Risk control management methods, systems and media based on the People's Bank of China's credit time series variables
By analyzing the correlation between credit customers' spending data and other customers' and changes in the People's Bank of China's credit data, the risk assessment strategy is dynamically updated, which solves the problem of frequent changes in the People's Bank of China's credit information in credit risk assessment and achieves efficient and reliable credit risk assessment.
Patent Information
- Application Number
- CN202510828338.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-20
- Publication Date
- 2025-09-12
- Estimated Expiration
- 2045-06-20
AI Technical Summary
In credit risk assessment, existing technologies are unable to effectively handle changes in the PBOC's credit information, resulting in the reliability and efficiency of credit risk assessment being unable to meet requirements. Especially when the PBOC's credit information changes frequently, how to dynamically update the risk assessment strategy becomes an urgent problem to be solved.
By analyzing the correlation between the spending data of credit customers and other customers, we can determine whether there is an aggregation risk. In combination with the changes in the People's Bank of China's credit data, we can dynamically update the risk assessment strategy and adopt the risk control management method of the People's Bank of China's credit time series variables for customers with changing credit risks. Taking into account historical assessment results and changes, we can generate differentiated assessment and processing strategies.
It improves the timeliness and reliability of credit risk assessment, ensures timely updating of frequently changing credit risks, improves the accuracy and efficiency of credit risk assessment, and provides differentiated processing strategies to deal with clustered fraud risks.
Smart Images

Figure CN120355502B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of data processing technology, and in particular relates to a risk control management method, system and medium based on the People's Bank of China's credit time series variables. Background Art
[0002] In the process of managing and controlling users' credit risks, the credit data of the People's Bank of China is of vital importance. Specifically, in the invention patent application CN202410105732.0 "A People's Bank of China Credit Scoring Method and System Based on a Time Series Graph Model", a time series graph model is used to automatically characterize the credit behavior sequence such as user institution type selection in the People's Bank of China credit investigation, fully learn the potential correlation between changes in credit behavior and risks, and achieve accurate classification of user risk levels, thereby providing financial institutions with more accurate and comprehensive credit decision support.
[0003] In the process of obtaining the time series variables of the People's Bank of China's credit information, due to the differences in the changes in the People's Bank of China's credit information of different post-loan users, only considering the People's Bank of China's credit information, especially when the degree of change of the People's Bank of China's credit information is high, makes it difficult to meet the reliability requirements of the credit risk assessment and processing. Therefore, how to realize the risk assessment strategy of post-loan users and the dynamic update processing of the risk assessment strategy based on the changes in the time series of the People's Bank of China's credit information, that is, whether to consider other dimensional data and the dynamic update processing of the conditions for considering other dimensional data, to ensure the reliability of the credit risk assessment and processing has become a technical problem that needs to be solved urgently.
[0004] In order to solve the above technical problems, this application provides a risk control management method, system and medium based on the People's Bank of China's credit time series variables. Summary of the Invention
[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:
[0006] Specifically, in a first aspect, the present application provides a risk control management method based on the People's Bank of China's credit time series variables, specifically including:
[0007] S1 proceeds to the next step when it is determined based on the correlation between the credit customer's spending data and that of other credit customers that the credit customer does not have agglomeration risk;
[0008] S2: acquiring and processing the credit customer's PBOC credit data according to a preset strategy, determining changes in the PBOC credit data of the credit customer, and determining customers with changed credit risks among the credit customers based on historical changes in the PBOC credit data of the credit customer;
[0009] S3 determines a risk assessment and processing strategy for the customer with changed credit risk based on changes in the PBOC credit information of the customer with changed credit risk and historical updates of the credit risk assessment results;
[0010] S4 determines an updated assessment result of the credit risk of the credit customer based on the risk assessment processing strategy, and determines an updated processing method for the risk control management strategy of the People's Bank of China's credit time series variable for the customer with changed credit risk based on the updated assessment result and the changes in the credit risk assessment result.
[0011] The beneficial effects of the present invention are:
[0012] Based on the correlation between the credit customer's spending data and that of other credit customers, it is determined whether the credit customer has a clustering risk, thereby realizing the screening of credit customers with a clustering fraud risk based on similar situations in spending location, spending object and spending time. It also lays the foundation for generating differentiated processing strategies for the credit risk assessment and processing of credit customers with a clustering fraud risk, and improves the timeliness and reliability of credit risk assessment and processing.
[0013] Based on the updated assessment results and changes in the credit risk assessment results, the update processing method of the risk control management strategy of the People's Bank of China's credit time series variables for customers with changing credit risks is determined. Not only the changes in the updated credit risk assessment results are taken into account, but also the changes in the historical credit risk assessment results are taken into account, thereby ensuring the timeliness and reliability of the updated credit risk processing for customers whose credit risk changes frequently and the fluctuation range is too large. At the same time, through the determination of differentiated risk control management strategies, the efficiency of the updated credit risk processing of the credit customers of the credit institutions is also guaranteed.
[0014] A further technical solution is that the expenditure data includes the number of expenditures by the credit user on different expenditure objects, the expenditure amounts for different expenditure times, and the expenditure locations.
[0015] A further technical solution is to determine that the credit customer does not have a concentration risk, specifically including:
[0016] Based on the correlation between the credit customer's and other credit customers' expenditure data, determine the situations in which the credit customer and other credit customers have the same expenditure objects and expenditure locations at different expenditure times, and determine the consistent expenditure times between the credit customer and other credit customers based on the expenditure times with the same expenditure objects and expenditure locations;
[0017] Based on the deviation of the disbursement times of the consistent disbursement times, determining the disbursement times of the credit customer and other credit customers with similar times in the consistent disbursement times;
[0018] Based on the number of similar expenditures at the same time between the credit customer and other credit customers, it is determined whether the credit customer has an aggregation risk.
[0019] A further technical solution is that the number of similar expenditures at the time is the number of consistent expenditures where the deviation between the expenditure time of the credit customer and other credit customers is less than a preset time deviation threshold.
[0020] A further technical solution is that when the number of other credit customers whose number of expenditures at the same time as the credit customer is greater than the preset number threshold of similar expenditures at the same time is greater than the preset credit customer number threshold, it is determined that the credit customer has an aggregation risk.
[0021] A further technical solution is that the method for determining the updating processing mode of the risk control management strategy of the PBOC credit time series variable of the customer with the credit risk change is:
[0022] Based on the updated assessment results and the changes in the credit risk assessment results, determine the amount of change between the updated assessment results and the most recent credit risk assessment results of the customer with changed credit risk, and use the amount as the amount of credit risk change;
[0023] Determining the number of risk changes in different credit risk assessment times based on changes in the credit risk assessment results;
[0024] Based on the number of risk changes and the amount of credit risk change, an update processing method for the risk control management strategy of the People's Bank of China credit time series variable of the customer with the credit risk change is determined.
[0025] A further technical solution is that the risk change times are credit risk assessment times in which the change in credit risk assessment results of adjacent credit risk assessment times is greater than a preset risk change threshold.
[0026] In a second aspect, the present invention provides a computer system comprising: a memory and a processor in communication connection, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned risk control management method based on the PBOC credit time series variables when running the computer program.
[0027] In a third aspect, the present invention provides a computer storage medium storing a computer program. When the computer program is executed in a computer, the computer is caused to execute the above-mentioned risk control management method based on the People's Bank of China's credit time series variables.
[0028] Other features and advantages will be described in the following description. The objectives and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.
[0029] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the accompanying drawings.
[0031] Figure 1 It is a flow chart of a risk control management method based on the People's Bank of China's credit time series variables;
[0032] Figure 2 It is a flow chart to determine that there is no aggregation risk among credit customers;
[0033] Figure 3 A flow chart of a method for determining credit risk change customers among credit customers;
[0034] Figure 4 It is a flowchart of the method for determining the risk assessment and treatment strategy for customers with changing credit risk;
[0035] Figure 5 It is a framework diagram of a computer system. DETAILED DESCRIPTION
[0036] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this specification without creative work should fall within the scope of protection of this specification.
[0037] In this application, differentiated credit risk assessment and processing strategies are generated based on changes in the credit data of credit customers from the People's Bank of China. While improving the efficiency of credit risk assessment and processing, it also ensures the accuracy of credit risk assessment and processing for credit customers whose credit risk changes are large.
[0038] Example 1
[0039] like Figure 1 As shown, this application provides a risk control management method based on the People's Bank of China's credit time series variables, specifically including:
[0040] S1 proceeds to the next step when it is determined based on the correlation between the credit customer's spending data and that of other credit customers that the credit customer does not have agglomeration risk;
[0041] Furthermore, the number of expenditures by other credit customers whose expenditure objects and locations are consistent and whose expenditure times have deviations within a preset deviation range is taken as the number of similar expenditures by the credit customer at the time. When the number of historical expenditures with similar expenditure times accounts for more than 0.9 of the historical expenditures of the credit customer, it is determined that the credit customer has an aggregation risk.
[0042] S2: acquiring and processing the credit customer's PBOC credit data according to a preset strategy, determining changes in the PBOC credit data of the credit customer, and determining customers with changed credit risks among the credit customers based on historical changes in the PBOC credit data of the credit customer;
[0043] Specifically, the amount of change in the credit information of a credit customer is determined based on the average of the ratio of the number of changed information items to the information items for which credit data exists, and the ratio of the number of information items with historical changes to the information items for which credit data exists. When the amount of change in credit information is greater than 0.2, the credit customer is determined to be a customer with changed credit risk.
[0044] S3 determines a risk assessment and processing strategy for the customer with changed credit risk based on changes in the PBOC credit information of the customer with changed credit risk and historical updates of the credit risk assessment results;
[0045] It should be noted that when the time interval between the most recent credit risk assessment and processing moment and the current moment is more than 2 months and the ratio of the number of changed information items to the information items with existing credit data is greater than 0.3, the credit risk of the credit customer will be assessed and processed based on the PBC credit time series variable constructed based on the changes in the PBC credit data and the read data of the associated data source of the credit customer.
[0046] S4 determines an updated assessment result of the credit risk of the credit customer based on the risk assessment processing strategy, and determines an updated processing method for the risk control management strategy of the People's Bank of China's credit time series variable for the customer with changed credit risk based on the updated assessment result and the changes in the credit risk assessment result.
[0047] The change between the updated assessment result of the customer whose credit risk changes and the most recent credit risk assessment result is taken as the credit risk change, and the risk change value is determined by taking the credit risk change and the average of the change between the number of credit risk assessments and the number of adjacent credit risk assessments. When the risk change value is greater than 0.4, once the PBOC credit data changes, the PBOC credit time series variable constructed based on the change in the PBOC credit data and the read data of the associated data source of the credit customer are used as the input of the credit risk control model, and the credit risk of the credit customer is assessed and processed based on the output of the credit risk control model.
[0048] When the risk change value is no more than 0.4, and when the number of changes in the information items of the PBOC's credit data is greater than 5, the PBOC's credit time series variables constructed based on the changes in the PBOC's credit data are used as the input of the credit risk control model, and the credit risk of the credit customer is assessed and processed based on the output of the credit risk control model.
[0049] Furthermore, the expenditure data includes the number of expenditures by the credit user on different expenditure objects, the expenditure amounts for different expenditure times, and the expenditure locations.
[0050] Specifically, such as Figure 2 As shown, it is determined that there is no concentration risk for the credit customer, specifically including:
[0051] Based on the correlation between the credit customer's and other credit customers' expenditure data, determine the situations in which the credit customer and other credit customers have the same expenditure objects and expenditure locations at different expenditure times, and determine the consistent expenditure times between the credit customer and other credit customers based on the expenditure times with the same expenditure objects and expenditure locations;
[0052] Based on the deviation of the disbursement times of the consistent disbursement times, determining the disbursement times of the credit customer and other credit customers with similar times in the consistent disbursement times;
[0053] Based on the number of similar expenditures at the same time between the credit customer and other credit customers, it is determined whether the credit customer has an aggregation risk.
[0054] Furthermore, the number of similar expenditures at different times is the number of consistent expenditures where the deviation between the expenditure times of the credit customer and other credit customers is less than a preset time deviation threshold.
[0055] It can be understood that when the number of other credit customers whose number of expenditures at the same time as the credit customer is greater than the preset threshold of the number of similar expenditures at the same time is greater than the preset threshold of the number of credit customers, it is determined that the credit customer has an aggregation risk.
[0056] It should be noted that when the credit customer has an aggregation risk, when the PBOC credit data of the credit customer changes, the credit risk of the credit customer will be assessed based on the PBOC credit time series variables constructed based on the changes in the PBOC credit data and the read data of the associated data source of the credit customer.
[0057] Furthermore, the associated data source is a data source that contains the credit customer's spending data and is associated with the user's credit application data.
[0058] In another possible embodiment, determining that the credit customer does not have aggregate risk specifically includes:
[0059] Based on the correlation between the credit customer's and other credit customers' expenditure data, determine the situations in which the credit customer and other credit customers have the same expenditure objects and expenditure locations at different expenditure times, and determine the consistent expenditure times between the credit customer and other credit customers based on the expenditure times with the same expenditure objects and expenditure locations;
[0060] Obtaining other credit customers whose disbursement objects and disbursement locations are consistent under different consistent disbursement times, and identifying them as consistent credit customers under different consistent usage times; and determining the number of consistent credit customers whose disbursement times fall within the disbursement time periods under different consistent disbursement times based on deviations from the disbursement times of the credit customers under the different consistent disbursement times;
[0061] The number of consistent expenditures in which the number of consistent credit customers in the expenditure period at the expenditure moment under different consistent expenditure times is greater than the preset consistent customer number threshold is taken as the risky expenditure times, and the risky expenditure times are used to determine whether the credit customer has an aggregation risk.
[0062] A further technical solution is that when the number of risky expenditures is greater than a preset risky expenditure threshold, it is determined that the credit customer has an aggregated risk.
[0063] Specifically, obtaining and processing the credit information data of the credit customer from the People's Bank of China according to the preset strategy includes:
[0064] The credit information data of the credit customer of the People's Bank of China is obtained and processed according to a preset time period.
[0065] It should be noted that the change in the credit customer's PBOC credit data includes the number of information items in the credit customer's PBOC credit data that have changed.
[0066] Specifically, such as Figure 3 As shown, the method for determining the credit risk change customers among the credit customers is:
[0067] Based on the changes in the credit customer's PBOC credit data, determine the information items of the credit customer that have changed, and use them as the changed information items; and determine the customer change value of the credit customer based on the ratio of the number of the changed information items to the information items for which the credit data exists;
[0068] Based on the historical changes in the credit customer's PBOC credit data, determine the number of information items with historical changes on the credit customer, and determine the historical change value of the information items on the credit customer based on the ratio of the number of information items with historical changes to the information items in the existing credit data;
[0069] The credit information change amount of the credit customer is determined based on the customer change value and the average of the historical change values of the information item, and the credit information change amount is used to determine whether the credit customer is a customer with changed credit risk.
[0070] Furthermore, when the amount of change in the credit information is greater than a preset information change threshold, the credit customer is determined to be a customer with changed credit risk.
[0071] It is understandable that when the credit customer does not belong to a customer with variable credit risk, there is no need to conduct a risk assessment of the credit customer.
[0072] In another possible embodiment, the method for determining the credit risk-variable customers among the credit customers is:
[0073] Determining the number of changed information items of the credit customer based on changes in the credit customer's PBOC credit information data and historical changes in the PBOC credit information data of the credit customer;
[0074] Determining a credit change value of the credit customer based on a ratio of the number of information items that have changed to the information items for which credit data exists;
[0075] Determine whether the credit customer is a customer with changed credit risk based on the credit change value.
[0076] Furthermore, when the credit change value is greater than a preset credit change value threshold, the credit customer is determined to be a customer with changed credit risk.
[0077] Optionally, the method for determining the credit risk-variable customers among the credit customers is:
[0078] Based on the changes in the credit customer's PBOC credit information data, determine the information item in which the credit customer has changed, and use it as the changed information item;
[0079] It is understandable that the above steps include the following three situations:
[0080] Scenario 1: Based on the ratio of the number of changed information items to the information items in the existing credit data, the change ratio of the credit customer is determined. If either the change ratio or the number of changed information items does not meet the requirements, that is, is greater than the threshold, the credit customer is determined to be a customer with changed credit risk;
[0081] Case 2: The sum of the change ratios of the credit customer's change information items is used as the credit customer's information item change value. When the credit customer's information item change value is less than a preset information item change threshold, it is determined that the credit customer does not belong to a customer with changed credit risk.
[0082] Scenario 3: Based on the changes in the credit customer's PBOC credit data and the historical changes in the credit customer's PBOC credit data, the number of changed information items of the credit customer is determined. Based on the ratio of the number of changed information items to the information items in the existing credit data, the credit change value of the credit customer is determined. When either the credit change value or the number of changed information items of the credit customer does not meet the requirements, that is, is greater than the threshold, the credit customer is determined to be a customer with changed credit risk. In other cases, the process proceeds to the next step:
[0083] Determine the change assessment amount of different information items based on the number of historical changes of different information items and whether they are change information items;
[0084] In a possible embodiment, the change assessment amount is determined by multiplying the ratio of the historical number of changes to the preset number of changes by a preset weight value, wherein the preset weight value is determined based on whether it belongs to a change information item, wherein the value is 1 when it belongs to a change information item and 0.5 in other cases.
[0085] Specifically, in the above steps, if the number of information items whose change assessment amount is greater than the preset threshold is greater than the preset value of the number of information items, then the credit customer is determined to be a customer with changed credit risk;
[0086] The amount of change in the credit information of the credit customer is determined based on the change assessment amounts of different information items, and the amount of change in the credit information is used to determine whether the credit customer is a customer with changed credit risk.
[0087] In a possible embodiment, the change amount of the credit information of the credit customer is the sum of the change assessment amounts of different information items, wherein when the change amount of the credit information is greater than a preset threshold, the credit customer is determined to be a customer with changed credit risk.
[0088] Specifically, such as Figure 4 As shown, the method for determining the risk assessment processing strategy for customers with changing credit risk is:
[0089] Based on the changes in the PBOC credit data of the customer whose credit risk has changed, determine the information items of the credit customer that have changed, and use them as the changed information items; and based on the ratio of the number of the changed information items to the information items for which credit data exists, determine the customer change value of the credit customer;
[0090] Determining the time interval between the most recent credit risk assessment and processing time and the current time based on historical updates of the credit risk assessment results;
[0091] According to the customer change value and interval length of the credit customer, the customer risk update requirement of the customer with changed credit risk is determined, and based on the customer risk update requirement, the risk assessment processing strategy of the customer with changed credit risk is determined.
[0092] In a possible embodiment, the customer risk update demand of the customer with changed credit risk is determined by multiplying the preset change weight coefficient corresponding to the interval time by the customer change value.
[0093] Furthermore, a risk assessment processing strategy for the customer with changed credit risk is determined based on the customer risk update demand, specifically including:
[0094] When the customer risk update demand is greater than a preset update demand threshold, the credit risk of the credit customer is assessed based on the PBC credit time series variable constructed based on the changes in the PBC credit data and the read data from the associated data source of the credit customer;
[0095] When the customer risk update demand is not greater than the preset update demand threshold, determine whether the customer risk update demand is less than the preset demand threshold. If so, there is no need to evaluate the credit risk of the credit customer. If not, determine the risk assessment and processing strategy for the credit risk change customer based on the customer change value of the credit customer.
[0096] It can be understood that when the customer change value of the credit customer is within the preset customer change value range, the credit risk of the credit customer is evaluated and processed based on the PBC credit time series variable constructed based on the changes in the PBC credit data; when the customer change value of the credit customer is not within the preset customer change value range, the credit risk of the credit customer is evaluated and processed based on the PBC credit data at the current moment.
[0097] In another possible embodiment, the method for determining the risk assessment processing strategy for customers with fluctuating credit risks is:
[0098] Based on the changes in the PBOC credit data of the customer whose credit risk has changed, determine the information items of the credit customer that have changed, and use them as the changed information items; and based on the ratio of the number of the changed information items to the information items for which credit data exists, determine the customer change value of the credit customer;
[0099] In a possible embodiment, in the above steps, if either the customer change value or the number of change information items does not meet the requirement, that is, is greater than the threshold, then the credit risk of the credit customer is assessed based on the PBOC credit time series variable constructed based on the change of the PBOC credit data and the read data of the associated data source of the credit customer;
[0100] Based on the historical update of the credit risk assessment results, determine the interval between the most recent credit risk assessment processing time and the current time, and determine the credit risk assessment processing reliability value of the credit customer based on the interval and the most recent credit risk assessment processing strategy;
[0101] It should also be noted that in the above steps, if the interval duration is greater than the preset interval duration threshold, the credit risk of the credit customer is assessed based on the PBC credit time series variable constructed based on the changes in the PBC credit data and the read data from the associated data source of the credit customer;
[0102] Furthermore, if the interval duration is not greater than a preset interval duration threshold, determining the credit risk assessment reliability value of the credit customer according to the product of a preset proportional factor corresponding to the interval duration and a preset updated reliability value corresponding to the most recent credit risk assessment processing strategy;
[0103] It should also be noted that in the above steps, if the reliability value of the credit risk assessment of the credit customer is less than the preset reliability value threshold, the credit risk of the credit customer is assessed based on the People's Bank of China credit time series variable constructed based on the changes in the People's Bank of China credit data and the read data from the associated data source of the credit customer;
[0104] When the reliability value of the credit risk assessment process of the credit customer is greater than the preset reliability value, it is not necessary to perform the credit risk assessment process of the credit customer.
[0105] The customer risk update requirement of the customer with changed credit risk is determined based on the customer change value of the credit customer and the credit risk assessment processing reliability value of the credit customer, and the risk assessment processing strategy of the customer with changed credit risk is determined based on the customer risk update requirement.
[0106] Furthermore, the method for determining the updating processing mode of the risk control management strategy of the PBOC credit time series variable for the customer with the credit risk change is as follows:
[0107] Based on the updated assessment results and the changes in the credit risk assessment results, determine the amount of change between the updated assessment results and the most recent credit risk assessment results of the customer with changed credit risk, and use the amount as the amount of credit risk change;
[0108] Determining the number of risk changes in different credit risk assessment times based on changes in the credit risk assessment results;
[0109] Based on the number of risk changes and the amount of credit risk change, an update processing method for the risk control management strategy of the People's Bank of China credit time series variable of the customer with the credit risk change is determined.
[0110] Specifically, the risk change times are credit risk assessment times in which the change in the credit risk assessment results of adjacent credit risk assessment times is greater than a preset risk change threshold.
[0111] It should be noted that, based on the number of risk changes and the amount of credit risk change, the update processing method of the risk control management strategy for the PBOC credit time series variable of the customer with the credit risk change is determined, specifically including:
[0112] When the credit risk change is greater than a preset risk change threshold, and when the PBOC credit information data of the credit customer changes, the credit risk of the credit customer is assessed based on the PBOC credit information time series variable constructed based on the change in the PBOC credit information data and the read data from the associated data source of the credit customer;
[0113] When the credit risk change amount is not greater than the preset risk change amount threshold, the risk change times are used to determine the update processing method of the risk control management strategy of the PBOC credit time series variable of the customer with the credit risk change.
[0114] It is understandable that the update processing method of the risk control management strategy for determining the PBOC credit time series variable of the customer with the credit risk change by using the risk change frequency specifically includes:
[0115] When the number of risk changes is greater than the preset risk change number threshold, when the number of risk changes is not greater than the preset risk change number threshold, then when the number of changes in the credit customer's information items is greater than the preset information item change number threshold, then the People's Bank of China credit time series variable constructed based on the changes in the People's Bank of China's credit data is used to evaluate the credit risk of the credit customer. When the number of risk changes is greater than the preset risk change number threshold, then when the People's Bank of China's credit data of the credit customer changes, then the People's Bank of China credit time series variable constructed based on the changes in the People's Bank of China's credit data is used to evaluate the credit risk of the credit customer.
[0116] Example 2
[0117] Second, as Figure 5As shown, the present invention provides a computer system, comprising: a memory and a processor in communication connection, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-mentioned risk control management method based on the PBOC credit time series variable when running the computer program.
[0118] Example 3
[0119] In a third aspect, the present invention provides a computer storage medium storing a computer program. When the computer program is executed in a computer, the computer is caused to execute the above-mentioned risk control management method based on the People's Bank of China's credit time series variables.
[0120] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, apparatus, and non-volatile computer storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant details, refer to the descriptions of the method embodiments.
[0121] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0122] The foregoing description is merely one or more embodiments of this specification and is not intended to limit this specification. It will be apparent to those skilled in the art that various modifications and variations may be made to one or more embodiments of this specification. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of one or more embodiments of this specification are intended to be within the scope of the claims of this specification.
Claims
1. A risk control management method based on the People's Bank of China's credit time series variables, characterized by: Specifically include: If it is determined based on the correlation between the credit customer's spending data and that of other credit customers that the credit customer does not have agglomeration risk, proceed to the next step; Acquiring and processing the credit customer's PBOC credit data according to a preset strategy, determining changes in the PBOC credit data of the credit customer, and determining customers with changed credit risks among the credit customers based on historical changes in the PBOC credit data of the credit customer; Determine the risk assessment and processing strategy for the customer with changed credit risk based on the changes in the PBOC credit information data of the customer with changed credit risk and the historical updates of the credit risk assessment results; Determining an updated assessment result of the credit risk of the credit customer based on the risk assessment processing strategy, and determining an updated processing method for the risk control management strategy of the PBOC credit time series variable for the customer with changed credit risk based on the updated assessment result and changes in the credit risk assessment result; The method for determining the risk assessment and processing strategy for customers with changing credit risk is as follows: Based on the changes in the PBOC credit data of the customer whose credit risk has changed, determine the information items of the credit customer that have changed, and use them as the changed information items; and based on the ratio of the number of the changed information items to the information items for which credit data exists, determine the customer change value of the credit customer; Determining the time interval between the most recent credit risk assessment and processing time and the current time based on historical updates of the credit risk assessment results; Determining a customer risk update requirement for the customer with changed credit risk based on the customer change value and interval length of the credit customer, and determining a risk assessment processing strategy for the customer with changed credit risk based on the customer risk update requirement; The expenditure data includes the number of expenditures by the credit customer on different expenditure objects, the expenditure amounts for different expenditure times, and the expenditure locations.
2. The risk control management method based on the People's Bank of China credit time series variable according to claim 1, characterized in that: Determine that there is no concentration risk among the credit customers, including: Based on the correlation between the credit customer's and other credit customers' expenditure data, determine the situations in which the credit customer and other credit customers have the same expenditure objects and expenditure locations at different expenditure times, and determine the consistent expenditure times between the credit customer and other credit customers based on the expenditure times with the same expenditure objects and expenditure locations; Based on the deviation of the disbursement times of the consistent disbursement times, determining the disbursement times of the credit customer and other credit customers with similar times in the consistent disbursement times; Based on the number of similar expenditures at the same time between the credit customer and other credit customers, it is determined whether the credit customer has an aggregation risk.
3. The risk control management method based on the People's Bank of China credit time series variable according to claim 2, characterized in that: The number of similar expenditures at different times is the number of consistent expenditures where the deviation between the expenditure times of the credit customer and other credit customers is less than a preset time deviation threshold.
4. The risk control management method based on the People's Bank of China credit time series variable according to claim 1, characterized in that: When the credit customer has an aggregation risk, when the credit customer's PBOC credit data changes, the credit risk of the credit customer is assessed based on the PBOC credit time series variables constructed based on the changes in the PBOC credit data and the read data of the credit customer's associated data source.
5. The risk control management method based on the People's Bank of China credit time series variable according to claim 4 is characterized in that: The associated data source is a data source that contains the credit customer's spending data and is associated with the credit customer's credit application data.
6. The risk control management method based on the People's Bank of China credit time series variable according to claim 1 is characterized in that: Acquiring and processing the credit information of the credit customer from the People's Bank of China according to the preset strategy, specifically including: The credit information data of the credit customer of the People's Bank of China is obtained and processed according to a preset time period.
7. The risk control management method based on the People's Bank of China credit time series variable according to claim 1 is characterized in that: The method for determining the updating processing mode of the risk control management strategy for the credit time series variables of the People's Bank of China for customers with changing credit risks is as follows: Based on the updated assessment results and the changes in the credit risk assessment results, determine the amount of change between the updated assessment results and the most recent credit risk assessment results of the customer with changed credit risk, and use the amount as the amount of credit risk change; Determining the number of risk changes in different credit risk assessment times based on changes in the credit risk assessment results; Based on the number of risk changes and the amount of credit risk change, an update processing method for the risk control management strategy of the People's Bank of China credit time series variable of the customer with the credit risk change is determined.
8. A computer system comprising: A memory and a processor in communication connection, and a computer program stored in the memory and capable of running on the processor, characterized in that when the processor runs the computer program, it executes a risk control management method based on the People's Bank of China credit time series variable as described in any one of claims 1 to 7.
9. A computer storage medium having a computer program stored thereon, wherein when the computer program is executed in a computer, Instruct a computer to execute any one of claims 1-7, a risk control management method based on the People's Bank of China's credit time series variables.
Citation Information
Patent Citations
Pedestrian credit scoring method and system based on time sequence diagram model
CN118134620A
Credit risk evaluation method and credit risk evaluation system
CN107993143A
Global financial risk knowledge graph construction method based on artificial intelligence technology
CN110717816A