CN114298823A - Data processing method and device for model construction - Google Patents
Data processing method and device for model construction Download PDFInfo
- Publication number
- CN114298823A CN114298823A CN202111628038.XA CN202111628038A CN114298823A CN 114298823 A CN114298823 A CN 114298823A CN 202111628038 A CN202111628038 A CN 202111628038A CN 114298823 A CN114298823 A CN 114298823A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- risk
- training
- credit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 25
- 238000010276 construction Methods 0.000 title claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 88
- 238000012502 risk assessment Methods 0.000 claims abstract description 45
- 238000013145 classification model Methods 0.000 claims abstract description 42
- 230000006399 behavior Effects 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000013136 deep learning model Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000011156 evaluation Methods 0.000 claims description 40
- 238000013210 evaluation model Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 4
- 238000012512 characterization method Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- 238000011002 quantification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
Images
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application discloses a data processing method and device for model construction. The method comprises the following steps: the critical refused user risk assessment method includes the steps of obtaining default classification models by training critical refused users and relevant data of users, conducting default classification processing on the relevant data of the critical refused users through the default classification models to obtain default classification label data, training a deep learning model according to critical refused user basic data, user lending behavior data and risk classification data corresponding to the critical refused users to obtain a salvage risk assessment model, carrying out salvage risk assessment on the critical refused user data through the salvage risk assessment model, quantifying the salvage risk of the critical refused users, matching appropriate credit granting strategies, solving the technical problem that the critical user risk in financial institutions in the prior art is difficult to quantitatively assess, and achieving the technical effects of improving accuracy and efficiency of credit granting to the critical users.
Description
Technical Field
The present application relates to the field of computers, and in particular, to a data processing method and apparatus for model building.
Background
In the prior art, with the gradual and strict financial service management of small loans on the internet, financial users are easily refused by mistake and cannot obtain services, and during credit granting evaluation, the early credit granting evaluation meets the requirements of a financial service company, but some users are critical, may be influenced by the environment and cannot obtain financial services, so that the user loss and the effective credit granting cost of a financial institution are increased.
Therefore, the trust evaluation in the prior art has the technical problem of low critical user risk quantification degree.
Disclosure of Invention
The application mainly aims to provide a data processing method and device for model construction, a salvage risk evaluation model is constructed to realize salvage risk evaluation of critical rejected users, and the technical problem that credit evaluation in the prior art is low in critical user risk quantification degree is solved.
In order to achieve the above object, the present application proposes a data processing method for model construction.
According to a second aspect of the present application, a data processing apparatus for model building is presented.
According to a third aspect of the present application, a computer-readable storage medium is presented.
According to a fourth aspect of the present application, an electronic device is presented.
In view of the above, according to a first aspect of the present application, there is provided a data processing method for model construction, including:
acquiring first training data, wherein the first training data comprises rejected training credit user data and passing training credit user data;
training a pre-established classification model based on the first training data to obtain a default risk classification model;
based on the default risk classification model, performing risk classification prediction on the training credit refused user data to obtain risk classification data;
training a pre-established deep learning model based on the training credit refused user data and the risk classification data to obtain a salvage risk assessment model so as to realize salvage risk assessment of the credit refused user.
Further, based on the first training data, training a pre-established classification model to obtain a default risk classification model, including:
identifying the first training data to obtain user equipment data and user risk default data;
based on a preset label generation rule, performing labeling processing on the user risk default data to obtain risk default label data;
and training the pre-established classification model based on the user equipment data and the risk default label data to obtain the default classification model.
Further, training a pre-established deep learning model based on the training credit refused user data and the risk classification data to obtain a salvage risk assessment model, comprising:
identifying the rejected user data to obtain user basic data and user lending behavior data, wherein the user basic data is age and occupation data provided when the user carries out credit granting evaluation, and the user lending behavior data is data generated when the user carries out lending behavior;
training a pre-established deep learning model based on the user basic data, the user lending behavior data and the risk classification data to obtain a process salvage risk evaluation model;
and carrying out verification iteration on the process salvage risk evaluation model based on preset conditions to obtain the salvage risk evaluation model.
Further, based on the default risk classification model, performing risk classification prediction on the training credit refused user data to obtain risk classification data, including:
identifying the rejected training credit user data to obtain user equipment data;
and performing risk classification prediction on the user equipment data based on the default risk classification model to obtain the risk classification data.
Further, after obtaining the salvage risk assessment model, the method further comprises the following steps:
acquiring user data to be evaluated within a preset time, wherein the user data to be evaluated is related data of a credit critical refused user, and the credit critical refused user is a refused user meeting a preset risk threshold of a credit large disk;
performing salvage risk assessment on the user data to be assessed based on the salvage risk model to obtain risk assessment data;
and matching credit strategy data corresponding to the risk evaluation data in a preset strategy database, and outputting credit evaluation result data, wherein the credit evaluation result data comprises the risk evaluation data and the credit strategy data.
Further, based on the bailing-back risk model, performing bailing-back risk assessment on the user data to be assessed to obtain risk assessment data, including:
identifying the user data to be evaluated to obtain user basic data and user loan behavior data of the user to be evaluated;
carrying out characterization processing on the user basic data and the user lending behavior data to obtain input characteristic data;
and performing salvage risk assessment on the input characteristic data based on the salvage risk model to obtain the risk assessment data.
According to a second aspect of the present application, a data processing apparatus for model building is presented, comprising:
the data acquisition module is used for acquiring first training data, wherein the first training data comprises rejected training credit user data and passed training credit user data;
the first model training module is used for training a pre-established classification model based on the first training data to obtain a default risk classification model;
the second model training module is used for carrying out risk classification prediction on the training credit refused user data based on the default risk classification model to obtain risk classification data;
training a pre-established deep learning model based on the training credit refused user data and the risk classification data to obtain a salvage risk assessment model so as to realize salvage risk assessment of the credit refused user.
Further, still include:
the data acquisition module is used for acquiring user data to be evaluated in preset time, wherein the user data to be evaluated is related data of a credit critical refused user, and the credit critical refused user is a refused user meeting a preset risk threshold of a credit large disk;
the salvage evaluation module is used for performing salvage risk evaluation on the user data to be evaluated based on the salvage risk evaluation model to obtain risk evaluation data;
and the result output module is used for matching credit granting strategy data corresponding to the risk evaluation data in a preset strategy database and outputting credit granting evaluation result data, wherein the credit granting evaluation result data comprises the risk evaluation data and the credit granting strategy data.
According to a third aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions for causing the computer to execute the above-mentioned data processing method for model construction.
According to a fourth aspect of the present application, there is provided an electronic apparatus, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to cause the at least one processor to perform the above-described data processing method for model building.
The technical scheme provided by the embodiment of the application can have the following beneficial effects:
in the application, a default classification model is obtained by training critical rejected users and relevant data of users, default classification processing is performed on the relevant data of the critical rejected users through the default classification model to obtain default classification label data, a deep learning model is trained according to critical rejected user basic data, user lending behavior data and risk classification data corresponding to the critical rejected users to obtain a salvage risk assessment model, the critical rejected user data is salvaged back to risk assessment through the salvage risk assessment model, the salvage risk of the critical rejected users is quantified, a proper credit granting strategy is matched, the technical problem that the critical user risk in a financial institution is difficult to quantitatively assess in the prior art is solved, and the technical effect of improving the accuracy and efficiency of credit granting for the critical users is achieved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:
FIG. 1 is a schematic flow chart of a data processing method for model building provided in the present application;
FIG. 2 is a schematic flow chart of a data processing method for model building provided in the present application;
FIG. 3 is a schematic flow chart of a data processing method for model building provided in the present application;
FIG. 4 is a schematic diagram of a data processing apparatus for model building according to the present application;
fig. 5 is a schematic structural diagram of another data processing apparatus for model building provided in the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In this application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings. These terms are used primarily to better describe the present application and its embodiments, and are not used to limit the indicated devices, elements or components to a particular orientation or to be constructed and operated in a particular orientation.
Moreover, some of the above terms may be used to indicate other meanings besides the orientation or positional relationship, for example, the term "on" may also be used to indicate some kind of attachment or connection relationship in some cases. The specific meaning of these terms in this application will be understood by those of ordinary skill in the art as appropriate.
Furthermore, the terms "mounted," "disposed," "provided," "connected," and "sleeved" are to be construed broadly. For example, "connected" may be a fixed connection, a detachable connection, or a unitary construction; can be a mechanical connection, or an electrical connection; may be directly connected, or indirectly connected through intervening media, or may be in internal communication between two devices, elements or components. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.
Fig. 1 is a schematic flowchart of a data processing method for model building provided in the present application, and as shown in fig. 1, the method includes the following steps:
s101: acquiring first training data, wherein the first training data comprises rejected training credit user data and passing training credit user data;
the method comprises the following steps that a credit granting rejected user is a credit granting critical rejected user, the credit granting critical rejected user is a rejected user meeting a preset risk threshold of a credit granting large disk, and if the rejected user has about three times of the credit granting large disk risk, both credit granting rejected user data and credit granting passing user data comprise: user equipment data, user risk default data, user basic data and user lending behavior data;
s102: training a pre-established classification model based on the first training data to obtain a default risk classification model;
fig. 2 is a schematic flowchart of a data processing method for model building provided in the present application, and as shown in fig. 2, the method includes the following steps:
s201: identifying the first training data to obtain user equipment data and user risk default data;
the user equipment data comprises equipment position data, active classification data, application list data and the like, the user position changes frequently, the loan APP is downloaded for multiple times, the user qualification is relatively poor, the risk is high, and credit granting evaluation is rejected; otherwise, the user qualification is relatively better, the risk is low, and the credit assessment is passed. For example, the number of times of installing application behaviors in approximately three months, the number of times of uninstalling applications in approximately three months, etc.;
the user risk default data comprises risk default data of a refused user of the credit and risk default data of the user of the credit, such as normal repayment, overdue amount, overdue time and the like.
S202: based on a preset label generation rule, performing labeling processing on the user risk default data to obtain risk default label data;
labeling the user risk default data, comprising: the method comprises the following steps that a user is refused to give credit, if the user is refused to give credit, the user has liabilities, and if the user is refused to give credit, the user has repayment behaviors within a period of time, the repayment behaviors are observed, if normal repayment is defined as a good user, and if overdue is defined as a bad user; the second type is that the credit is passed through the user, the repayment behavior after payment is passed is observed, if the repayment is normal, the user is defined as a good user, and if the repayment is overdue, the user is defined as a bad user.
S203: and training the pre-established classification model based on the user equipment data and the risk default label data to obtain the default classification model.
And training a classification model by taking the user equipment data as an input variable and the risk default label data as a target variable, wherein the classification model can be a decision tree model to obtain a default classification model.
S103: based on the default risk classification model, performing risk classification prediction on the training credit refused user data to obtain risk classification data;
selecting the data of the trusted and refused user, comprising the following steps: data related to users with liabilities when the credit is refused and users without liabilities when the credit is refused;
identifying the rejected training credit user data to obtain user equipment data;
and performing risk classification prediction on the user equipment data based on the default risk classification model to obtain the risk classification data.
S104: training a pre-established deep learning model based on the training credit refused user data and the risk classification data to obtain a salvage risk assessment model so as to realize salvage risk assessment of the credit refused user.
Identifying the rejected user data to obtain user basic data and user loan behavior data, wherein the user basic data is data provided when the user performs credit assessment, such as data of age, occupation, academic calendar and the like; the user lending behavior data is data generated when the user lending behavior occurs, such as lending amount, lending duration, lending times and the like;
training a pre-established deep learning model based on the user basic data, the user lending behavior data and the risk classification data to obtain a process salvage risk evaluation model;
and carrying out verification iteration on the process salvage risk evaluation model based on preset conditions to obtain the salvage risk evaluation model.
And (3) training a deep learning model by taking the user basic data and the user lending behavior data as input variables and the risk classification data as target variables, wherein the deep learning model can be an XGboost model, and the deep learning model is trained to obtain a salvage risk evaluation model.
Fig. 3 is a schematic flowchart of a data processing method for model building according to the present application, and as shown in fig. 3, the method further includes the following steps:
s301: acquiring user data to be evaluated within a preset time, wherein the user data to be evaluated is related data of a credit critical refused user, and the credit critical refused user is a refused user meeting a preset risk threshold of a credit large disk;
s302: performing salvage risk assessment on the user data to be assessed based on the salvage risk model to obtain risk assessment data;
identifying the user data to be evaluated to obtain user basic data and user loan behavior data of the user to be evaluated;
carrying out characterization processing on the user basic data and the user lending behavior data to obtain input characteristic data;
and performing salvage risk assessment on the input characteristic data based on the salvage risk model to obtain the risk assessment data.
S303: and matching credit strategy data corresponding to the risk evaluation data in a preset strategy database, and outputting credit evaluation result data, wherein the credit evaluation result data comprises the risk evaluation data and the credit strategy data.
For example, if the number of users in a month is more than 16 and the prediction result of the bailing-back risk assessment model is higher than the bailing-back critical value by 0.3, the credit assessment result is output as a rejection; when the number of users in the last month is more than 16 and less than 20 and the prediction result of the bailing-back risk evaluation model is lower than the bailing-back critical value by 0.3, outputting the credit evaluation result as credit, wherein the amount of the credit is 1500; when the number of users in the last month is more than 10 and less than 16 and the prediction result of the salvage risk evaluation model is lower than the salvage critical value by 0.3, outputting the credit evaluation result as credit, wherein the amount of the credit is 2000; when the number of users in the last month is less than 10 and the prediction result of the bailing-back risk evaluation model is less than 0.1, the credit evaluation result is output as credit, and the amount of the credit is 5000.
Fig. 4 is a schematic structural diagram of a data processing apparatus for model building provided in the present application, and as shown in fig. 4, the apparatus includes:
a data obtaining module 41, configured to obtain first training data, where the first training data includes rejected training credit user data and passing training credit user data;
a first model training module 42, which trains a pre-established classification model based on the first training data to obtain a default risk classification model;
a second model training module 43, which performs risk classification prediction on the training credit denied user data based on the default risk classification model to obtain risk classification data;
training a pre-established deep learning model based on the training credit refused user data and the risk classification data to obtain a salvage risk assessment model so as to realize salvage risk assessment of the credit refused user.
Fig. 5 is a schematic structural diagram of another data processing apparatus for model building provided in the present application, and as shown in fig. 5, the apparatus includes:
the data acquisition module 51 is configured to acquire user data to be evaluated within a preset time, where the user data to be evaluated is related to a critical refused user for credit granting, and the critical refused user for credit granting is a refused user meeting a preset risk threshold of a credit granting large disk;
a salvage evaluation module 52, which performs salvage risk evaluation on the user data to be evaluated based on the salvage risk evaluation model to obtain risk evaluation data;
and a result output module 53, configured to match trust policy data corresponding to the risk assessment data in a preset policy database, and output trust assessment result data, where the trust assessment result data includes the risk assessment data and the trust policy data.
Specifically, the specific process of implementing the functions of each unit and module in the device in the embodiment of the present application may refer to the related description in the method embodiment, and is not described herein again.
According to an embodiment of the present application, there is further provided a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions for causing the computer to execute the data processing method for model building in the above method embodiment.
According to an embodiment of the present application, there is also provided an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to cause the at least one processor to perform the data processing method for model building in the above method embodiments.
In summary, in the application, a default classification model is obtained by training critical rejected users and relevant data of users, default classification processing is performed on the relevant data of the critical rejected users through the default classification model to obtain default classification label data, a salvage risk assessment model is obtained by training a deep learning model according to critical rejected user basic data, user loan behavior data and risk classification data corresponding to the critical rejected users, the salvage risk assessment model is used for performing salvage risk assessment on the critical rejected user data, the salvage risk of the critical rejected users is quantified, and a proper credit granting strategy is matched, so that the technical problem that the critical user risk in a financial institution is difficult to quantify and assess in the prior art is solved, and the technical effects of improving the accuracy and efficiency of credit granting for the critical users are achieved.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
It will be apparent to those skilled in the art that the various elements or steps of the present application described above may be implemented by a general purpose computing device, centralized on a single computing device or distributed across a network of multiple computing devices, or alternatively, may be implemented by program code executable by a computing device, such that the program code may be stored in a memory device and executed by a computing device, or may be implemented by individual integrated circuit modules, or by a plurality of modules or steps included in the program code as a single integrated circuit module. Thus, the present application is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A data processing method for model building, comprising:
acquiring first training data, wherein the first training data comprises rejected training credit user data and passing training credit user data;
training a pre-established classification model based on the first training data to obtain a default risk classification model;
based on the default risk classification model, performing risk classification prediction on the training credit refused user data to obtain risk classification data;
training a pre-established deep learning model based on the training credit refused user data and the risk classification data to obtain a salvage risk assessment model so as to realize salvage risk assessment of the credit refused user.
2. The data processing method of claim 1, wherein training a pre-established classification model based on the first training data to obtain a default risk classification model comprises:
identifying the first training data to obtain user equipment data and user risk default data;
based on a preset label generation rule, performing labeling processing on the user risk default data to obtain risk default label data;
and training the pre-established classification model based on the user equipment data and the risk default label data to obtain the default classification model.
3. The data processing method of claim 1, wherein training a pre-established deep learning model based on the training credit denied user data and the risk classification data to obtain a salvage risk assessment model comprises:
identifying the rejected user data to obtain user basic data and user loan behavior data, wherein the user basic data is data provided when the user performs credit granting evaluation, and the user loan behavior data is data generated when the user performs loan behavior;
training a pre-established deep learning model based on the user basic data, the user lending behavior data and the risk classification data to obtain a process salvage risk evaluation model;
and carrying out verification iteration on the process salvage risk evaluation model based on preset conditions to obtain the salvage risk evaluation model.
4. The data processing method of claim 1, wherein performing risk classification prediction on the training credit denied user data based on the default risk classification model to obtain risk classification data comprises:
identifying the rejected training credit user data to obtain user equipment data;
and performing risk classification prediction on the user equipment data based on the default risk classification model to obtain the risk classification data.
5. The data processing method of claim 1, further comprising, after obtaining the bailed-back risk assessment model:
acquiring user data to be evaluated within a preset time, wherein the user data to be evaluated is related data of a credit critical refused user, and the credit critical refused user is a refused user meeting a preset risk threshold of a credit large disk;
performing salvage risk assessment on the user data to be assessed based on the salvage risk model to obtain risk assessment data;
and matching credit strategy data corresponding to the risk evaluation data in a preset strategy database, and outputting credit evaluation result data, wherein the credit evaluation result data comprises the risk evaluation data and the credit strategy data.
6. The data processing method of claim 5, wherein performing salvage risk assessment on the user data to be assessed based on the salvage risk model to obtain risk assessment data comprises:
identifying the user data to be evaluated to obtain user basic data and user loan behavior data of the user to be evaluated;
carrying out characterization processing on the user basic data and the user lending behavior data to obtain input characteristic data;
and performing salvage risk assessment on the input characteristic data based on the salvage risk model to obtain the risk assessment data.
7. A data processing apparatus for model building, comprising:
the data acquisition module is used for acquiring first training data, wherein the first training data comprises rejected training credit user data and passed training credit user data;
the first model training module is used for training a pre-established classification model based on the first training data to obtain a default risk classification model;
the second model training module is used for carrying out risk classification prediction on the training credit refused user data based on the default risk classification model to obtain risk classification data;
training a pre-established deep learning model based on the training credit refused user data and the risk classification data to obtain a salvage risk assessment model so as to realize salvage risk assessment of the credit refused user.
8. The data processing apparatus of claim 7, further comprising:
the data acquisition module is used for acquiring user data to be evaluated in preset time, wherein the user data to be evaluated is related data of a credit critical refused user, and the credit critical refused user is a refused user meeting a preset risk threshold of a credit large disk;
the salvage evaluation module is used for performing salvage risk evaluation on the user data to be evaluated based on the salvage risk evaluation model to obtain risk evaluation data;
and the result output module is used for matching credit granting strategy data corresponding to the risk evaluation data in a preset strategy database and outputting credit granting evaluation result data, wherein the credit granting evaluation result data comprises the risk evaluation data and the credit granting strategy data.
9. A computer-readable storage medium storing computer instructions for causing a computer to execute the data processing method for model construction according to any one of claims 1 to 6.
10. An electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to cause the at least one processor to perform the data processing method for model building of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111628038.XA CN114298823A (en) | 2021-12-28 | 2021-12-28 | Data processing method and device for model construction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111628038.XA CN114298823A (en) | 2021-12-28 | 2021-12-28 | Data processing method and device for model construction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114298823A true CN114298823A (en) | 2022-04-08 |
Family
ID=80971555
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111628038.XA Pending CN114298823A (en) | 2021-12-28 | 2021-12-28 | Data processing method and device for model construction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114298823A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114880637A (en) * | 2022-07-07 | 2022-08-09 | 深圳竹云科技股份有限公司 | Account risk verification method and device, computer equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110706096A (en) * | 2019-09-30 | 2020-01-17 | 上海淇玥信息技术有限公司 | Method and device for managing credit line based on salvage-back user and electronic equipment |
| CN112488817A (en) * | 2020-10-21 | 2021-03-12 | 上海旻浦科技有限公司 | Financial default risk assessment method and system based on refusal inference |
| CN112529481A (en) * | 2021-02-08 | 2021-03-19 | 北京淇瑀信息科技有限公司 | User fishing-back method and device and electronic equipment |
-
2021
- 2021-12-28 CN CN202111628038.XA patent/CN114298823A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110706096A (en) * | 2019-09-30 | 2020-01-17 | 上海淇玥信息技术有限公司 | Method and device for managing credit line based on salvage-back user and electronic equipment |
| CN112488817A (en) * | 2020-10-21 | 2021-03-12 | 上海旻浦科技有限公司 | Financial default risk assessment method and system based on refusal inference |
| CN112529481A (en) * | 2021-02-08 | 2021-03-19 | 北京淇瑀信息科技有限公司 | User fishing-back method and device and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114880637A (en) * | 2022-07-07 | 2022-08-09 | 深圳竹云科技股份有限公司 | Account risk verification method and device, computer equipment and storage medium |
| CN114880637B (en) * | 2022-07-07 | 2022-09-20 | 深圳竹云科技股份有限公司 | Account risk verification method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200210899A1 (en) | Machine learning model training method and device, and electronic device | |
| Koene et al. | A governance framework for algorithmic accountability and transparency | |
| Kleinberg et al. | Algorithmic monoculture and social welfare | |
| Harrison et al. | Evaluating the expected welfare gain from insurance | |
| US20180308160A1 (en) | Risk assessment method and system | |
| US10445496B2 (en) | Product risk profile | |
| EP3543922B1 (en) | Method and device for identifying risk of service to be processed and electronic device | |
| US20210035224A1 (en) | Applying Telematics to Generate Dynamic Insurance Premiums | |
| US20210073915A1 (en) | Event-driven natural catastrophe modeling and model refinement for insurance and risk management | |
| Bahrami et al. | Using behavioral analytics to predict customer invoice payment | |
| CN108876188B (en) | Inter-connected service provider risk assessment method and device | |
| CN104965844A (en) | Information processing method and apparatus | |
| CN110503564B (en) | Security case processing method, system, equipment and storage medium based on big data | |
| US20190303781A1 (en) | System and method for implementing a trust discretionary distribution tool | |
| CN111179051A (en) | Financial target customer determination method and device and electronic equipment | |
| CN110414989A (en) | Method for detecting abnormality and device, electronic equipment and computer readable storage medium | |
| CN114298823A (en) | Data processing method and device for model construction | |
| CN115203496A (en) | Project intelligent prediction and evaluation method and system based on big data and readable storage medium | |
| Achille et al. | AI model disgorgement: Methods and choices | |
| CN110689425A (en) | Method and device for pricing quota based on income and electronic equipment | |
| WO2022015488A1 (en) | Event-driven model refinement for insurance and risk management | |
| CN114298829A (en) | Data processing method and device for credit assessment | |
| US11514187B1 (en) | Systems and methods for managing the processing of customer information within a global enterprise | |
| CN111612366A (en) | Channel quality evaluation method and device, electronic equipment and storage medium | |
| CN109919414A (en) | P2P network loan platform risk analysis method, device and storage medium |
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 |