CN109934688A - A kind of reference result determines method and device - Google Patents
A kind of reference result determines method and device Download PDFInfo
- Publication number
- CN109934688A CN109934688A CN201910221721.8A CN201910221721A CN109934688A CN 109934688 A CN109934688 A CN 109934688A CN 201910221721 A CN201910221721 A CN 201910221721A CN 109934688 A CN109934688 A CN 109934688A
- Authority
- CN
- China
- Prior art keywords
- target
- reference model
- characteristic index
- model
- result
- 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
Abstract
This application provides a kind of reference results to determine method and device, is applied to reference platform, method includes: to handle request to target service for user, obtains the reference message of user；For target service, a reference model is selected from the reference model library constructed in advance, as target reference model；The relation table of target reference model and reference characteristic index is obtained, and parses reference characteristic index from reference message according to relation table, as target reference characteristic index；By target reference characteristic index input target reference model in, obtain target reference model output as a result, as reference result.In this application, it is improved the movable whole implementation efficiency of reference, and then can be improved and provide the efficiency of Credit Information Services for user.
Description
Technical field
This application involves financial technology field, in particular to a kind of reference result determines method and device.
Background technique
Credit is product of the development of commerce to certain phase as specific economic transaction behavior.As commodity pass through
The range of the development of Ji, transaction with credit is increasingly extensive, especially when transaction with credit diffuses to the whole nation, the whole world, transaction with credit
The credit status that one side wants to know about other side will be extremely difficult.In this case, reference activity is (i.e. by specialized, independent
The third-party institution be that personal or enterprise establishes credibility record, acquisition, objective record its credit information in accordance with the law, and externally mentioning in accordance with the law
For the activity of Credit Information Services) it comes into being.
But how reference activity is efficiently implemented, and provides efficient Credit Information Services as problem for user.
Summary of the invention
In order to solve the above technical problems, the embodiment of the present application, which provides a kind of reference result, determines method and device, to reach
It is improved the movable whole implementation efficiency of reference, and then rises to the purpose that user provides the efficiency of Credit Information Services,
Technical solution is as follows:
A kind of reference result determines method, is applied to reference platform, which comprises
Request is handled to target service for user, obtains the reference message of the user；
For the target service, a reference model is selected from the reference model library constructed in advance, is levied as target
Believe model；
Obtain the relation table of the target reference model and reference characteristic index, and according to the relationships table from the reference
Reference characteristic index is parsed in message, as target reference characteristic index；
The target reference characteristic index is inputted in the target reference model, the target reference model output is obtained
As a result, as reference result.
Preferably, the building process of the reference model in the reference model library, comprising:
Collage-credit data is obtained, as training sample；
Machine learning reference model is trained using the training sample；
Machine learning reference model after training is assessed, and according to the result of assessment to the machine after the training
Study reference model is adjusted, until the result of assessment meets sets requirement；
Executing rule setting is carried out to machine learning reference model adjusted.
Preferably, the building process of the relation table, comprising:
Reference characteristic index is parsed from multiple reference message samples respectively, and the reference characteristic index parsed is deposited
Storage is in index table；
The corresponding reference characteristic index of the target reference model is obtained from the index table；
The corresponding reference characteristic index of the target reference model and the mapping relations of the target reference model are deposited
Storage is in object table, as the relation table.
It is preferably, described to parse reference characteristic index from multiple reference message samples respectively, comprising:
Using the analytical function defined by Similar integral mode, reference feature is parsed from multiple reference message samples respectively
Index.
A kind of reference result determining device, is applied to reference platform, and described device includes:
First obtains module, for handling request to target service for user, obtains the reference message of the user；
First determining module selects a sign for being directed to the target service from the reference model library constructed in advance
Model is believed, as target reference model；
Second determining module, for obtaining the relation table of the target reference model and reference characteristic index, and according to institute
It states relation table and parses reference characteristic index from the reference message, as target reference characteristic index；
Third determining module obtains institute for inputting the target reference characteristic index in the target reference model
State target reference model output as a result, as reference result.
Preferably, described device further include: reference model construction module is used for:
Collage-credit data is obtained, as training sample；
Machine learning reference model is trained using the training sample；
Machine learning reference model after training is assessed, and according to the result of assessment to the machine after the training
Study reference model is adjusted, until the result of assessment meets sets requirement；
Executing rule setting is carried out to machine learning reference model adjusted.
Preferably, described device further include: relation table constructs module, is used for:
Reference characteristic index is parsed from multiple reference message samples respectively, and the reference characteristic index parsed is deposited
Storage is in index table；
The corresponding reference characteristic index of the target reference model is obtained from the index table；
The corresponding reference characteristic index of the target reference model and the mapping relations of the target reference model are deposited
Storage is in object table, as the relation table.
Preferably, the relation table building module includes:
Analyzing sub-module, for using the analytical function defined by Similar integral mode, respectively from multiple reference message samples
In parse reference characteristic index.
Compared with prior art, the application has the beneficial effect that
In this application, request is handled to target service for user, the reference message of the user is obtained, as sign
The data basis for believing analysis selects a reference model, as mesh for target service from the reference model library constructed in advance
Reference model is marked, reduces the process for target service building target reference model, and obtain target reference model and reference
The relation table of characteristic index, relation table can parse for reference characteristic index provides parsing reference, therefore table according to the relationships
Reference characteristic index is parsed from reference message, and the efficiency that reference characteristic index is parsed from reference message can be improved,
On this basis, target reference characteristic index is inputted in target reference model, obtains the result of target reference model output.This
Application shortens the time used, keeps reference movable from the determination of target reference model and the parsing of reference characteristic index
Whole implementation efficiency is improved, and then be can be improved and provided the efficiency of Credit Information Services for user.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the drawings in the following description are only some examples of the present application, for
For those of ordinary skill in the art, without any creative labor, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 is the flow chart that a kind of reference result provided by the present application determines method；
Fig. 2 is a kind of building flow chart of reference model provided by the present application；
Fig. 3 is the building flow chart of the relation table of a kind of target reference model provided by the present application and reference characteristic index；
Fig. 4 is a kind of logical construction schematic diagram of reference result determining device provided by the present application.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
The embodiment of the present application discloses a kind of reference result and determines method, is applied to reference platform, and method includes: for using
Request is handled to target service in family, obtains the reference message of the user；For the target service, from the sign constructed in advance
Believe and select a reference model in model library, as target reference model；The target reference model is obtained to refer to reference feature
Target relation table, and table parses reference characteristic index from the reference message according to the relationships, it is special as target reference
Levy index；The target reference characteristic index is inputted in the target reference model, the target reference model output is obtained
As a result, as reference result.In this application, it is improved the movable whole implementation efficiency of reference, and then can be improved
The efficiency of Credit Information Services is provided for user.
Next method, which is introduced, to be determined to reference result disclosed in the embodiment of the present application, referring to Figure 1, can wrap
It includes:
Step S11, request is handled to target service for user, obtains the reference message of the user.
Needing the target service handled in user, there are in the case where credit evaluation requirement, need to carry out reference for user
Activity, the movable execution of reference, it is necessary first to obtain the reference message of user, the sign of user can be specifically obtained from the People's Bank
Believe message.
The reference message of user is it is to be understood that at least record the history for having the credit transaction occurred between client and bank
The credit report of information.The reference message of user may include but be not limited to: Ministry of Public Security's identity information verifies result, personal base
This information, bank credit Transaction Information, non-banking credit information, I claim and objection mark and query history information.
Step S12, it is directed to the target service, a reference model is selected from the reference model library constructed in advance, is made
For target reference model.
It is understood that including multiple and different reference models, different references in the reference model library constructed in advance
Model is used for the reference activity of different business.
For the target service, a reference model is selected from the reference model library constructed in advance, it is possible to understand that are as follows:
The reference model for being used for target service is selected from the reference model library constructed in advance.
Reference model in reference model library is the model of machine learning training.
Step S13, obtain the relation table of the target reference model and reference characteristic index, and according to the relationships table from
Reference characteristic index is parsed in the reference message, as target reference characteristic index.
In the present embodiment, the relation table of each reference model and reference characteristic index in reference model library is constructed in advance.
Wherein, reference model and the mapping comprising reference model and required reference characteristic index in the relation table of reference characteristic index
Relationship.
On the basis of step S12 determines target reference model, this step from multiple reference models for constructing in advance with
The relation table that target reference model and reference characteristic index are obtained in the relation table of reference characteristic index, that is, determine target reference mould
The mapping relations of type and required reference characteristic index.
Table parses reference characteristic index from the reference message according to the relationships, as target reference characteristic index
It is to be understood that according to the mapping relations of the target reference model and required reference characteristic index, from the reference report
Reference characteristic index is parsed in text, as target reference characteristic index.
It is understood that the mapping relations of the target reference model and required reference characteristic index are index solution
Analysis provides parsing reference, and the efficiency that reference characteristic index is parsed from the reference message can be improved.
Step S14, the target reference characteristic index is inputted in the target reference model, obtains the target reference
Model output as a result, as reference result.
Model of the target reference model as machine learning can execute automatically in the machine, by target reference feature
After index inputs in target reference model, target reference model can be exported as a result, as reference result.
In this application, request is handled to target service for user, the reference message of the user is obtained, as sign
The data basis for believing analysis selects a reference model, as mesh for target service from the reference model library constructed in advance
Reference model is marked, reduces the process for target service building target reference model, and obtain target reference model and reference
The relation table of characteristic index, relation table can parse for reference characteristic index provides parsing reference, therefore table according to the relationships
Reference characteristic index is parsed from reference message, and the efficiency that reference characteristic index is parsed from reference message can be improved,
On this basis, target reference characteristic index is inputted in target reference model, obtains the result of target reference model output.This
Application shortens the time used, keeps reference movable from the determination of target reference model and the parsing of reference characteristic index
Whole implementation efficiency is improved, and then be can be improved and provided the efficiency of Credit Information Services for user.
In another embodiment of the application, it is situated between to the building process of the reference model in above-mentioned reference model library
It continues, refers to Fig. 2, may include:
Step S21, collage-credit data is obtained, as training sample.
Preferably, it can be obtained from the reference characteristic index of history reference message and in the collage-credit data of history Debit User
Collage-credit data is taken, as training sample.
Certainly, in order to improve the efficiency of model construction, can after obtaining collage-credit data, to the collage-credit data of acquisition into
Row normalized, using the collage-credit data after normalized as training sample.
It should be noted that the collage-credit data got needs the collage-credit data for including the good user of credit and generation to disobey
The collage-credit data of user about, to guarantee the accuracy of model training.
Step S22, machine learning reference model is trained using the training sample.
Preferably, machine learning reference model can be established using linear fit machine learning mode.For example, using linear
Fit correlation formula P=a0X0+a1X1+…+anXnEstablish promise breaking model.Wherein: P is that violation correction probability (indicates if P=20%
The client applies for that the Default Probability of loan is that 20%), X0-Xn is reference characteristic index (such as personal credit total amount, six nearest
Month anticipated number etc.), a0-an is the weight of every reference characteristic index.Machine is established using linear fit machine learning mode
The advantage of study reference model is that interpretation is strong, and index weights are clear, are easy to understand.
After establishing machine learning reference model, machine learning reference model is trained using training sample.
Step S23, the machine learning reference model after training is assessed, and according to the result of assessment to the training
Machine learning reference model afterwards is adjusted, until the result of assessment meets sets requirement.
It, can be in terms of technical indicator be assessed with business reasonable evaluation two, to the engineering after training in the present embodiment
Reference model is practised to be assessed.Preferably, technical indicator is assessed can be evaluated using K-S value, and (K-S value is that model distinguishes energy
Power index, K-S value is bigger, and model separating capacity is better), business reasonable evaluation can be to the client to have broken a contract in history
(a loan, credit card) is assessed.
Sets requirement can be configured according to actual needs, be not limited in the present embodiment.
It is corresponding in terms of technical indicator assessment and business reasonable evaluation two to the machine learning reference model after training into
The embodiment of row assessment, sets requirement can be set to technical indicator assessment result and business reasonable evaluation result meets
It is required that.
Machine learning reference model after training is assessed, and according to the result of assessment to the machine after the training
Study reference model is adjusted, until the result of assessment meets sets requirement, the machine learning reference after training can be improved
The accuracy of model.
Step S24, executing rule setting is carried out to machine learning reference model adjusted.
Executing rule setting is carried out to machine learning reference model adjusted, it is possible to understand that are as follows: setting machine learning is levied
Believe the executing rule of model.Such as, executing rule setting is carried out to the promise breaking model established in step S22, is provided with executing rule
Promise breaking model are as follows: if
a0*X0+a1*X1...+an*Xn>0.5
So
Refusal
Otherwise
Pass through.
After carrying out executing rule setting to machine learning reference model adjusted, that is, complete the building of reference model.
It should be noted that the process of each reference model construction is referred to the process of step S21-S24, building
Multiple reference models form reference model library.
In another embodiment of the application, to the target reference model and reference characteristic index in previous embodiment
The building process of relation table is introduced, and refers to Fig. 3, may include:
Step S31, reference characteristic index is parsed from multiple reference message samples respectively, and the reference parsed is special
Sign index is stored in index table.
In the present embodiment, available different types of a large amount of reference messages, as reference message sample, to guarantee to parse
The comprehensive and integrality of obtained reference characteristic index.
Preferably, it can be solved from multiple reference message samples respectively using the analytical function defined by Similar integral mode
Reference characteristic index is precipitated.The analytical function defined by Similar integral mode it is easy to maintain, the update of analytical function can be improved
And maintenance efficiency.
The structure of index table may refer to table 1, as shown in table 1, the index number of a certain item reference characteristic index, index name
Claim and state is stored in index table.
Table 1
| Field name | Chinese name | Sample |
| indexID | Index number | I_A_001/I_A_001/I_B_001 |
| indexName | Index name | LoanCount (loaning bill stroke count) |
| state | State | 0- is effective, 1-XX, 2-XX, and ..N- is invalid |
Step S32, the corresponding reference characteristic index of the target reference model is obtained from the index table.
In the case where target reference model determines, reference characteristic index required for target reference model can also be true
It is fixed, after determining reference characteristic index required for target reference model, target reference model pair is obtained from index table
The reference characteristic index answered.
Step S33, reflecting the corresponding reference characteristic index of the target reference model and the target reference model
The relationship of penetrating is stored in object table, as the relation table.
The structure of relation table may refer to table 2, as shown in table 2, pattern number, this model of some target reference model
In index serial number and the mapping relations of index number be stored in relation table.
Table 2
Next reference result determining device provided by the present application is introduced, the reference result being introduced below determines dress
It sets and determines that method can correspond to each other reference with the reference result being described above.
Fig. 4 is referred to, reference result determining device includes: the first acquisition module 11, the determination of the first determining module 12, second
Module 13 and third determining module 14.
First obtains module 11, for handling request to target service for user, obtains the reference report of the user
Text；
First determining module 12 selects one for being directed to the target service from the reference model library constructed in advance
Reference model, as target reference model；
Second determining module 13, for obtaining the relation table of the target reference model and reference characteristic index, and according to
The relation table parses reference characteristic index from the reference message, as target reference characteristic index；
Third determining module 14 is obtained for inputting the target reference characteristic index in the target reference model
Target reference model output as a result, as reference result.
In the present embodiment, above-mentioned reference result determining device can also include:
Reference model construction module, is used for:
Collage-credit data is obtained, as training sample；
Machine learning reference model is trained using the training sample；
Machine learning reference model after training is assessed, and according to the result of assessment to the machine after the training
Study reference model is adjusted, until the result of assessment meets sets requirement；
Executing rule setting is carried out to machine learning reference model adjusted.
In the present embodiment, above-mentioned reference result determining device can also include:
Relation table constructs module, is used for:
Reference characteristic index is parsed from multiple reference message samples respectively, and the reference characteristic index parsed is deposited
Storage is in index table；
The corresponding reference characteristic index of the target reference model is obtained from the index table；
The corresponding reference characteristic index of the target reference model and the mapping relations of the target reference model are deposited
Storage is in object table, as the relation table.
In the present embodiment, the relation table building module may include:
Analyzing sub-module, for using the analytical function defined by Similar integral mode, respectively from multiple reference message samples
In parse reference characteristic index.
It should be noted that all the embodiments in this specification are described in a progressive manner, each embodiment weight
Point explanation is the difference from other embodiments, and the same or similar parts between the embodiments can be referred to each other.
For device class embodiment, since it is basically similar to the method embodiment, so being described relatively simple, related place ginseng
See the part explanation of embodiment of the method.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each unit can be realized in the same or multiple software and or hardware when application.
As seen through the above description of the embodiments, those skilled in the art can be understood that the application can
It realizes by means of software and necessary general hardware platform.Based on this understanding, the technical solution essence of the application
On in other words the part that contributes to existing technology can be embodied in the form of software products, the computer software product
It can store in storage medium, such as ROM/RAM, magnetic disk, CD, including some instructions are used so that a computer equipment
(can be personal computer, server or the network equipment etc.) executes the certain of each embodiment of the application or embodiment
Method described in part.
Method and device, which is described in detail, to be determined to a kind of reference result provided herein above, is answered herein
With specific case, the principle and implementation of this application are described, and the explanation of above example is only intended to help to manage
Solve the present processes and its core concept；At the same time, for those skilled in the art, according to the thought of the application,
There will be changes in specific embodiment and application range, in conclusion the content of the present specification should not be construed as to this Shen
Limitation please.
Claims (8)
1. a kind of reference result determines method, which is characterized in that be applied to reference platform, which comprises
Request is handled to target service for user, obtains the reference message of the user；
For the target service, a reference model is selected from the reference model library constructed in advance, as target reference mould
Type；
Obtain the relation table of the target reference model and reference characteristic index, and according to the relationships table from the reference message
In parse reference characteristic index, as target reference characteristic index；
The target reference characteristic index is inputted in the target reference model, the knot of the target reference model output is obtained
Fruit, as reference result.
2. the method according to claim 1, wherein the building of the reference model in the reference model library
Journey, comprising:
Collage-credit data is obtained, as training sample；
Machine learning reference model is trained using the training sample；
Machine learning reference model after training is assessed, and according to the result of assessment to the machine learning after the training
Reference model is adjusted, until the result of assessment meets sets requirement；
Executing rule setting is carried out to machine learning reference model adjusted.
3. the method according to claim 1, wherein the building process of the relation table, comprising:
Reference characteristic index is parsed from multiple reference message samples respectively, and the reference characteristic index parsed is stored in
In index table；
The corresponding reference characteristic index of the target reference model is obtained from the index table；
The corresponding reference characteristic index of the target reference model and the mapping relations of the target reference model are stored in
In object table, as the relation table.
4. according to the method described in claim 3, it is characterized in that, described parse from multiple reference message samples respectively is gone on an expedition
Believe characteristic index, comprising:
Using the analytical function defined by Similar integral mode, reference feature is parsed from multiple reference message samples respectively and is referred to
Mark.
5. a kind of reference result determining device, which is characterized in that be applied to reference platform, described device includes:
First obtains module, for handling request to target service for user, obtains the reference message of the user；
First determining module selects a reference mould for being directed to the target service from the reference model library constructed in advance
Type, as target reference model；
Second determining module, for obtaining the relation table of the target reference model and reference characteristic index, and according to the pass
It is that table parses reference characteristic index from the reference message, as target reference characteristic index；
Third determining module obtains the mesh for inputting the target reference characteristic index in the target reference model
Mark reference model output as a result, as reference result.
6. device according to claim 5, which is characterized in that described device further include: reference model construction module is used
In:
Collage-credit data is obtained, as training sample；
Machine learning reference model is trained using the training sample；
Machine learning reference model after training is assessed, and according to the result of assessment to the machine learning after the training
Reference model is adjusted, until the result of assessment meets sets requirement；
Executing rule setting is carried out to machine learning reference model adjusted.
7. device according to claim 5, which is characterized in that described device further include: relation table constructs module, is used for:
Reference characteristic index is parsed from multiple reference message samples respectively, and the reference characteristic index parsed is stored in
In index table；
The corresponding reference characteristic index of the target reference model is obtained from the index table；
The corresponding reference characteristic index of the target reference model and the mapping relations of the target reference model are stored in
In object table, as the relation table.
8. device according to claim 7, which is characterized in that the relation table constructs module and includes:
Analyzing sub-module, for being solved from multiple reference message samples respectively using the analytical function defined by Similar integral mode
Reference characteristic index is precipitated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910221721.8A CN109934688A (en) | 2019-03-22 | 2019-03-22 | A kind of reference result determines method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910221721.8A CN109934688A (en) | 2019-03-22 | 2019-03-22 | A kind of reference result determines method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109934688A true CN109934688A (en) | 2019-06-25 |
Family
ID=66988139
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910221721.8A Pending CN109934688A (en) | 2019-03-22 | 2019-03-22 | A kind of reference result determines method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109934688A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112215424A (en) * | 2020-10-16 | 2021-01-12 | 平安国际智慧城市科技股份有限公司 | Medical index prediction method, device, electronic equipment and storage medium |
| CN112581276A (en) * | 2020-12-24 | 2021-03-30 | 中国农业银行股份有限公司 | Data processing method and device |
| CN112598508A (en) * | 2020-12-28 | 2021-04-02 | 中国农业银行股份有限公司 | Credit investigation data use method and system |
| CN112613988A (en) * | 2020-12-31 | 2021-04-06 | 中国农业银行股份有限公司 | Method and device for generating credit investigation index information |
| CN113626415A (en) * | 2021-08-27 | 2021-11-09 | 天元大数据信用管理有限公司 | Credit data output method, device and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170140461A1 (en) * | 2014-03-05 | 2017-05-18 | Marc Abramowitz | System and method for generating a dynamic credit risk rating for a debt security |
| 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 |
| CN108830696A (en) * | 2018-07-02 | 2018-11-16 | 平安科技（深圳）有限公司 | Reference reports analyzing and processing method, device, computer equipment and storage medium |
| EP3274928A4 (en) * | 2015-03-27 | 2018-12-12 | Equifax, Inc. | Optimizing neural networks for risk assessment |
-
2019
- 2019-03-22 CN CN201910221721.8A patent/CN109934688A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170140461A1 (en) * | 2014-03-05 | 2017-05-18 | Marc Abramowitz | System and method for generating a dynamic credit risk rating for a debt security |
| EP3274928A4 (en) * | 2015-03-27 | 2018-12-12 | Equifax, Inc. | Optimizing neural networks for risk assessment |
| 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 |
| CN108830696A (en) * | 2018-07-02 | 2018-11-16 | 平安科技（深圳）有限公司 | Reference reports analyzing and processing method, device, computer equipment and storage medium |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112215424A (en) * | 2020-10-16 | 2021-01-12 | 平安国际智慧城市科技股份有限公司 | Medical index prediction method, device, electronic equipment and storage medium |
| CN112581276A (en) * | 2020-12-24 | 2021-03-30 | 中国农业银行股份有限公司 | Data processing method and device |
| CN112598508A (en) * | 2020-12-28 | 2021-04-02 | 中国农业银行股份有限公司 | Credit investigation data use method and system |
| CN112598508B (en) * | 2020-12-28 | 2024-01-19 | 中国农业银行股份有限公司 | Credit data use method and system |
| CN112613988A (en) * | 2020-12-31 | 2021-04-06 | 中国农业银行股份有限公司 | Method and device for generating credit investigation index information |
| CN113626415A (en) * | 2021-08-27 | 2021-11-09 | 天元大数据信用管理有限公司 | Credit data output method, device and medium |
| CN113626415B (en) * | 2021-08-27 | 2024-02-23 | 天元大数据信用管理有限公司 | Credit data output method, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109934688A (en) | A kind of reference result determines method and device | |
| US20210232608A1 (en) | Trust scores and/or competence ratings of any entity | |
| US20200162350A1 (en) | Distributed storage / computation network for automatic transaction initiation | |
| US20200252423A1 (en) | Systems and methods for vulnerability assessment and remedy identification | |
| US20130124393A1 (en) | Connecting decisions through customer transaction profiles | |
| WO2005022348A2 (en) | Application processing and decision systems and processes | |
| WO2010037030A1 (en) | Evaluating loan access using online business transaction data | |
| US8984022B1 (en) | Automating growth and evaluation of segmentation trees | |
| US20210287303A9 (en) | Scoring trustworthiness, competence, and/or compatibility of any entity for activities including recruiting or hiring decisions, composing a team, insurance underwriting, credit decisions, or shortening or improving sales cycles | |
| EP2545479A2 (en) | Methods, computer-accessible medium and systems for construction of and inference with networked data, for example, in a financial setting | |
| Kuzior et al. | Global digital convergence: Impact of cybersecurity, business transparency, economic transformation, and AML efficiency | |
| US20230116362A1 (en) | Scoring trustworthiness, competence, and/or compatibility of any entity for activities including recruiting or hiring decisions, composing a team, insurance underwriting, credit decisions, or shortening or improving sales cycles | |
| US20150302097A1 (en) | System for classifying characterized information | |
| Xu et al. | A hybrid interpretable credit card users default prediction model based on RIPPER | |
| CN107256231B (en) | Team member identification device, method and system | |
| US20080215988A1 (en) | System and method to process information contributed by members of a virtual community | |
| JP6437053B1 (en) | Calculation device, calculation method, calculation program, and model | |
| CN110619564B (en) | Anti-fraud feature generation method and device | |
| CN109598623A (en) | A kind of financial product future profits data predication method, apparatus and system | |
| US20130179324A1 (en) | Method, system, and program product for determining a value of an index | |
| CN112823502B (en) | Real-time feedback service for resource access rule configuration | |
| JP6531059B2 (en) | Business matching system and business matching method | |
| CN117611099A (en) | Money backwashing risk monitoring system and method | |
| CN109146132A (en) | Field miss rate method for early warning, server, storage medium and computer program | |
| CN115456764A (en) | Credit risk analysis method, device and related equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190625 |