CN112488822A - Cooperation risk preference-based guest group distribution method and system - Google Patents
Cooperation risk preference-based guest group distribution method and system Download PDFInfo
- Publication number
- CN112488822A CN112488822A CN202011408427.7A CN202011408427A CN112488822A CN 112488822 A CN112488822 A CN 112488822A CN 202011408427 A CN202011408427 A CN 202011408427A CN 112488822 A CN112488822 A CN 112488822A
- Authority
- CN
- China
- Prior art keywords
- customer
- early warning
- model
- risk
- monitoring
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012544 monitoring process Methods 0.000 claims abstract description 48
- 238000004458 analytical method Methods 0.000 claims description 18
- 238000011161 development Methods 0.000 claims description 18
- 230000010354 integration Effects 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 16
- 230000007246 mechanism Effects 0.000 abstract description 12
- 238000011835 investigation Methods 0.000 description 20
- 238000010586 diagram Methods 0.000 description 6
- 238000012795 verification Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000010365 information processing Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a method and a system for distributing guest groups based on partner risk preference, wherein the method comprises the following steps: integrating internal and external data through a risk score rating model to obtain a uniform risk score rating of a customer; based on the preferences of different partners on the client risks, distributing the client groups according to the default rate level after the risk score rating prediction; and monitoring the distributed guest groups in real time. The invention can distinguish corresponding guest groups according to the risk preferences of different sponsors and establish a prospective, stable and flexible flow distribution mechanism based on the risk application experience.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a system for distributing a guest group based on partner risk preference.
Background
At present, when the existing passenger group flow distribution platform realizes passenger group distribution, most of the existing passenger group flow distribution platform only needs simple flow distribution according to the requirements of the sponsors, and the passenger groups are not distinguished according to the risk preferences of different sponsors; in addition, most of the customers are matched according to the fixed rules of the partner, and the customer groups cannot be flexibly and quickly screened and distributed.
Therefore, how to distinguish the corresponding customer groups according to the risk preferences of different sponsors and how to establish a prospective, stable and flexible traffic distribution mechanism is a problem to be solved urgently.
Disclosure of Invention
In view of the above, the present invention provides a method for distributing guest groups based on partner risk preferences, which can distinguish corresponding guest groups according to risk preferences of different parties, and establish a prospective, stable and flexible traffic distribution mechanism based on risk application experience.
The invention provides a partner risk preference-based guest group distribution method, which comprises the following steps:
integrating internal and external data through a risk score rating model to obtain a uniform risk score rating of a customer;
based on the preferences of different partners on the client risks, distributing the client groups according to the default rate level after the risk score rating prediction;
and monitoring the distributed guest groups in real time.
Preferably, the method further comprises:
a rules/model management platform is developed.
Preferably, the development rule/model management platform comprises:
analyzing different dimensions of the set early warning rules and models;
and carrying out configuration management on the rules/models.
Preferably, the method further comprises:
and developing an early warning management platform.
Preferably, the developing an early warning management platform includes:
monitoring and early warning the model;
distributing the early warning information;
and processing the early warning information.
A system for tenant distribution based on partner risk preferences, comprising:
the integration module is used for integrating internal and external data through a risk score rating model to obtain a uniform risk score rating of a customer;
the distribution module is used for distributing the customer groups according to the default rate level after the risk grading prediction based on the preferences of different partners on the customer risk;
and the monitoring module is used for monitoring the distributed guest groups in real time.
Preferably, the system further comprises:
and the first development module is used for developing a rule/model management platform.
Preferably, the first development module includes:
the analysis unit is used for analyzing different dimensions of the set early warning rules and models;
and the management unit is used for carrying out configuration management on the rules/models.
Preferably, the system further comprises:
and the second development module is used for developing an early warning management platform.
Preferably, the second development module includes:
the monitoring and early warning unit is used for monitoring and early warning the model;
the dispatching unit is used for dispatching the early warning information;
and the processing unit is used for processing the early warning information.
In summary, the invention discloses a partner risk preference-based customer group distribution method, which includes integrating internal and external data through a risk score rating model to obtain a uniform risk score rating of a customer; then based on the preferences of different partners on the client risks, distributing the client groups according to the default rate level after the risk score rating prediction; and monitoring the distributed guest groups in real time. The invention can distinguish corresponding guest groups according to the risk preferences of different sponsors and establish a prospective, stable and flexible flow distribution mechanism based on the risk application experience.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flowchart of an embodiment 1 of a method for distributing a group of guests based on partner risk preferences, according to the present disclosure;
FIG. 2 is a flowchart of an embodiment 2 of a method for distributing a group of guests based on partner risk preferences, according to the present disclosure;
FIG. 3 is a flowchart of an embodiment 3 of a method for distributing customers based on partner risk preferences, according to the present disclosure;
FIG. 4 is a schematic structural diagram of an embodiment 1 of a partner risk preference-based guest group distribution system disclosed in the present invention;
FIG. 5 is a schematic structural diagram of an embodiment 2 of a partner risk preference-based guest group distribution system disclosed in the present invention;
fig. 6 is a schematic structural diagram of an embodiment 3 of a partner risk preference-based guest group distribution system disclosed in the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.
As shown in fig. 1, which is a flowchart of an embodiment 1 of a method for distributing a guest group based on a partner risk preference, the method may include the following steps:
s101, integrating internal and external data through a risk score rating model to obtain a uniform risk score rating of a customer;
when a customer group needs to be distributed, internal and external data are integrated through a risk scoring rating model to form a uniform risk scoring rating of a customer.
The integral credit granting condition and risk exposure of the customer in the bank are shown through the unified grading of the risk score of the customer, and directly or indirectly related risk factors of the customer can be revealed through the asset condition of the customer, the relationship between the customer and the related person and the related enterprise. The specific implementation scheme is that a data platform is accessed into a service system such as a unified customer center system, a three-party credit investigation system (external data), a combined loan system, an on-line loan system, a comprehensive credit system and the like, a customer identity number in the three-party credit investigation system is associated through a customer identity number provided by the unified customer center, the customer number of the unified customer center is taken as a unique identifier of a customer of the three-party credit investigation system, the customer basic information table of the core customer number associated with the on-line loan, the combined loan and the comprehensive credit system provided by the unified customer center is used for integrating information of the three systems such as application information, five-level classification condition, credit granting information, credit contract, borrowing data information, loan, repayment and the like of a source system customer through the customer number in the system in the table, and the customer number of the unified customer center is taken as the unique identifier of the customer after integration, the integration of internal and external data is realized through the unique identification, and the uniform risk scoring rating model of the customer is formed by using the variables to enter the model.
S102, distributing the customer groups according to the default rate level after the risk grading prediction based on the preferences of different partners on the customer risk;
and then, based on the risk rating model, predicting the default rate level under the rating according to the risk rating of the client predicted by the historical pre-loan rating model, and pushing the client group to the corresponding cooperative business according to different default rate levels of the client.
And S103, monitoring the distributed guest groups in real time.
After the guest group is pushed to the corresponding cooperation bank, the real-time performance condition of the distributed guest group can be further monitored.
In summary, in the above embodiments, when a customer group needs to be distributed, internal and external data are integrated through a risk score rating model to obtain a uniform risk score rating of a customer; then based on the preferences of different partners on the client risks, distributing the client groups according to the default rate level after the risk score rating prediction; and monitoring the distributed guest groups in real time. The method can distinguish corresponding guest groups according to risk preferences of different sponsors, and establish a prospective, stable and flexible traffic distribution mechanism based on risk application experience.
As shown in fig. 2, which is a flowchart of an embodiment 2 of the method for distributing a guest group based on a partner risk preference according to the present invention, the method may include the following steps:
s201, integrating internal and external data through a risk score rating model to obtain a uniform risk score rating of a customer;
when a customer group needs to be distributed, internal and external data are integrated through a risk scoring rating model to form a uniform risk scoring rating of a customer.
The integral credit granting condition and risk exposure of the customer in the bank are shown through the unified grading of the risk score of the customer, and directly or indirectly related risk factors of the customer can be revealed through the asset condition of the customer, the relationship between the customer and the related person and the related enterprise. The specific implementation scheme is that a data platform is accessed into a service system such as a unified customer center system, a three-party credit investigation system (external data), a combined loan system, an on-line loan system, a comprehensive credit system and the like, a customer identity number in the three-party credit investigation system is associated through a customer identity number provided by the unified customer center, the customer number of the unified customer center is taken as a unique identifier of a customer of the three-party credit investigation system, the customer basic information table of the core customer number associated with the on-line loan, the combined loan and the comprehensive credit system provided by the unified customer center is used for integrating information of the three systems such as application information, five-level classification condition, credit granting information, credit contract, borrowing data information, loan, repayment and the like of a source system customer through the customer number in the system in the table, and the customer number of the unified customer center is taken as the unique identifier of the customer after integration, the integration of internal and external data is realized through the unique identification, and the uniform risk scoring rating model of the customer is formed by using the variables to enter the model.
S202, based on the preferences of different partners on the risk of the client, distributing the client group according to the default rate level after the risk score rating prediction;
and then, based on the risk rating model, predicting the default rate level under the rating according to the risk rating of the client predicted by the historical pre-loan rating model, and pushing the client group to the corresponding cooperative business according to different default rate levels of the client.
S203, monitoring the distributed guest groups in real time;
after the guest group is pushed to the corresponding cooperation bank, the real-time performance condition of the distributed guest group can be further monitored.
S204, developing a rule/model management platform;
a rule/model management platform can be further developed, and the rule/model management platform comprises rule/model analysis and rule/model configuration management. Can be realized by JAVA development.
And S205, developing an early warning management platform.
And an early warning management platform can be further developed, and the early warning management platform comprises model monitoring early warning, early warning information distribution and early warning information processing.
In summary, in this embodiment, based on the above embodiments, a rule/model management platform and a development early warning management platform may be further developed, so that business personnel can flexibly configure an early warning rule/model as needed through a rule/model distribution mechanism.
As shown in fig. 3, which is a flowchart of embodiment 3 of the method for distributing guest groups based on partner risk preference according to the present invention, the method may include the following steps:
s301, integrating internal and external data through a risk score rating model to obtain a uniform risk score rating of a customer;
when a customer group needs to be distributed, internal and external data are integrated through a risk scoring rating model to form a uniform risk scoring rating of a customer.
The integral credit granting condition and risk exposure of the customer in the bank are shown through the unified grading of the risk score of the customer, and directly or indirectly related risk factors of the customer can be revealed through the asset condition of the customer, the relationship between the customer and the related person and the related enterprise. The specific implementation scheme is that a data platform is accessed into a service system such as a unified customer center system, a three-party credit investigation system (external data), a combined loan system, an on-line loan system, a comprehensive credit system and the like, a customer identity number in the three-party credit investigation system is associated through a customer identity number provided by the unified customer center, the customer number of the unified customer center is taken as a unique identifier of a customer of the three-party credit investigation system, the customer basic information table of the core customer number associated with the on-line loan, the combined loan and the comprehensive credit system provided by the unified customer center is used for integrating information of the three systems such as application information, five-level classification condition, credit granting information, credit contract, borrowing data information, loan, repayment and the like of a source system customer through the customer number in the system in the table, and the customer number of the unified customer center is taken as the unique identifier of the customer after integration, the integration of internal and external data is realized through the unique identification, and the uniform risk scoring rating model of the customer is formed by using the variables to enter the model.
S302, based on the preferences of different partners on the risk of the client, distributing the client group according to the default rate level after the risk score rating prediction;
and then, based on the risk rating model, predicting the default rate level under the rating according to the risk rating of the client predicted by the historical pre-loan rating model, and pushing the client group to the corresponding cooperative business according to different default rate levels of the client.
S303, monitoring the distributed guest groups in real time;
after the guest group is pushed to the corresponding cooperation bank, the real-time performance condition of the distributed guest group can be further monitored.
S304, analyzing different dimensions of the set early warning rules and models;
a rule/model management platform can be further developed, and the rule/model management platform comprises rule/model analysis and rule/model configuration management. Can be realized by JAVA development.
Specifically, different dimensionality analyses are performed on the set early warning rules and models.
S305, carrying out configuration management on the rules/models;
the basis of risk monitoring is to effectively manage and maintain a monitoring model, and the main functions of model configuration comprise:
(1) the model is newly built, namely basic information of the model is configured, wherein the basic information comprises model basic information, data acquisition sources, early warning and verification information and the like;
(2) model modification, which can flexibly modify parameter values of a monitoring model, basic information of the model and the like;
(3) the method comprises the following steps of model verification, wherein a predefined model is operated, a risk early warning and checking tool is used for verifying a model result, and the correctness of the model, the practicability of the model and the like are demonstrated;
(4) releasing the model, wherein the model is released after the model configuration is completed;
(5) configuring model authority, and setting the management authority of the model;
(6) and (4) deactivating the model, and closing and deactivating the model which is not applicable any more.
S306, monitoring and early warning the model;
and an early warning management platform can be further developed, and the early warning management platform comprises model monitoring early warning, early warning information distribution and early warning information processing.
Specifically, the monitoring model automatically analyzes the operation frequency of the monitoring model at regular time according to the day, week, month, quarter, half year, year and the like, and the background data analysis engine automatically analyzes and calculates according to the rule and the operation frequency preset by the early warning model. After the operation is finished, the system automatically stores the operation result into a system data mart, simultaneously automatically distributes clues to related personnel according to a system clue distribution strategy, and after the related personnel receive a clue task, the related personnel carry out investigation analysis and fact confirmation through a checking tool, if the problem exists, the related personnel enter a problem management and risk assessment platform to carry out problem rectification tracking and accountability.
S307, distributing the early warning information;
the system supports two modes of automatic clue distribution and manual clue distribution, and the clue distribution strategy can be automatically set to be distributed according to models, mechanisms, service types, models and mechanisms, models and service types and the like according to the requirements in the row.
The system supports multi-channel information distribution of the early warning information, and comprises various modes such as WEB, short message, mail, telephone notification and the like.
And S308, processing the early warning information.
After each early warning model is operated, a series of early warning clues are generated, related personnel need to analyze and judge the early warning clues, corresponding subsequent processing is executed, and early warning tasks are divided into unprocessed, processed and processed according to processing states.
Related personnel can check the number of the untreated early warning models and the number of the treated early warning models under the early warning models treated by the online cables, the details of the early warning cables and the untreated early warning model cables can be treated. After the early warning inquiry and verification task is issued, the early warning clue state is changed from unprocessed to processed. Meanwhile, the processing state of the early warning model can be checked in early warning monitoring processing. Specifically, a soft BI tool self-help instrument panel function can be adopted, so that business analysis personnel can perform self-help analysis in a dragging and pulling mode.
In conclusion, the method and the system can integrate internal and external data related to risks to form a unified pre-loan risk score rating for the customer; risk business personnel can flexibly configure early warning rules/models as required through a risk data mart/intelligent monitoring platform; can satisfy the user through holding in the palm and draw through intelligent monitoring and draw nimble, carry out the analysis fast, real-time adjustment model and strategy performance.
As shown in fig. 4, which is a schematic structural diagram of an embodiment 1 of a partner risk preference-based guest group distribution system disclosed in the present invention, the system may include:
the integration module 401 is configured to integrate internal and external data through a risk score rating model to obtain a uniform risk score rating of a customer;
when a customer group needs to be distributed, internal and external data are integrated through a risk scoring rating model to form a uniform risk scoring rating of a customer.
The integral credit granting condition and risk exposure of the customer in the bank are shown through the unified grading of the risk score of the customer, and directly or indirectly related risk factors of the customer can be revealed through the asset condition of the customer, the relationship between the customer and the related person and the related enterprise. The specific implementation scheme is that a data platform is accessed into a service system such as a unified customer center system, a three-party credit investigation system (external data), a combined loan system, an on-line loan system, a comprehensive credit system and the like, a customer identity number in the three-party credit investigation system is associated through a customer identity number provided by the unified customer center, the customer number of the unified customer center is taken as a unique identifier of a customer of the three-party credit investigation system, the customer basic information table of the core customer number associated with the on-line loan, the combined loan and the comprehensive credit system provided by the unified customer center is used for integrating information of the three systems such as application information, five-level classification condition, credit granting information, credit contract, borrowing data information, loan, repayment and the like of a source system customer through the customer number in the system in the table, and the customer number of the unified customer center is taken as the unique identifier of the customer after integration, the integration of internal and external data is realized through the unique identification, and the uniform risk scoring rating model of the customer is formed by using the variables to enter the model.
A distribution module 402, configured to distribute, based on preferences of different partners on the client risk, the client group according to the level of default rate predicted by the risk score rating;
and then, based on the risk rating model, predicting the default rate level under the rating according to the risk rating of the client predicted by the historical pre-loan rating model, and pushing the client group to the corresponding cooperative business according to different default rate levels of the client.
And a monitoring module 403, configured to perform real-time monitoring on the distributed guest groups.
After the guest group is pushed to the corresponding cooperation bank, the real-time performance condition of the distributed guest group can be further monitored.
In summary, in the above embodiments, when a customer group needs to be distributed, internal and external data are integrated through a risk score rating model to obtain a uniform risk score rating of a customer; then based on the preferences of different partners on the client risks, distributing the client groups according to the default rate level after the risk score rating prediction; and monitoring the distributed guest groups in real time. The method can distinguish corresponding guest groups according to risk preferences of different sponsors, and establish a prospective, stable and flexible traffic distribution mechanism based on risk application experience.
As shown in fig. 5, which is a schematic structural diagram of an embodiment 2 of a partner risk preference-based guest group distribution system disclosed in the present invention, the system may include:
the integration module 501 is configured to integrate internal and external data through a risk score rating model to obtain a uniform risk score rating of a customer;
when a customer group needs to be distributed, internal and external data are integrated through a risk scoring rating model to form a uniform risk scoring rating of a customer.
The integral credit granting condition and risk exposure of the customer in the bank are shown through the unified grading of the risk score of the customer, and directly or indirectly related risk factors of the customer can be revealed through the asset condition of the customer, the relationship between the customer and the related person and the related enterprise. The specific implementation scheme is that a data platform is accessed into a service system such as a unified customer center system, a three-party credit investigation system (external data), a combined loan system, an on-line loan system, a comprehensive credit system and the like, a customer identity number in the three-party credit investigation system is associated through a customer identity number provided by the unified customer center, the customer number of the unified customer center is taken as a unique identifier of a customer of the three-party credit investigation system, the customer basic information table of the core customer number associated with the on-line loan, the combined loan and the comprehensive credit system provided by the unified customer center is used for integrating information of the three systems such as application information, five-level classification condition, credit granting information, credit contract, borrowing data information, loan, repayment and the like of a source system customer through the customer number in the system in the table, and the customer number of the unified customer center is taken as the unique identifier of the customer after integration, the integration of internal and external data is realized through the unique identification, and the uniform risk scoring rating model of the customer is formed by using the variables to enter the model.
A distribution module 502, configured to distribute, based on preferences of different partners on the client risk, the client group according to the level of default rate predicted by the risk score rating;
and then, based on the risk rating model, predicting the default rate level under the rating according to the risk rating of the client predicted by the historical pre-loan rating model, and pushing the client group to the corresponding cooperative business according to different default rate levels of the client.
A monitoring module 503, configured to perform real-time monitoring on the distributed guest groups;
after the guest group is pushed to the corresponding cooperation bank, the real-time performance condition of the distributed guest group can be further monitored.
A first development module 504 for developing a rule/model management platform;
a rule/model management platform can be further developed, and the rule/model management platform comprises rule/model analysis and rule/model configuration management. Can be realized by JAVA development.
And a second development module 505, configured to develop an early warning management platform.
And an early warning management platform can be further developed, and the early warning management platform comprises model monitoring early warning, early warning information distribution and early warning information processing.
In summary, in this embodiment, based on the above embodiments, a rule/model management platform and a development early warning management platform may be further developed, so that business personnel can flexibly configure an early warning rule/model as needed through a rule/model distribution mechanism.
As shown in fig. 6, which is a schematic structural diagram of an embodiment 3 of a partner risk preference-based guest group distribution system disclosed in the present invention, the system may include:
the integration module 601 is used for integrating internal and external data through a risk score rating model to obtain a uniform risk score rating of a customer;
when a customer group needs to be distributed, internal and external data are integrated through a risk scoring rating model to form a uniform risk scoring rating of a customer.
The integral credit granting condition and risk exposure of the customer in the bank are shown through the unified grading of the risk score of the customer, and directly or indirectly related risk factors of the customer can be revealed through the asset condition of the customer, the relationship between the customer and the related person and the related enterprise. The specific implementation scheme is that a data platform is accessed into a service system such as a unified customer center system, a three-party credit investigation system (external data), a combined loan system, an on-line loan system, a comprehensive credit system and the like, a customer identity number in the three-party credit investigation system is associated through a customer identity number provided by the unified customer center, the customer number of the unified customer center is taken as a unique identifier of a customer of the three-party credit investigation system, the customer basic information table of the core customer number associated with the on-line loan, the combined loan and the comprehensive credit system provided by the unified customer center is used for integrating information of the three systems such as application information, five-level classification condition, credit granting information, credit contract, borrowing data information, loan, repayment and the like of a source system customer through the customer number in the system in the table, and the customer number of the unified customer center is taken as the unique identifier of the customer after integration, the integration of internal and external data is realized through the unique identification, and the uniform risk scoring rating model of the customer is formed by using the variables to enter the model.
A distribution module 602, configured to distribute, based on preferences of different partners on the risk of the customer, the customer base according to the level of default rate predicted by the risk score rating;
and then, based on the risk rating model, predicting the default rate level under the rating according to the risk rating of the client predicted by the historical pre-loan rating model, and pushing the client group to the corresponding cooperative business according to different default rate levels of the client.
A monitoring module 603, configured to perform real-time monitoring on the distributed guest groups;
after the guest group is pushed to the corresponding cooperation bank, the real-time performance condition of the distributed guest group can be further monitored.
The analysis unit 604 is configured to perform different-dimension analysis on the set early warning rules and models;
a rule/model management platform can be further developed, and the rule/model management platform comprises rule/model analysis and rule/model configuration management. Can be realized by JAVA development.
Specifically, different dimensionality analyses are performed on the set early warning rules and models.
A management unit 605, configured and managed to the rule/model;
the basis of risk monitoring is to effectively manage and maintain a monitoring model, and the main functions of model configuration comprise:
(1) the model is newly built, namely basic information of the model is configured, wherein the basic information comprises model basic information, data acquisition sources, early warning and verification information and the like;
(2) model modification, which can flexibly modify parameter values of a monitoring model, basic information of the model and the like;
(3) the method comprises the following steps of model verification, wherein a predefined model is operated, a risk early warning and checking tool is used for verifying a model result, and the correctness of the model, the practicability of the model and the like are demonstrated;
(4) releasing the model, wherein the model is released after the model configuration is completed;
(5) configuring model authority, and setting the management authority of the model;
(6) and (4) deactivating the model, and closing and deactivating the model which is not applicable any more.
A monitoring and early warning unit 606, configured to perform monitoring and early warning on the model;
and an early warning management platform can be further developed, and the early warning management platform comprises model monitoring early warning, early warning information distribution and early warning information processing.
Specifically, the monitoring model automatically analyzes the operation frequency of the monitoring model at regular time according to the day, week, month, quarter, half year, year and the like, and the background data analysis engine automatically analyzes and calculates according to the rule and the operation frequency preset by the early warning model. After the operation is finished, the system automatically stores the operation result into a system data mart, simultaneously automatically distributes clues to related personnel according to a system clue distribution strategy, and after the related personnel receive a clue task, the related personnel carry out investigation analysis and fact confirmation through a checking tool, if the problem exists, the related personnel enter a problem management and risk assessment platform to carry out problem rectification tracking and accountability.
A dispatch unit 607 for dispatching the early warning information;
the system supports two modes of automatic clue distribution and manual clue distribution, and the clue distribution strategy can be automatically set to be distributed according to models, mechanisms, service types, models and mechanisms, models and service types and the like according to the requirements in the row.
The system supports multi-channel information distribution of the early warning information, and comprises various modes such as WEB, short message, mail, telephone notification and the like.
And the processing unit 608 is configured to process the early warning information.
After each early warning model is operated, a series of early warning clues are generated, related personnel need to analyze and judge the early warning clues, corresponding subsequent processing is executed, and early warning tasks are divided into unprocessed, processed and processed according to processing states.
Related personnel can check the number of the untreated early warning models and the number of the treated early warning models under the early warning models treated by the online cables, the details of the early warning cables and the untreated early warning model cables can be treated. After the early warning inquiry and verification task is issued, the early warning clue state is changed from unprocessed to processed. Meanwhile, the processing state of the early warning model can be checked in early warning monitoring processing. Specifically, a soft BI tool self-help instrument panel function can be adopted, so that business analysis personnel can perform self-help analysis in a dragging and pulling mode.
In conclusion, the method and the system can integrate internal and external data related to risks to form a unified pre-loan risk score rating for the customer; risk business personnel can flexibly configure early warning rules/models as required through a risk data mart/intelligent monitoring platform; can satisfy the user through holding in the palm and draw through intelligent monitoring and draw nimble, carry out the analysis fast, real-time adjustment model and strategy performance.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for distributing a group of guests based on partner risk preferences, comprising:
integrating internal and external data through a risk score rating model to obtain a uniform risk score rating of a customer;
based on the preferences of different partners on the client risks, distributing the client groups according to the default rate level after the risk score rating prediction;
and monitoring the distributed guest groups in real time.
2. The method of claim 1, further comprising:
a rules/model management platform is developed.
3. The method of claim 2, wherein the development rule/model management platform comprises:
analyzing different dimensions of the set early warning rules and models;
and carrying out configuration management on the rules/models.
4. The method of claim 3, further comprising:
and developing an early warning management platform.
5. The method of claim 4, wherein developing the early warning management policy comprises:
monitoring and early warning the model;
distributing the early warning information;
and processing the early warning information.
6. A system for distributing a group of guests based on a partner risk preference, comprising:
the integration module is used for integrating internal and external data through a risk score rating model to obtain a uniform risk score rating of a customer;
the distribution module is used for distributing the customer groups according to the default rate level after the risk grading prediction based on the preferences of different partners on the customer risk;
and the monitoring module is used for monitoring the distributed guest groups in real time.
7. The system of claim 6, further comprising:
and the first development module is used for developing a rule/model management platform.
8. The system of claim 7, wherein the first development module comprises:
the analysis unit is used for analyzing different dimensions of the set early warning rules and models;
and the management unit is used for carrying out configuration management on the rules/models.
9. The system of claim 8, further comprising:
and the second development module is used for developing an early warning management platform.
10. The system of claim 9, wherein the second development module comprises:
the monitoring and early warning unit is used for monitoring and early warning the model;
the dispatching unit is used for dispatching the early warning information;
and the processing unit is used for processing the early warning information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011408427.7A CN112488822A (en) | 2020-12-04 | 2020-12-04 | Cooperation risk preference-based guest group distribution method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011408427.7A CN112488822A (en) | 2020-12-04 | 2020-12-04 | Cooperation risk preference-based guest group distribution method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112488822A true CN112488822A (en) | 2021-03-12 |
Family
ID=74938124
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011408427.7A Pending CN112488822A (en) | 2020-12-04 | 2020-12-04 | Cooperation risk preference-based guest group distribution method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112488822A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102081781A (en) * | 2009-11-26 | 2011-06-01 | 陈晓明 | Finance modeling optimization method based on information self-circulation |
| CN109472646A (en) * | 2018-11-16 | 2019-03-15 | 广发证券股份有限公司 | A kind of financial product recommended method and device |
| CN111798307A (en) * | 2020-07-17 | 2020-10-20 | 睿智合创(北京)科技有限公司 | Rejection inference method and system for multi-flow platform and financial institution correction sample |
| CN111932359A (en) * | 2020-07-16 | 2020-11-13 | 吉林亿联银行股份有限公司 | Risk monitoring method and system and electronic equipment |
-
2020
- 2020-12-04 CN CN202011408427.7A patent/CN112488822A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102081781A (en) * | 2009-11-26 | 2011-06-01 | 陈晓明 | Finance modeling optimization method based on information self-circulation |
| CN109472646A (en) * | 2018-11-16 | 2019-03-15 | 广发证券股份有限公司 | A kind of financial product recommended method and device |
| CN111932359A (en) * | 2020-07-16 | 2020-11-13 | 吉林亿联银行股份有限公司 | Risk monitoring method and system and electronic equipment |
| CN111798307A (en) * | 2020-07-17 | 2020-10-20 | 睿智合创(北京)科技有限公司 | Rejection inference method and system for multi-flow platform and financial institution correction sample |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10152692B2 (en) | Governing exposing services in a service model | |
| US20070023515A1 (en) | System and method for overcoming decision making and communications errors to produce expedited and accurate group choices | |
| US20090198534A1 (en) | Governing A Service Oriented Architecture | |
| US20100138250A1 (en) | Governing Architecture Of A Service Oriented Architecture | |
| EP1073941A2 (en) | Methods and apparatus for gauging group choices | |
| WO2006041882A2 (en) | Financial institution portal system and method | |
| US20100138252A1 (en) | Governing Realizing Services In A Service Oriented Architecture | |
| CN112817939A (en) | Construction method of data wind control model and data wind control model | |
| CN101751254A (en) | Governing the design of services in a service oriented architecture | |
| CN112598513B (en) | Method and device for identifying stockholder risk transaction behaviors | |
| CN115688110A (en) | Financial Internet of things platform equipment early warning method and device | |
| CN111178952A (en) | System, method and medium for sales lead follow-up and processing for the automotive industry | |
| CN111598360A (en) | Service policy determination method and device and electronic equipment | |
| CN111932359A (en) | Risk monitoring method and system and electronic equipment | |
| CN115393036A (en) | Post-credit early warning platform and method based on post-credit early warning model | |
| US20130262473A1 (en) | Systems, methods, and apparatus for reviewing file management | |
| EP3764310A1 (en) | Prediction task assistance device and prediction task assistance method | |
| CN115485662A (en) | Quota request resolution on a computing platform | |
| US20170270611A1 (en) | Processing system to automatically assign electronic records to verification process subset levels | |
| US20130041712A1 (en) | Emerging risk identification process and tool | |
| CN112488822A (en) | Cooperation risk preference-based guest group distribution method and system | |
| CN115577983A (en) | Enterprise task matching method based on block chain, server and storage medium | |
| CN112712270B (en) | Information processing method, device, equipment and storage medium | |
| JP2004192125A (en) | Project management system, data structure used therefor, and project management method | |
| CN114881767A (en) | Method, apparatus, storage medium, and program product for generating an acceptance policy |
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 |