection unit is detected in the M credit scoring card before the practical miss rate of the first field, according to
The parameter of the prediction model determines whether first field is critical field；
The third adjustment unit, for determining the case where first field is critical field in the determination unit
Under, reduce the preset first miss rate threshold value of the first field；
4th adjustment unit, for determining the case where first field is not critical field in the determination unit
Under, increase the preset first miss rate threshold value of the first field.
The third aspect, the embodiment of the invention provides another servers, including processor, input equipment, output equipment
And memory, the processor, input equipment, output equipment and memory are connected with each other, wherein the memory is for storing
Server is supported to execute the computer program of the above method, the computer program includes program instruction, and the processor is matched
It sets for calling described program to instruct, the method for executing above-mentioned first aspect.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage medium, the computer storage medium
It is stored with computer program, the computer program includes program instruction, and described program instruction makes institute when being executed by a processor
State the method that processor executes above-mentioned first aspect.
5th aspect, the embodiment of the invention provides a kind of computer program, the computer program includes above-mentioned service
Program instruction used in device, described program instruction make the processor execute above-mentioned first when being executed by the processor of server
Aspect is program designed by server.
The embodiment of the present invention is greater than pre- by the practical miss rate of the field in detection credit scoring card in practical miss rate
If in the case where threshold value, sending early warning, so that server improves the accuracy of the approval results for client.
Detailed description of the invention
Technical solution in order to illustrate the embodiments of the present invention more clearly, below will be to needed in embodiment description
Attached drawing is briefly described.
Figure 1A is a kind of schematic flow diagram of field miss rate method for early warning provided in an embodiment of the present invention；
Figure 1B is the schematic diagram of data before the loan in a kind of air control data access platform provided in an embodiment of the present invention；
Fig. 2 be another embodiment of the present invention provides a kind of field miss rate method for early warning schematic flow diagram；
Fig. 3 be another embodiment of the present invention provides a kind of field miss rate method for early warning schematic flow diagram；
Fig. 4 be another embodiment of the present invention provides a kind of field miss rate method for early warning schematic flow diagram；
Fig. 5 A is a kind of schematic block diagram of server provided in an embodiment of the present invention；
Fig. 5 B be another embodiment of the present invention provides a kind of server schematic block diagram；
Fig. 5 C be another embodiment of the present invention provides a kind of server schematic block diagram；
Fig. 5 D be another embodiment of the present invention provides a kind of server schematic block diagram；
Fig. 6 be another embodiment of the present invention provides a kind of server schematic block diagram.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention is described.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this description of the invention merely for the sake of description specific embodiment
And be not intended to limit the present invention.As description of the invention and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
Below with reference to the flow diagram of field miss rate method for early warning provided in an embodiment of the present invention shown in figure 1A, tool
Body illustrates that the practical miss rate of a certain field of the embodiment of the present invention in credit scoring card is greater than preset miss rate threshold value
In the case of be how to realize early warning, can include but is not limited to following steps S101-S103:
Step S101, the essential information of M user is obtained, and M credit scoring is generated according to the essential information of M client
Card.
In the specific implementation, the essential information of client referred to herein may include Q, it is raw according to the essential information of client
At scorecard in include N number of field, wherein Q be greater than N.N number of field referred to herein is the credit information for characterizing client.
For example, the essential information of client includes identity, gender, age, credit line, hobby, previous working experience, marriage
Situation, whether there is or not fixed assets, every monthly average fixed income, monthly the average consumption amount of money, of that month repayment state, of that month bill gold
Maximum overdue number of volume, last month billing amount, history etc., server selected from the essential information of above-mentioned client identity,
Gender, the age, credit line, whether there is or not fixed assets, every monthly average fixed income, monthly the average consumption amount of money, of that month repayment shape
The maximum overdue number of state, history predicts that client brings the probability size of default risk as the field in credit scoring card with this, into
And the approval results of the client are determined according to above-mentioned probability.In the specific implementation, approval results referred to herein may include
Examination & approval pass through, examine failure.
Optionally, the essential information for obtaining M client includes:
The essential information of the M client is obtained by big data platform, the essential information of the client includes characterization institute
State the credit information of client.
In the specific implementation, server can obtain the essential information of client by big data platform.
In one possible implementation, included in credit scoring card since financial institution type of service is different
Field is also different.In the specific implementation, the form of expression of credit scoring card can be as shown in table 1:
Table 1
By table 1 it is recognised that including 7 credit scoring cards in table 1, each credit scoring card may include 8 fields, point
It Wei not identify, credit line, gender, education degree, marital status, age, of that month repayment state, the maximum overdue number of history.This
Outside, -2 in above-mentioned this field of credit scoring card " of that month repayment state " indicate not consume；- 1 indicates full refund；0 table
Show amortization；1-9 indicates to repay for overdue N number of month.In the specific implementation, field included in above-mentioned credit scoring card is only made
Restriction should not be constituted in practical applications for a kind of example, for example, the field in credit scoring card can also include of that month account
Single amount of money, last month billing amount, the of that month payment beforehand amount of money, last month payment beforehand amount of money etc..
In the specific implementation, above-mentioned credit scoring card may include application credit scorecard.Apply for credit scorecard main sides
Before overweighting loan, refer in the Customer Acquisition phase, establish credit scoring, prediction client brings the probability size of default risk, after
And can determine that the client that needs are borrowed or lent money is good person or bad person according to probability size, it can also determine approval results.If
The client for needing to borrow or lend money is good person, namely examination & approval pass through, it is meant that financial institution can make loans to the client；If desired it borrows
The client of loan is bad person, namely examination & approval failure, it is meant that financial institution cannot make loans to the client.
In the specific implementation, the M credit scoring card is stored in air control data access platform.Air control referred to herein
Data access platform may include a large-scale database, can be used as the integrated application platform of Various types of data, for financial machine
Structure uses.For example, the air control data access platform can provide loan before, borrow in, borrow after data.Come below in conjunction with Figure 1B detailed
Data before the loan that elaboration air control data access platform can provide.As shown in Figure 1B, before the loan data may include 101 sudden strains of a muscle it is anti-,
102 dodge cores, 103 sudden strains of a muscle are adjusted, 104 sudden strains of a muscle are estimated, 105 dodge pictures, 106 sudden strains of a muscle are commented.Specifically, 101 dodge prevent may include blacklist inquiry, law court
Executed person inquiry, law court are broken one's promise, and people inquires, the doubtful arbitrage of credit card detects, instead cheats model and overdue record queries.102
Dodging core may include personal name, identity card, the veritification inquiry of cell-phone number essential information.103, which dodge tune, may include personal educational background, holds
Industry qualification authentication inquiry and personal industrial and commercial shareholder's information.It may include by personal mobile phone number, bank card bill that 104 sudden strains of a muscle, which are estimated,
Details, house property information of vehicles, consumer information etc. carry out valuation to personal asset situation.105 sudden strain of a muscle pictures may include by a
The analysis of the contents such as people's cell-phone number, bank card consumption preference and internet Behavior preference precisely draws a portrait to individual.106 sudden strains of a muscle are commented
It may include that comprehensive score is carried out to individual according to acquired various information.
Step S102, the practical miss rate of the first field in M credit scoring card is detected.
In the specific implementation, credit scoring card is as shown in Table 1 above:
Table 1
In the specific implementation, the practical miss rate of the first field is the practical missing quantity S of the first field in the first field
Accounting in total quantity M.It is illustrated by taking " the maximum overdue number of history " this field as an example, by table 1 it is recognised that 7 credits
The practical missing quantity of " the maximum overdue number of history " this field is 1 in scorecard, " the maximum overdue number of history " this field
Total quantity is 7, so as to know that the miss rate of " the maximum overdue number of history " this field is 1/7 namely 14.3%.
If step S103, the miss rate of the first field is greater than preset first miss rate threshold value, by first field
Missing information be sent to default mailing address.
In the specific implementation, the miss rate threshold value of each field setting can phase in 7 credit scoring cards in above-mentioned table 1
Together, it can also be different.For example, the miss rate threshold value of each field setting is identical in credit scoring card, which may include
15%.In another example the threshold value of the miss rate of each field setting is different in credit scoring card.In a kind of possible implementation
In, the threshold value of the miss rate of each field setting is not both by the field in credit scoring card to prediction in above-mentioned credit scoring card
What the influence degree of model (for example, credit scoring card mold type) determined.For example, the threshold value of " credit line " this field of setting
Threshold value for 10%, " the maximum overdue number of history " this field is 8%, etc..As a kind of optional implementation, server
The corresponding miss rate threshold value of each field included in credit scoring card can be set according to preset rules.
In the specific implementation, 8 fields are corresponding in the above-mentioned credit scoring card that server is arranged according to preset rules
Miss rate threshold value can be as shown in table 2:
Table 2
By table 2 it is recognised that the miss rate threshold of field in the preset credit scoring card of server " the maximum overdue number of history "
Value is 10%.By table 1 it is recognised that the practical miss rate of " the maximum overdue number of history " this field is 14.3%, at this point, service
Device determines that the practical miss rate of " the maximum overdue number of history " this field is greater than threshold value, will " the maximum overdue number of history " this field
Missing information be sent to default mailing address.
In the specific implementation, the missing information of first field may include the total quantity M of first field, described
The title of one field and the corresponding practical miss rate of first field.
For example, determining that the practical miss rate of " the maximum overdue number of history " this field is greater than preset miss rate in server
After threshold value, by missing information, " total quantity of the maximum overdue number of history is 100 to server, and the reality of the maximum overdue number of history lacks
Mistake rate is sent to default mailing address for 14.8% ".
In the specific implementation, the missing information of first field can also include prompt alarm information.
For example, determining that the practical miss rate of " the maximum overdue number of history " this field is greater than preset miss rate in server
After threshold value, by missing information, " total quantity of the maximum overdue number of history is 100 to server, the miss rate of the maximum overdue number of history
It is 14.8%, the miss rate 14.8% of the maximum overdue number of history is sent to more than preset miss rate threshold value 8% " to be preset communicatedly
Location.
By implementing the embodiment of the present invention, server can detecte the practical miss rate of the field in credit scoring card,
In the case that practical miss rate is greater than preset threshold, early warning is sent, so that server improves the standard of the approval results for client
True property.
Below with reference to it is shown in Fig. 2 another embodiment of the present invention provides field miss rate method for early warning flow diagram,
The practical miss rate for illustrating a certain field of the embodiment of the present invention in credit scoring card is greater than preset miss rate threshold value
In the case where be how to realize early warning, can include but is not limited to following steps S201-S205:
Step S201, the essential information of M user is obtained, and M credit scoring is generated according to the essential information of M client
Card, wherein each credit scoring card in M credit scoring card includes N number of field, and M, N are positive integer, and credit scoring card is used for
Server predicts the approval results of client by prediction model.
Specifically, step S201 can not add herein with reference to the associated description of step S101 in above-mentioned Figure 1A embodiment
It repeats.
Step S202, judge the first field whether with other fields in N number of field in addition to the first field for associated characters
Section, if so, thening follow the steps S203.
In the specific implementation, the form of expression of credit scoring card is as shown in table 3:
Table 3
| Mark | Credit line | Gender | Education degree | Marital status | Age | Job site | Every average monthly income |
| Small A | 2000 | Male | Training | It is married | 20 | Changsha | 3500 |
| Small B | 5000 | Male | Undergraduate course | It is unmarried | 35 | Shenzhen | 10000 |
| Small C | 2000 | Male | Master | It is unmarried | 27 | Zhuzhou | 4000 |
| Small D | 2000 | Female | Undergraduate course | 28 | Changde | 3900 | |
| Small E | 1800 | Female | Undergraduate course | It is married | 25 | Dongguan | 4800 |
| Small F | Female | Undergraduate course | It is married | 28 | Huizhou | 4600 | |
| Small H | 1000 | Female | Special secondary school | It is married | 25 | Changsha | 2800 |
| Small I | 10000 | Male | Doctor | It is unmarried | 30 | Chengdu | 9000 |
As shown in table 3, table 3 includes 8 credit scoring cards, and each credit scoring card may include 8 fields, this 8 words
Section is respectively mark, credit line, gender, education degree, marital status, age, job site, every average monthly income.
In the specific implementation, each field in above-mentioned 8 credit scoring cards that server is arranged according to preset rules is respectively
Corresponding miss rate threshold value is as shown in table 4:
Table 4
In the specific implementation, for example, server judges that the field in table 3 " is monthly put down for field " every average monthly income "
Income " is associate field with field " job site ", is also associate field with field " credit line ", that is, it is known that
, in above-mentioned 8 fields, the quantity with field " every average monthly income " associated field is 2.In another example with field
For " job site ", server judge field " job site " in table 3 and field " every average monthly income " for associate field,
That is, it is appreciated that the quantity with field " job site " associated field is 1 in above-mentioned 8 fields.
Step S203, reduce the preset first miss rate threshold value of the first field.
In the specific implementation, for example, server judges that the field in table 3 " is monthly put down for field " every average monthly income "
Income " is associate field with field " job site ", is also server adjustment after associate field with field " credit line "
The preset miss rate threshold value of field " every average monthly income ".For example, server reduction field " every average monthly income " is preset
Miss rate threshold value.In another example server judges field " job site " and field in table 3 for field " job site "
" every average monthly income " is the preset miss rate threshold value of server adjustment field " job site " after associate field.For example,
Server reduces field " job site " preset miss rate threshold value.
In one possible implementation, server determines institute according to the quantity of the associate field with first field
The adjustment numerical value of the first miss rate threshold value is stated, the adjustment numerical value includes the quantity of the associate field.
In the specific implementation, it is Q that the adjustment numerical value, which may include: with the quantity of the associated field of the first field, then
The preset first miss rate threshold value of first field reduces Q%.
In the specific implementation, as previously mentioned, being associated in 8 fields of credit scoring card with field " every average monthly income "
The quantity of field be 2, at this point, determining that the adjustment numerical value of field " every average monthly income " corresponding miss rate threshold value is 2%.
That is, the miss rate threshold value of field " every average monthly income " can be reduced to 8% by 10%, adjustment numerical value is 2%.Specifically, may be used
Referring to table 5:
Table 5
In the specific implementation, as previously mentioned, in 8 fields of credit scoring card, with field " job site " associated word
The quantity of section is 1, at this point, determining that the adjustment numerical value of field " every average monthly income " corresponding miss rate threshold value is 1%.That is,
The miss rate threshold value of field " job site " can be reduced to 14% by 15%, and adjustment numerical value is 1%.Specifically, it may refer to
Table 6:
Table 6
Step S204, the practical miss rate of the first field in M credit scoring card is detected.
If step S205, the practical miss rate of the first field is greater than preset first miss rate threshold value, by the first field
Missing information be sent to default mailing address so that server improve for client approval results accuracy.
Specifically, step S204, S205 can be with reference to the associated description of S102, S103 in above-mentioned Figure 1A embodiment, herein
Do not add to repeat.
By implementing the embodiment of the present invention, server is determining other fields in the first field and credit scoring card for pass
When joining field, reduce the preset miss rate threshold value of the first field.When server detects that the practical miss rate of the first field is greater than
When the preset miss rate threshold value of the first field adjusted, early warning is sent, so that server improves the approval results for being directed to client
Accuracy.
Below with reference to it is shown in Fig. 3 another embodiment of the present invention provides field miss rate method for early warning flow diagram,
The practical miss rate for illustrating a certain field of the embodiment of the present invention in credit scoring card is greater than preset miss rate threshold value
In the case where be how to realize early warning, can include but is not limited to following steps S301-S305:
Step S301, the essential information of M user is obtained, and M credit scoring is generated according to the essential information of M client
Card, wherein each credit scoring card in M credit scoring card includes N number of field, and M, N are positive integer, and credit scoring card is used for
Server predicts the approval results of client by prediction model.
Specifically, step S301 can not add herein with reference to the associated description of step S101 in above-mentioned Figure 1A embodiment
It repeats.
S302, judge the first field whether with other fields in N number of field in addition to the first field to couple field, if
It is to then follow the steps S303.
In the specific implementation, the form of expression of credit scoring card is as shown in table 7:
Table 7
As shown in table 7, table 7 includes 3 credit scoring cards, and each credit scoring card may include 8 fields, respectively mark
Know, of that month repayment state, last month repayment state, upper two months repayment states, upper three months repayment states, repay within upper four months
The maximum overdue number (moon) of state, upper five months repayment states, history.
In the specific implementation, each field in above-mentioned 8 fields that server is arranged according to preset rules is corresponding
Miss rate threshold value is as shown in table 8:
Table 8
In the specific implementation, server judges the field " upper five months repayment states " in table 7, " history maximum is overdue with field
Number (moon) " is coupling field (for example, this is coupled as content coupling), at this point, server adjusts the word being arranged according to preset rules
The miss rate threshold value of section " the maximum overdue number (moon) of history ".For example, server reduces field " the maximum overdue number (moon) of history " in advance
If miss rate threshold value.
In one possible implementation, server determines institute according to the quantity of the coupling field with first field
The adjustment numerical value of the first miss rate threshold value is stated, the adjustment numerical value includes the quantity of the coupling field.
In the specific implementation, the quantity that the adjustment numerical value may include: the field coupled with first field is Q, then
The preset first miss rate threshold value of first field reduces Q%.
For example, the coupling as previously mentioned, in 8 fields of credit scoring card, with field " the maximum overdue number (moon) of history "
The quantity for closing field is 1, at this point, determining the adjustment numerical value of the corresponding miss rate threshold value of field " the maximum overdue number (moon) of history "
It is 1%.That is, the miss rate threshold value of field " the maximum overdue number (moon) of history " is reduced to 9% by 10%, adjustment numerical value is 1%.Tool
Body, it may refer to table 9:
Table 9
Step S304, the practical miss rate of the first field in M credit scoring card is detected.
If step S305, the practical miss rate of the first field is greater than preset first miss rate threshold value, by the first field
Missing information be sent to default mailing address.
Specifically, step S304, S305 can be with reference to the associated description of S102, S103 in above-mentioned Figure 1A embodiment, herein
Do not add to repeat.
By implementing the embodiment of the present invention, server is determining that other fields in the first field and credit scoring card are coupling
When closing field, reduce the preset miss rate threshold value of the first field.When server detects that the practical miss rate of the first field is greater than
When the preset miss rate threshold value of the first field adjusted, early warning is sent, so that server improves the approval results for being directed to client
Accuracy.
Below with reference to it is shown in Fig. 4 another embodiment of the present invention provides field miss rate method for early warning flow diagram,
The practical miss rate for illustrating a certain field of the embodiment of the present invention in credit scoring card is greater than preset miss rate threshold value
In the case where be how to realize early warning, can include but is not limited to following steps S401-S406:
Step S401, the essential information of M user is obtained, and M credit scoring is generated according to the essential information of M client
Card, wherein each credit scoring card in M credit scoring card includes N number of field, and M, N are positive integer, and credit scoring card is used for
Server predicts the approval results of client by prediction model.
Specifically, step S401 can not add herein with reference to the associated description of step S101 in above-mentioned Figure 1A embodiment
It repeats.
Step S402, determine whether the first field is critical field according to the parameter of prediction model, if so, thening follow the steps
S403；If it is not, thening follow the steps S404.
In the specific implementation, the form of expression of credit scoring card is as shown in table 10:
Table 10
In the specific implementation, each field in above-mentioned 8 fields that server is arranged according to preset rules is corresponding
Miss rate threshold value is as shown in table 11:
Table 11
In one possible implementation, prediction model may include credit scoring card mold type, and the principle of the model is
Logistic regression model will be used to carry out after model variable WOE (Weight of Evidence) coding mode discretization
A kind of generalized linear model of two classified variables.In the specific implementation, to the one of promise breaking ratio when WOE characterization independent variable takes some value
Kind influences.
In the specific implementation, server determines that field " the maximum overdue number (moon) of history " is key according to the parameter of prediction model
Field, at the same time, server determine that field " gender " is non-key field according to the parameter of prediction model.
It in one possible implementation, can be in credit scoring card after determining the field is critical field
The attributive character of the field is set, for example, field " the maximum overdue number (moon) of history " is critical field, it is set in credit scoring
Attributive character in card is non-empty.It is possible to understand, when determine a certain field in credit scoring card be non-keyword
After section, for example, field " gender " is non-key field, its attributive character in credit scoring card is set for sky.Then, may be used
With the attributive character that is set according to each field in credit scoring card come the better miss rate threshold value for determining field.
Step S403, reduce the preset first miss rate threshold value of the first field.
In the specific implementation, server judges field, and " history is most so that the first field is " the maximum overdue number (moon) of history " as an example
Big overdue number (moon) " is server adjustment field " the maximum overdue number (moon) of history " preset miss rate threshold after critical field
Value.For example, server reduces the miss rate threshold value of field " the maximum overdue number (moon) of history ".In the specific implementation, server is by word
The miss rate threshold value of section " the maximum overdue number (moon) of history " is reduced to 8% by 10%.Specifically, it may refer to table 12:
Table 12
Step S404, increase the preset first miss rate threshold value of the first field.
In the specific implementation, by the first field be " gender " for, server judge field " gender " for non-key field it
Afterwards, server adjusts field " gender " preset miss rate threshold value.For example, server increases the miss rate threshold of field " gender "
Value.In the specific implementation, the miss rate threshold value of field " gender " is increased to 17% by 15% by server.Specifically, it may refer to
Table 13:
Table 13
Step S405, the practical miss rate of the first field in M credit scoring card is detected.
If step S406, the practical miss rate of the first field is greater than preset first miss rate threshold value, by the first field
Missing information be sent to default mailing address.
Specifically, step S405, S406 can be with reference to the associated description of S102, S103 in above-mentioned Figure 1A embodiment, herein
Do not add to repeat.
By implementing the embodiment of the present invention, server may determine that whether the first field is critical field, and then basis is sentenced
Disconnected result is adjusted the preset miss rate threshold value of the first field.When server detects that the practical miss rate of the first field is big
When the first field adjusted preset miss rate threshold value, early warning is sent, so that server improves the examination & approval knot for being directed to client
The accuracy of fruit.
For the ease of the above scheme of the better implementation embodiment of the present invention, the embodiment of the present invention is also described and above-mentioned figure
Embodiment of the method described in 1A, Fig. 2, Fig. 3 and Fig. 4 belongs to a kind of structural schematic diagram of server under same inventive concept.
It is described in detail with reference to the accompanying drawing:
As shown in Figure 5A, which may include:
Acquiring unit 501, for obtaining the essential information of M client；
Generation unit 502, for generating M credit scoring card according to the essential information of the M client；Wherein, the M
Each credit scoring card in a credit scoring card includes N number of field, and M, N are positive integer, and the credit scoring card is for servicing
Device predicts the approval results of the client by prediction model；
Detection unit 503, for detecting the practical miss rate of the first field in the M credit scoring card；
Processing unit 504 is greater than preset first miss rate threshold value for the practical miss rate in first field
In the case of, then the missing information of first field is sent to default mailing address；Wherein, the reality of first field lacks
Mistake rate is accounting of the practical missing quantity S of first field in the total quantity M of first field.
Optionally, the acquiring unit 501 is specifically used for obtaining the basic letter of the M client by big data platform
Breath, the essential information of the client includes the credit information for characterizing the client.
Further, as shown in Figure 5 B, the server 500 further includes the first judging unit 505, the first adjustment unit
506；
Wherein, first judging unit 505 is used in the generation unit 502 according to the basic letter of the M client
After breath generates M credit scoring card, the detection unit 503 detects the reality of the first field in the M credit scoring card
Before miss rate, judge first field whether with other fields in N number of field in addition to first field be
Associate field；
The first adjustment unit 506, for judging first field and the N in first judging unit 505
In the case that other fields in a field in addition to first field are associate field, it is preset to reduce first field
The first miss rate threshold value.
Further, as shown in Figure 5 C, the server 500 can also include: second judgment unit 507, second adjustment
Unit 508；
Wherein, the second judgment unit 507, for the basic letter in the generation unit 502 according to the M client
After breath generates M credit scoring card, the detection unit 503 detects the reality of the first field in the M credit scoring card
Before miss rate, judge first field whether with other fields in N number of field in addition to first field be
Couple field；
The second adjustment unit 508, for second judgement single 507 judge first field with it is described N number of
In the case that other fields in field in addition to first field are coupling field, reduce the preset institute of the first field
State the first miss rate threshold value.
Further, as shown in Figure 5 D, the server further includes determination unit 509, third adjustment unit 510 and the 4th
Adjustment unit 511；
Wherein, the determination unit 509 is used for raw according to the essential information of the M client in the generation unit 502
After M credit scoring card, the detection unit 503 detects the practical missing of the first field in the M credit scoring card
Before rate, determine whether first field is critical field according to the parameter of the prediction model；
The third adjustment unit 510, for determining that first field is critical field in the determination unit 509
In the case of, reduce the preset first miss rate threshold value of the first field；
4th adjustment unit 511, for determining that first field is not critical field in the determination unit 509
In the case where, increase the preset first miss rate threshold value of the first field.
It is understood that the function of each functional unit of the server 500 of the embodiment of the present invention can according to above-mentioned Figure 1A,
Method specific implementation in embodiment of the method shown in Fig. 2, Fig. 3 and Fig. 4, specific implementation process are referred to above method reality
The associated description of example is applied, details are not described herein again.
For the ease of better implementing the above scheme of the embodiment of the present invention, the present invention also correspondence provides another service
The structural schematic diagram of device is described in detail with reference to the accompanying drawing:
The structural schematic diagram of another server provided in an embodiment of the present invention as shown in Figure 6, the server 600 can be with
Including at least one processor 601, communication bus 602, memory 603 and at least one communication interface 604.
Processor 601 can be a general central processor (Central Processing Unit, CPU), micro process
Device, application-specific integrated circuit (Application-Specific Integrated Circuit, ASIC) or one or more
A integrated circuit executed for controlling the present invention program program.
Communication bus 602 may include an access, and information is transmitted between said modules.The communication interface 604, using appoint
The device of what transceiver one kind is used for and other equipment or communication, such as Ethernet, wireless access network (Radio
Access Technology, RAN), WLAN (Wireless Local Area Networks, WLAN) etc..
Memory 603 can be read-only memory (Read-Only Memory, ROM) or can store static information and instruction
Other kinds of static storage device, random access memory (Random Access Memory, RAM) or letter can be stored
The other kinds of dynamic memory of breath and instruction, is also possible to Electrically Erasable Programmable Read-Only Memory (Electrically
Erasable Programmable Read-Only Memory, EEPROM), CD-ROM (Compact Disc Read-
Only Memory, CD-ROM) or other optical disc storages, optical disc storage (including compression optical disc, laser disc, optical disc, digital universal
Optical disc, Blu-ray Disc etc.), magnetic disk storage medium or other magnetic storage apparatus or can be used in carrying or store to have referring to
Enable or data structure form desired program code and can by any other medium of computer access, but not limited to this.
Memory, which can be, to be individually present, and is connected by bus with processor.Memory can also be integrated with processor.
Wherein, the memory 603 is used to store the program code for executing the present invention program, and is controlled by processor 601
System executes.The processor 601 is for executing the program code stored in the memory 603, execution following steps:
The essential information of M client is obtained, and M credit scoring card is generated according to the essential information of the M client；Its
In, each credit scoring card in the M credit scoring card includes N number of field, and M, N are positive integer, the credit scoring card
The approval results of the client are predicted by prediction model for server；
Detect the practical miss rate of the first field in the M credit scoring card；
If the practical miss rate of first field is greater than preset first miss rate threshold value, by first field
Missing information is sent to default mailing address；Wherein, the practical miss rate of first field is the reality of first field
Lack accounting of the quantity S in the total quantity M of first field.
Wherein, the essential information of M client of the acquisition of processor 601 may include:
The essential information of the M client is obtained by big data platform, the essential information of the client includes characterization institute
State the credit information of client.
Wherein, processor 601 obtains the essential information of M client, and generates M according to the essential information of the M client
After a credit scoring card, processor 601 is detected in the M credit scoring card before the practical miss rate of the first field, also
May include:
According to preset rules, N number of corresponding miss rate threshold value of field described in the credit scoring card is set.
Wherein, processor 601 obtains the essential information of M client, and generates M according to the essential information of the M client
After a credit scoring card, processor 601 is detected in the M credit scoring card before the practical miss rate of the first field, also
May include:
Judge first field whether with other fields in N number of field in addition to first field to be associated with
Field；
If so, reducing the preset first miss rate threshold value of the first field.
Wherein, processor 601 obtains the essential information of M client, and generates M according to the essential information of the M client
After a credit scoring card, processor 601 is detected in the M credit scoring card before the practical miss rate of the first field, also
May include:
Judge first field whether with other fields in N number of field in addition to first field to couple
Field；
If so, reducing the preset first miss rate threshold value of the first field.
Wherein, processor 601 obtains the essential information of M client, and generates M according to the essential information of the M client
After a credit scoring card, processor 601 is detected in the M credit scoring card before the practical miss rate of the first field, also
May include:
Determine whether first field is critical field according to the parameter of the prediction model；
If so, reducing the preset first miss rate threshold value of the first field；
If it is not, then increasing the preset first miss rate threshold value of first field.
In the concrete realization, as a kind of optional embodiment, processor 601 may include one or more CPU, such as
CPU0 and CPU1 in Fig. 6.
In the concrete realization, as a kind of optional embodiment, server 600 may include multiple processors, such as Fig. 6
In processor 601 and processor 608.Each of these processors can be monokaryon (single-CPU) processing
Device is also possible to multicore (multi-CPU) processor.Here processor can refer to one or more equipment, circuit,
And/or the processing core for handling data (such as computer program instructions).
In the concrete realization, as a kind of optional embodiment, server 600 can also include output equipment 605 and defeated
Enter equipment 606.Output equipment 605 and processor 601 communicate, and can show information in many ways.For example, output equipment
605 can be liquid crystal display (Liquid Crystal Display, LCD), light emitting diode (Light Emitting
Diode, LED) display equipment, cathode-ray tube (Cathode Ray Tube, CRT) display equipment or projector
(projector) etc..Input equipment 606 and processor 601 communicate, and can receive the input of user in many ways.For example, defeated
Entering equipment 606 can be mouse, keyboard, touch panel device or sensing equipment etc..
In the concrete realization, server 600 can be desktop computer, portable computer, network server, palm PC
(Personal Digital Assistant, PDA), cell phone, wireless device, communication equipment, embedded are set tablet computer
It is standby.The embodiment of the present invention does not limit the type of server 600.
The embodiment of the invention also provides a kind of computer storage medium, for be stored as above-mentioned Figure 1A, Fig. 2, Fig. 3 and
Computer software instructions used in server shown in Fig. 4, it includes for executing program involved in above method embodiment.
By executing the program of storage, the early warning to field miss rate may be implemented.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The shape for the computer program product implemented in usable storage medium (including but not limited to magnetic disk storage and optical memory etc.)
Formula.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Obviously, those skilled in the art can carry out various modification and variations without departing from the essence of the application to the application
Mind and range.In this way, if these modifications and variations of the application belong to the range of the claim of this application and its equivalent technologies
Within, then the application is also intended to include these modifications and variations.
Claims (10)
1. a kind of field miss rate method for early warning characterized by comprising
The essential information of M client is obtained, and M credit scoring card is generated according to the essential information of the M client；Wherein,
Each credit scoring card in the M credit scoring card includes N number of field, and M, N are positive integer, and the credit scoring card is used for
Server predicts the approval results of the client by prediction model；
Detect the practical miss rate of the first field in the M credit scoring card；
If the practical miss rate of first field is greater than preset first miss rate threshold value, by the missing of first field
Information is sent to default mailing address；Wherein, the practical miss rate of first field is the practical missing of first field
Accounting of the quantity S in the total quantity M of first field.
2. the method according to claim 1, wherein the essential information for obtaining M client includes:
The essential information of the M client is obtained by big data platform, the essential information of the client includes characterizing the visitor
The credit information at family.
3. the method according to claim 1, wherein the essential information for obtaining M client, and according to described
After the essential information of M client generates M credit scoring card, the first field in the detection M credit scoring card
Before practical miss rate, further includes:
According to preset rules, N number of corresponding miss rate threshold value of field described in the credit scoring card is set.
4. the method according to claim 1, wherein the essential information for obtaining M client, and according to described
After the essential information of M client generates M credit scoring card, the first field in the detection M credit scoring card
Before practical miss rate, further includes:
Judge first field whether with other fields in N number of field in addition to first field for associated characters
Section；
If so, reducing the preset first miss rate threshold value of the first field.
5. the method according to claim 1, wherein the essential information for obtaining M client, and according to described
After the essential information of M client generates M credit scoring card, the first field in the detection M credit scoring card
Before practical miss rate, further includes:
Judge first field whether with other fields in N number of field in addition to first field to couple word
Section；
If so, reducing the preset first miss rate threshold value of the first field.
6. the method according to claim 1, wherein the essential information for obtaining M client, and according to described
After the essential information of M client generates M credit scoring card, the first field in the detection M credit scoring card
Before practical miss rate, further includes:
Determine whether first field is critical field according to the parameter of the prediction model；
If so, reducing the preset first miss rate threshold value of the first field；
If it is not, then increasing the preset first miss rate threshold value of first field.
7. a kind of server, which is characterized in that including the unit for executing as the method according to claim 1 to 6.
8. a kind of server, which is characterized in that including processor and memory, the processor and memory are connected with each other,
In, the memory is configured for calling said program code, execute such as storing application code, the processor
Method described in any one of claims 1-6.
9. a kind of computer readable storage medium, which is characterized in that the computer storage medium is stored with computer program, institute
Stating computer program includes program instruction, and described program instruction executes the processor as right is wanted
Seek the described in any item methods of 1-6.
10. a kind of computer program, which is characterized in that the computer program includes program instruction, and quilt is worked as in described program instruction
Processor makes the processor execute as the method according to claim 1 to 6 when executing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810760345.5A CN109146132A (en) | 2018-07-11 | 2018-07-11 | Field miss rate method for early warning, server, storage medium and computer program |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810760345.5A CN109146132A (en) | 2018-07-11 | 2018-07-11 | Field miss rate method for early warning, server, storage medium and computer program |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109146132A true CN109146132A (en) | 2019-01-04 |
Family
ID=64800207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810760345.5A Withdrawn CN109146132A (en) | 2018-07-11 | 2018-07-11 | Field miss rate method for early warning, server, storage medium and computer program |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109146132A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090006489A (en) * | 2007-07-11 | 2009-01-15 | 고려대학교 산학협력단 | Toolkit of constructing credit risk model, method of managing credit risk using credit risk model construction and recording medium thereof |
| CN102163310A (en) * | 2010-02-22 | 2011-08-24 | 深圳市腾讯计算机***有限公司 | Information pushing method and device based on credit rating of user |
| US20170039637A1 (en) * | 2015-08-05 | 2017-02-09 | Telefonica Digital Espana, S.L.U. | Computer-implemented method, a system and computer program products for assessing the credit worthiness of a user |
| CN108053310A (en) * | 2017-11-24 | 2018-05-18 | 深圳市牛鼎丰科技有限公司 | Credit scoring method, apparatus, computer equipment and storage medium |
| AU2018101523A4 (en) * | 2018-10-14 | 2018-11-15 | Gao, Zhuolun Mr | A personal credit scoring model based on machine learning method |
-
2018
- 2018-07-11 CN CN201810760345.5A patent/CN109146132A/en not_active Withdrawn
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090006489A (en) * | 2007-07-11 | 2009-01-15 | 고려대학교 산학협력단 | Toolkit of constructing credit risk model, method of managing credit risk using credit risk model construction and recording medium thereof |
| CN102163310A (en) * | 2010-02-22 | 2011-08-24 | 深圳市腾讯计算机***有限公司 | Information pushing method and device based on credit rating of user |
| US20170039637A1 (en) * | 2015-08-05 | 2017-02-09 | Telefonica Digital Espana, S.L.U. | Computer-implemented method, a system and computer program products for assessing the credit worthiness of a user |
| CN108053310A (en) * | 2017-11-24 | 2018-05-18 | 深圳市牛鼎丰科技有限公司 | Credit scoring method, apparatus, computer equipment and storage medium |
| AU2018101523A4 (en) * | 2018-10-14 | 2018-11-15 | Gao, Zhuolun Mr | A personal credit scoring model based on machine learning method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109063985B (en) | Business risk decision method and device | |
| CN110766541B (en) | Loan risk assessment method, apparatus, device and computer readable storage medium | |
| US20140250011A1 (en) | Account type detection for fraud risk | |
| CN109670936A (en) | Loan examination & approval processing method, platform, equipment and computer readable storage medium | |
| US20110166987A1 (en) | Evaluating Loan Access Using Online Business Transaction Data | |
| EP1676189A2 (en) | Application processing and decision systems and processes | |
| CN107844948A (en) | Credit methods, device, equipment and readable storage medium storing program for executing based on credit product storehouse | |
| CN113989019A (en) | Method, device, equipment and storage medium for identifying risks | |
| US20030144933A1 (en) | Method and apparatus for determining a customer's likelihood of reusing a financial account | |
| CN109934688A (en) | A kind of reference result determines method and device | |
| CN112581283A (en) | Method and device for analyzing and alarming business bank employee transaction behaviors | |
| CN114331191A (en) | Credit risk assessment method and device based on enterprise scale and association | |
| CN110197426A (en) | A kind of method for building up of credit scoring model, device and readable storage medium storing program for executing | |
| CN105631732A (en) | Method and device for determining user authority | |
| CN107563588A (en) | A kind of acquisition methods of personal credit and acquisition system | |
| CN113536319B (en) | Interface risk prediction method and device, computer equipment and storage medium | |
| JP2003036346A (en) | Method for evaluating operational risk and its system | |
| Bello | The Role of Data Analytics in Enhancing Financial Inclusion in Emerging Economies | |
| CN116934131A (en) | Enterprise operation condition assessment method, device and equipment | |
| CN115578170A (en) | Financial batch certificate making method, device, equipment and storage medium | |
| CN109146132A (en) | Field miss rate method for early warning, server, storage medium and computer program | |
| CN110263044B (en) | Data storage method, device, equipment and computer readable storage medium | |
| US20170186095A1 (en) | Centralized GAAP approach for multidimensional accounting to reduce data volume and data reconciliation processing costs | |
| CN107423982A (en) | Service implementation method and device based on account | |
| CN114880369A (en) | Risk credit granting method and system based on weak data technology |
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 | ||
| CB02 | Change of applicant information |
Address after: 518000 Guangdong city of Shenzhen province Qianhai Shenzhen Hong Kong cooperation zone before Bay Road No. 1 building 201 room A (located in Shenzhen Qianhai business secretary Co. Ltd.) Applicant after: Shenzhen Rongyimai Information Technology Co., Ltd. Address before: 518000 Guangdong city of Shenzhen province Qianhai Shenzhen Hong Kong cooperation zone before Bay Road No. 1 building 201 room A (located in Shenzhen Qianhai business secretary Co. Ltd.) Applicant before: Maimaiti Mdt InfoTech Ltd, Shenzhen |
|
| CB02 | Change of applicant information | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190104 |
|
| WW01 | Invention patent application withdrawn after publication |