CN109345371A - Personal reference report backtracking method and system - Google Patents
Personal reference report backtracking method and system Download PDFInfo
- Publication number
- CN109345371A CN109345371A CN201811001738.4A CN201811001738A CN109345371A CN 109345371 A CN109345371 A CN 109345371A CN 201811001738 A CN201811001738 A CN 201811001738A CN 109345371 A CN109345371 A CN 109345371A
- Authority
- CN
- China
- Prior art keywords
- report
- backtracking
- risk rating
- identified
- time point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention relates to a kind of personal reference report backtracking method and system, and the method comprising the steps of: obtaining the credit information of each body of the report；Seek the risk rating of all body of the report；Risk rating cut-off is set, the body of the report by risk rating lower than the risk rating cut-off is identified as white label, and the body of the report equal to or higher than the risk rating cut-off is identified as black label；Setting backtracking time point and backtracking rule, are recalled according to the backtracking rule, and the personal reference for generating backtracking time point recalls report, the sample identification of individual's reference backtracking report with good sample or bad sample.By the method for the invention and system, the personal reference backtracking report of specified time point can be generated ,/the mark of black label and have in reporting, sample is provided for building Credit Model and supports, be conducive to the accuracy of raising credit evaluation.
Description
Technical field
The present invention relates to financial credit technical field, in particular to a kind of personal reference report backtracking method and system.
Background technique
" reference " has recorded personal past behavior of credit, these behaviors will affect the economic activity in personal future.It is " a
People's reference report " is the record for the record personal credit information provided by People's Bank of China's reference center, and data are by commercial silver
Capable and associated mechanisms provide, and summarize integration by reference center.Personal reference reports the carrier as reference information, can be by right
The interpretation of its content predicts the Default Probability of the body of the report, to carry out the assessment of " credit " risk." reference " is in finance
Good financial " debt-credit " order is established in environment, plays great contribution.However, People's Bank of China's reference center is provided
Personal reference report can only be current time report, then cause assessing credit risks according to extremely limited, Zhi Nengtong
It crosses the mode interpreted and reported and carries out credit evaluation, and the quantitative model of credit evaluation cannot be established, lead to the accurate of credit evaluation
Property is low.
Summary of the invention
The purpose of the present invention is to provide a kind of personal reference report backtracking method and system, can obtain backtracking time point
Reference report provides sample support for the quantization modeling of credit evaluation.
In order to achieve the above-mentioned object of the invention, the embodiment of the invention provides following technical schemes:
On the one hand, a kind of personal reference report retrogressive method is provided in the embodiment of the present invention, which is characterized in that including with
Lower step:
Step 1, the credit information of each body of the report is obtained；
Step 2, it is directed to each body of the report, based on the credit information of this report main body, seeks this report main body
Risk rating；
Step 3, the risk rating of all body of the report is sought out according to step 2；
Step 4, risk rating cut-off is set, risk rating is lower than to the body of the report mark of the risk rating cut-off
Knowing is white label, and the body of the report equal to or higher than the risk rating cut-off is identified as black label；
Step 5, setting backtracking time point and backtracking rule, are recalled according to the backtracking rule, generate backtracking time point
Personal reference backtracking report, individual's reference backtracking report have sample identification, are identified as the body of the report of white label
Personal reference backtracking report is identified preferably sample, and the personal reference backtracking report for being identified as the body of the report of black label is marked
Knowing is bad sample.
The personal reference backtracking report of specified time point can be generated by the above method, and have good bad sample in report
Sample identification, i.e., the body of the report have black/white label mark, for building Credit Model provide sample support, be conducive to mention
The accuracy of high credit evaluation.
On the other hand, the embodiment of the present invention provides a kind of personal reference report backtracking system simultaneously, which is characterized in that packet
It includes with lower module:
Information acquisition module, for obtaining the credit information of the body of the report；
Risk rating module seeks all body of the report for the credit information based on each body of the report respectively
Risk rating；
Good black tag identifier module cuts risk rating lower than the risk rating for setting risk rating cut-off
The body of the report of branch is identified as white label, and the body of the report equal to or higher than the risk rating cut-off is identified as black mark
Label；
Recall report generation module, recall time point and backtracking rule for setting, recalled according to the backtracking rule,
The personal reference for generating backtracking time point recalls report, and individual's reference backtracking report has sample identification, is identified as white mark
The personal reference backtracking report of the body of the report of label is identified preferably sample, is identified as the personal sign of the body of the report of black label
Letter backtracking report is identified as bad sample.
In another aspect, the embodiment of the present invention provides a kind of computer-readable storage including computer-readable instruction simultaneously
Medium, the computer-readable instruction make processor execute the operation in method described in the embodiment of the present invention when executed.
In another aspect, the embodiment of the present invention provides a kind of electronic equipment simultaneously, comprising: memory stores program instruction；
Processor is connected with the memory, executes the program instruction in memory, realizes in method described in the embodiment of the present invention
The step of.
Compared with prior art, the personal reference backtracking report of specified time point, and body of the report band can be generated in the present invention
There is the mark of black/white label, provides sample for building Credit Model and support, can be constructed by the modeling method of any conventional
Credit Model is conducive to the accuracy for improving credit evaluation.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is a kind of flow chart of personal reference report retrogressive method described in present pre-ferred embodiments.
Fig. 2 is the various dimensions risk class mapping ruler schematic diagram of the loan illustrated.
Fig. 3 is the schematic diagram of the index set of the backtracking report building generated based on Fig. 1 the method.
Fig. 4 is that a kind of personal reference provided in the present embodiment reports the functional block diagram of backtracking system.
Fig. 5 is the structural block diagram of a kind of electronic equipment provided in the present embodiment.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but it is merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
It should be noted that for the ease of difference, herein, the personal reference report name that People's Bank of China is provided
It is reported for personal reference, and the report that the method through the embodiment of the present invention generates is named as personal reference backtracking report.
Referring to Fig. 1, the present embodiment has illustratively provided a kind of personal reference report retrogressive method, this method include with
Lower step:
Step 1, the credit information of each body of the report is obtained.The body of the report is to refer to being queried for personal reference report
Person, i.e. individual subscriber, credit information can be obtained from each business bank or associated mechanisms, i.e., from being arranged in business bank or phase
It is obtained in the server of shutting mechanism.
Step 2, it is directed to each body of the report, based on the credit information of this report main body, seeks this report main body
Risk rating.Specifically, it can realize in the following ways:
It is comprehensive to multiple dimensions of each loan of the body of the report to carry out risk mapping, it takes in the multiple dimension most
The risk rating that high-risk grade is provided a loan as this chooses the risk rating maximum value of all loans as this report main body
Risk rating.
As an example, the multiple dimension may include four dimensions, be longest continuously overdue issue, account status respectively
(normally, close, produce, is overdue, bad accounts), five-category (normally, pay close attention to, is secondary, suspicious, lose, is unknown), special deal
(duration of an exhibition, guarantor go back, pay a debt with the capital, payment beforehand, producing, other in generation), risk class can be preferably divided into 0-5 totally 6 etc.
Grade can carry out risk mapping according to rule as shown in Figure 2.Longest therein continuously overdue issue, account status and Pyatyi
These three dimensions of classifying can individually carry out risk mapping, and for special deal, then it can be continuously overdue in conjunction with longest
Issue is comprehensive to carry out risk mapping, for example, if the type of transaction of special deal is " guarantor's generation is also " or " paying a debt with the capital ", wind
Dangerous grade is mapped as 5, and for another example, if the type of transaction of special deal is " duration of an exhibition ", and continuously overdue issue is not the longest provided a loan
0, then risk class is mapped as 4, if the type of transaction of special deal is " duration of an exhibition ", and continuously overdue issue is 0 to the longest provided a loan,
Then risk class is mapped as 0.
Citing, the credit information based on certain body of the report obtain the longest of a certain pen loan continuously overdue issue, account shape
State, five-category, special deal this four dimensions risk class be respectively 3,3,4,2, then the pen of this report main body is borrowed
The risk rating of money is 4, and this report main body is provided a loan for 3 totally, and in addition the risk ratings of two loans are respectively 2,3, then should
The risk rating of the body of the report is 4.
Step 3, the risk rating of all body of the report is sought out according to step 2.
Step 4, risk rating cut-off is set, risk rating is lower than to the body of the report mark of the risk rating cut-off
Knowing is white label (or being white list), and the body of the report equal to or higher than the risk rating cut-off is identified as black label
(or being blacklist).
Generally, when setting risk rating cut-off, the risk partiality according to business demand is needed, suitable risk is selected
Grading cut-off.For example, the risk partiality of small amount consumer credit class loan is provided a loan higher than wholesale home mortgage class, the former can be selected
It selects 3 and is used as risk rating cut-off, the latter can choose 2 and be used as risk rating cut-off.Under normal conditions, risk rating cutting
Point suggests being selected as 2 or 3 (the case where being directed to 6 risk class).Too low risk rating cut-off to noise-sensitive,
The accuracy of model is reduced when constructing Credit Model, excessively high risk rating cut-off is excessive to signal screening, can reduce model
Applicability.
Step 5, setting backtracking time point and backtracking rule, are recalled according to the backtracking rule, generate backtracking time point
Personal reference backtracking report, individual's reference backtracking report has sample identification, specifically, being identified as the report of white label
The personal reference backtracking report of main body is identified preferably sample, is identified as the personal reference backtracking report of the body of the report of black label
Announcement is identified as bad sample.The personal reference backtracking report of generation can be exported to the service of the lending agencies such as each business bank
In device, using the sample as building Credit Model.Or it can also be in personal reference backtracking report component of the local based on generation
After good Credit Model, output carries out credit evaluation for the server in the server of the lending agencies such as each business bank.
For white label, any loan is normally to provide a loan, it is possible to when selecting the granting of any loan
Between as backtracking time point.For black label, the loan that only risk rating is higher than risk rating cut-off is only abnormal loan, and
Loan is only the judgement reason for causing this report main body to be identified as black label extremely for these, therefore can only select any risk
Grading is higher than the Time Of Release of the loan of risk rating cut-off as backtracking time point.Therefore in this step, for recalling time point
Setting the Time Of Release of any loan can be set as backtracking time point for white label, and for black label, then
Need to set Time Of Release of any risk rating higher than the loan of risk rating cut-off as backtracking time point.
And as more preferably set-up mode, for white label, it can choose the granting of the loan of loan time the latest
Time is as backtracking time point；For black label, can choose the loan time the latest and risk rating be higher than risk rating cutting
The Time Of Release of one loan of point is as backtracking time point.The loan of selection loan time the latest, i.e., selection is near existing
The backtracking time, can farthest reduce as information backtracking caused by historical information lose, guarantee establishing credit
There is information as much as possible can use when model.
Backtracking rule described in this step refers to that included field is reported in personal reference backtracking.Personal reference backtracking report
Field in announcement can be arranged with reference to the field in personal reference report, i.e., to whole fields in the report of personal reference, first
Determine which field is not influenced and can be retained by recalling, the influence which field will receive backtracking can not retain and can only delete
It removes, which field is influenced but can retain and need to do correspondingly to adjust by recalling.For example, loan principal balance field is
Dynamic field, can with refund carry out and change because can not know the refund behavior of the specific body of the report, thus the field without
Method retains, and needs to delete.Loan agreement amount field, be static fields, just had determined that in loan origination and will not with also
Money carries out and changes, therefore the field can retain, and be not required to adjust.Loan status deadline field, the generation dependent on report
Date can be known, therefore the field can protect after the backtracking time of report has been determined (date of formation of i.e. new report)
It stays, but needs to adjust.In addition, to whole records in the report of personal reference, record occurs between backtracking time point and current time point
Need to delete, record is that can retain before recalling time point occurs.
In this step, the generating mode of personal reference report is copied, according to backtracking rule, the first personal basic letter of backtracking
Then breath recalls credit transaction information, then summarized again based on the information after these backtrackings for informative abstract, then recalled public
Information finally recalls query information.The final personal reference backtracking report for obtaining backtracking time point end to end plus report.
Different backtracking time point available more part personal reference backtracking reports of one body of the report in reality, but
The generally unified a individual's reference time for use (Time Of Release of a nearest loan is as backtracking time point) the latest in practical application
It traces back report, ignores other personal reference backtracking reports earlier.So in practical applications, the body of the report and its people's reference are returned
One-to-one relationship is presented in report of tracing back.
Report that the difficult point that assessing credit risks is carried out to establish quantitative model is according to personal reference at present: 1) in individual
Reference report generation time point, i.e., before loan origination, the not no black and white tag identifier of the body of the report, thus can not be according to supervised learning
Method personal reference is modeled, afterwards can not before loan origination to application main body carry out default risk assessment.2)
Due to whether breaking a contract the generation of this event after offering loans, it is contemplated that answering utilization of a loan to the actual effect of reference report
Collage-credit data before granting is modeled, if still using after offering loans reference report modeling, will affect reference for
The accuracy of risk assessment.And the middle above method, the personal reference backtracking that specified time point can be generated are reported through this embodiment,
And the sample identification of good bad sample is had in report, i.e. the body of the report has black/white label, provides for building Credit Model
Sample is supported, may be implemented to construct Credit Model by machine learning method, is conducive to the accuracy for improving credit evaluation.
Using the present embodiment above method, sample set when building Credit Model can be expanded first.By taking XX project as an example,
By analyzing the distribution characteristics of user, filter out two datasets: 1) the personal reference report generation time loan origination just
User in negative a quarter loan period, including the white label of the black label in 107 families and 535 families.2) reference report generation
The user in a quarter period to 3 years after loan origination time, including the white label of the black label in 277 families and 1385 families.The
The reference report of a kind of user group can be used directly to measure the reference state of applicant at that time.Due to the second class customer group's
Reference report generally lags behind loan origination time point, can not accurately describe applicant in the reference state of loan origination time point.
Using the reference retrogressive method stated herein, reference report is pushed back into loan origination time point, reduces use to the full extent
Reference state of the family before loan origination time point, has expanded modeling sample significantly, has preferably depicted the feature between black/white label
Difference plays major contribution for the foundation of subsequent Credit Model.
Variable and explained variable secondly can be explained using this method to model in the supervised learning of identical time point.With
For YY project, 18 black labels are defined with 3 for risk rating cut-off to 877 samples of total amount.Based on the sample set
It is total to construct six credit history, overdue history, debt burden, contractual capacity, financial strain, recent credit demand Index modules
45 indexs are counted, as shown in Figure 3.Final logistic regression and random forests algorithm in supervised learning method, Credit Model
Performance on test set, (Area Under of the Curve of ROC, as area under ROC curve, value exist AUC
0-1, if a white label and black label are randomly selected in AUC expression, model correctly judges that the value of black label is higher than the value of white label
Probability, AUC=0.5 indicates that random guess, model do not have a separating capacity, and AUC is higher than 0.5, and the area for indicating model closer to 1
Point ability is higher) be 0.6 or so, KS (Kolmogorov-Smirnov is examined, to examine two experiences distributions whether different,
Whether the distribution i.e. to the distribution and white label of examining black label is different, and the difference of good black label distribution is bigger, and KS value is bigger,
The separating capacity of model is stronger) it is 0.4 or so, show the personal reference obtained using the method for the present invention backtracking report as sample
It is trained, the Credit Model constructed separating capacity with higher, it can credit relatively accurately is carried out to individual and is commented
Estimate.
Referring to Fig. 4, being based on identical inventive concept, a kind of personal reference backtracking system is provided in the present embodiment simultaneously
System, because being identical inventive concept, place not described herein may refer to the description process of preceding method.
As shown in figure 4, individual's reference backtracking system includes information acquisition module, risk rating module, black and white label
Mark module and backtracking report generation module.
Wherein, information acquisition module is used to obtain the credit information of the body of the report.
Risk rating module is used for the credit information based on each body of the report, seeks the wind of all body of the report respectively
Danger grading.For example, being directed to each body of the report, the multiple dimensions provided a loan its each are comprehensive to carry out risk mapping, takes
The risk rating that highest risk class in the multiple dimension is provided a loan as this, the risk rating for choosing all loans are maximum
It is worth the risk rating as this report main body.
Black and white tag identifier module is lower than the risk rating cutting for setting risk rating cut-off, by risk rating
The body of the report of point is identified as white label, and the body of the report equal to or higher than the risk rating cut-off is identified as black label.
Report generation module is recalled for setting backtracking time point and backtracking rule, and is returned according to the backtracking rule
It traces back, the personal reference for generating backtracking time point recalls report, the sample of individual's reference backtracking report with good sample or bad sample
This mark, wherein the personal reference backtracking report for being identified as the body of the report of white label is identified preferably sample, is identified as
The personal reference backtracking report of the body of the report of black label is identified as bad sample.
In the scheme advanced optimized, above system further includes model construction module, for application backtracking report generation
Module personal reference backtracking report generated is used as training sample, and building is used for the Credit Model of credit evaluation.
As shown in figure 5, the present embodiment provides a kind of electronic equipment simultaneously, which may include 51 He of processor
Memory 52, wherein memory 52 is coupled to processor 51.It is worth noting that, the figure is exemplary, it can also be used
The structure is supplemented or substituted to the structure of his type, realizes data extraction, report generation, communication or other function.
As shown in figure 5, the electronic equipment can also include: input unit 53, display unit 54 and power supply 55.It is worth noting
, which is also not necessary to include all components shown in Fig. 5.In addition, electronic equipment can also include
The component being not shown in Fig. 5 can refer to the prior art.
Processor 51 is sometimes referred to as controller or operational controls, may include microprocessor or other processor devices and/
Or logic device, the processor 51 receive the operation of all parts of input and controlling electronic devices.
Wherein, memory 52 for example can be buffer, flash memory, hard disk driver, removable medium, volatile memory, it is non-easily
The property lost one of memory or other appropriate devices or a variety of, can store configuration information, the processor 51 of above-mentioned processor 51
The instruction of execution, record the information such as list data.Processor 51 can execute the program of the storage of memory 52, to realize information
Storage or processing etc..It in one embodiment, further include buffer storage in memory 52, i.e. buffer, with the intermediate letter of storage
Breath.
Input unit 53 is for example for providing the credit information of each body of the report to processor 51.Display unit 54 is used for
Show treatment process in it is various as a result, risk rating, the generation of for example each body of the report personal reference recall report, should
Display unit can be for example LCD display, but the present invention is not limited thereto.Power supply 55 is used to provide electric power for electronic equipment.
The embodiment of the present invention also provides a kind of computer-readable instruction, wherein when executing described instruction in the electronic device
When, described program makes electronic equipment execute the operating procedure that the method for the present invention is included.
The embodiment of the present invention also provides a kind of storage medium for being stored with computer-readable instruction, wherein the computer can
Reading instruction makes electronic equipment execute the operating procedure that the method for the present invention is included.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware
With the interchangeability of software, each exemplary composition and step are generally described according to function in the above description.This
A little functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Specially
Industry technical staff can use different methods to achieve the described function each specific application, but this realization is not
It is considered as beyond the scope of this invention.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or the network equipment etc.) executes the complete of each embodiment the method for the present invention
Portion or part steps.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only
Memory), random access memory (RAM, RandomAccess Memory), magnetic or disk etc. are various can store journey
The medium of sequence code.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.
Claims (11)
1. a kind of individual's reference reports retrogressive method, which comprises the following steps:
Step 1, the credit information of each body of the report is obtained；
Step 2, it is directed to each body of the report, based on the credit information of this report main body, seeks the risk of this report main body
Grading；
Step 3, the risk rating of all body of the report is sought out according to step 2；
Step 4, risk rating cut-off is set, the body of the report by risk rating lower than the risk rating cut-off is identified as
White label, the body of the report equal to or higher than the risk rating cut-off are identified as black label；
Step 5, setting backtracking time point and backtracking rule, are recalled according to the backtracking rule, generate the individual of backtracking time point
Reference backtracking report, individual's reference backtracking report have sample identification, are identified as the individual of the body of the report of white label
Reference backtracking report is identified preferably sample, and the personal reference backtracking report for being identified as the body of the report of black label is identified as
Bad sample.
2. right the method according to claim 1, wherein be directed to each body of the report in the step 2
Multiple dimensions of its each loan are comprehensive to carry out risk mapping, takes the highest risk class in the multiple dimension as the pen
Risk rating of the risk rating maximum value of all loans as this report main body is chosen in the risk rating of loan.
3. the method according to claim 1, wherein in the step 5 setting backtracking time point when, for black mark
Label select any risk rating to be higher than the Time Of Release of the loan of risk rating cut-off as backtracking time point.
4. according to the method described in claim 3, it is characterized in that, in the step 5 setting backtracking time point when, for white mark
Label select the Time Of Release of the loan of loan time the latest as backtracking time point；For black label, the selection loan time is most
Late and risk rating is higher than the Time Of Release of a loan of risk rating cut-off as backtracking time point.
5. the method according to claim 1, wherein being levied when setting backtracking rule for individual in the step 5
Whole fields in letter report, determine the field for needing the field retained, the field deleted and needs being needed to adjust respectively, need to
The field that the field and needs to be retained adjust forms the field in personal reference backtracking report.
6. according to the method described in claim 5, it is characterized in that, being recalled in the step 5 according to the backtracking rule
When, the personal essential information of the body of the report is recalled first, credit transaction information is then recalled, then again based on the information after backtracking
Summarize for informative abstract, then recalls public information again, finally recall query information.
7. the method according to claim 1, wherein further including step 6, the obtained personal sign of applying step 5
Letter backtracking report is used as training sample, and building is used for the Credit Model of credit evaluation.
8. a kind of individual's reference reports backtracking system, which is characterized in that comprise the following modules:
Information acquisition module, for obtaining the credit information of each body of the report:
Risk rating module seeks the risk of all body of the report for the credit information based on each body of the report respectively
Grading；
Risk rating is lower than the risk rating cut-off for setting risk rating cut-off by black and white tag identifier module
The body of the report be identified as white label, the body of the report equal to or higher than the risk rating cut-off is identified as black label；
Recall report generation module, for setting backtracking time point and backtracking rule, is recalled according to the backtracking rule, generated
The personal reference for recalling time point recalls report, and individual's reference backtracking report has sample identification, is identified as white label
The personal reference backtracking report of the body of the report is identified preferably sample, and the personal reference for being identified as the body of the report of black label is returned
Report of tracing back is identified as bad sample.
9. system according to claim 8, which is characterized in that further include model construction module, for application backtracking report
Generation module personal reference backtracking report generated is used as training sample, and building is used for the Credit Model of credit evaluation.
10. a kind of computer readable storage medium including computer-readable instruction, which is characterized in that the computer-readable finger
Enable the operation for requiring processor perform claim in any the method for 1-7.
11. a kind of electronic equipment, which is characterized in that the equipment includes:
Memory stores program instruction；
Processor is connected with the memory, executes the program instruction in memory, realizes that claim 1-7 is any described
Step in method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811001738.4A CN109345371A (en) | 2018-08-30 | 2018-08-30 | Personal reference report backtracking method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811001738.4A CN109345371A (en) | 2018-08-30 | 2018-08-30 | Personal reference report backtracking method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109345371A true CN109345371A (en) | 2019-02-15 |
Family
ID=65292321
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811001738.4A Pending CN109345371A (en) | 2018-08-30 | 2018-08-30 | Personal reference report backtracking method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109345371A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110717817A (en) * | 2019-08-14 | 2020-01-21 | 深圳壹账通智能科技有限公司 | Pre-loan approval method and device, electronic equipment and computer-readable storage medium |
| CN111046947A (en) * | 2019-12-10 | 2020-04-21 | 成都数联铭品科技有限公司 | Training system and method of classifier and identification method of abnormal sample |
| CN113177047A (en) * | 2021-04-23 | 2021-07-27 | 上海晓途网络科技有限公司 | Data backtracking method and device, electronic equipment and storage medium |
| CN115186489A (en) * | 2022-07-13 | 2022-10-14 | 中银消费金融有限公司 | Grading modeling method and system based on pedestrian credit information rejection inference technology |
| CN113177047B (en) * | 2021-04-23 | 2024-06-07 | 上海晓途网络科技有限公司 | Data backtracking method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106802928A (en) * | 2016-12-26 | 2017-06-06 | 厦门亿力吉奥信息科技有限公司 | Power network historical data management method and its system |
| CN107330785A (en) * | 2017-07-10 | 2017-11-07 | 广州市触通软件科技股份有限公司 | A kind of petty load system and method based on the intelligent air control of big data |
| CN107424070A (en) * | 2017-03-29 | 2017-12-01 | 广州汇融易互联网金融信息服务有限公司 | A kind of loan user credit ranking method and system based on machine learning |
| CN107437223A (en) * | 2017-08-17 | 2017-12-05 | 重庆小雨点小额贷款有限公司 | Credit information checking method, device and equipment |
| CN107657525A (en) * | 2017-08-29 | 2018-02-02 | 深圳市佰仟金融服务有限公司 | One kind loan measures and procedures for the examination and approval and server |
-
2018
- 2018-08-30 CN CN201811001738.4A patent/CN109345371A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106802928A (en) * | 2016-12-26 | 2017-06-06 | 厦门亿力吉奥信息科技有限公司 | Power network historical data management method and its system |
| CN107424070A (en) * | 2017-03-29 | 2017-12-01 | 广州汇融易互联网金融信息服务有限公司 | A kind of loan user credit ranking method and system based on machine learning |
| CN107330785A (en) * | 2017-07-10 | 2017-11-07 | 广州市触通软件科技股份有限公司 | A kind of petty load system and method based on the intelligent air control of big data |
| CN107437223A (en) * | 2017-08-17 | 2017-12-05 | 重庆小雨点小额贷款有限公司 | Credit information checking method, device and equipment |
| CN107657525A (en) * | 2017-08-29 | 2018-02-02 | 深圳市佰仟金融服务有限公司 | One kind loan measures and procedures for the examination and approval and server |
Non-Patent Citations (1)
| Title |
|---|
| 向娟等: "地下管网时空数据库设计与应用", 《地理空间信息》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110717817A (en) * | 2019-08-14 | 2020-01-21 | 深圳壹账通智能科技有限公司 | Pre-loan approval method and device, electronic equipment and computer-readable storage medium |
| CN111046947A (en) * | 2019-12-10 | 2020-04-21 | 成都数联铭品科技有限公司 | Training system and method of classifier and identification method of abnormal sample |
| CN113177047A (en) * | 2021-04-23 | 2021-07-27 | 上海晓途网络科技有限公司 | Data backtracking method and device, electronic equipment and storage medium |
| CN113177047B (en) * | 2021-04-23 | 2024-06-07 | 上海晓途网络科技有限公司 | Data backtracking method and device, electronic equipment and storage medium |
| CN115186489A (en) * | 2022-07-13 | 2022-10-14 | 中银消费金融有限公司 | Grading modeling method and system based on pedestrian credit information rejection inference technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR100751965B1 (en) | method and system for predicting attrition customers | |
| CN110111198A (en) | User's financial risks predictor method, device, electronic equipment and readable medium | |
| CN109523276A (en) | The pre-warning monitoring method and device of customer complaint | |
| US20230027450A1 (en) | System and methods for credit underwriting and ongoing monitoring using behavioral parameters | |
| CN108256993A (en) | A kind of credit score appraisal procedure and credit score Evaluation Platform | |
| CN110163413A (en) | Enterprise supervision and method for early warning, device, computer equipment and readable storage medium storing program for executing | |
| CN109345371A (en) | Personal reference report backtracking method and system | |
| CN109214915A (en) | Borrow risk methods of marking, system and computer readable storage medium | |
| CN110223164A (en) | Air control method and system based on transfer learning, computer installation, storage medium | |
| US20210125272A1 (en) | Using Inferred Attributes as an Insight into Banking Customer Behavior | |
| CN110728301A (en) | Credit scoring method, device, terminal and storage medium for individual user | |
| CN109102396A (en) | A kind of user credit ranking method, computer equipment and readable medium | |
| CN115689752A (en) | Method, device and equipment for adjusting wind control rule and storage medium | |
| CN113434575B (en) | Data attribution processing method, device and storage medium based on data warehouse | |
| CN110930078A (en) | Business object identification method, device and equipment | |
| CN102496126A (en) | Custody asset transaction data monitoring equipment | |
| CN110335061A (en) | Trade mode portrait method for building up, device, medium and electronic equipment | |
| CN110059234A (en) | Water utilities anomalous event method for detecting and device, computer installation and storage medium | |
| CN110223132A (en) | Order processing method, apparatus, terminal and storage medium based on more authorization roles | |
| CN109919414A (en) | P2P network loan platform risk analysis method, device and storage medium | |
| CN114298825A (en) | Method and device for extremely evaluating repayment volume | |
| CN113077251A (en) | Abnormal behavior monitoring method and device in prepaid transaction scene | |
| CN112712270A (en) | Information processing method, device, equipment and storage medium | |
| CN111429257A (en) | Transaction monitoring method and device | |
| Menzies et al. | Evidence of Hysteresis| RDP 9310: Explaining the Recent Performance of Australia's Manufactured Exports |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190215 |
|
| RJ01 | Rejection of invention patent application after publication |