CN117473366A - User overdue data processing method, device, equipment and storage medium - Google Patents

User overdue data processing method, device, equipment and storage medium Download PDF

Info

Publication number
CN117473366A
CN117473366A CN202311418492.1A CN202311418492A CN117473366A CN 117473366 A CN117473366 A CN 117473366A CN 202311418492 A CN202311418492 A CN 202311418492A CN 117473366 A CN117473366 A CN 117473366A
Authority
CN
China
Prior art keywords
overdue
user
time period
preset time
grade
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
Application number
CN202311418492.1A
Other languages
Chinese (zh)
Inventor
方啓先
朱浪锋
张鲲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China United Network Communications Group Co Ltd
Original Assignee
China United Network Communications Group Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China United Network Communications Group Co Ltd filed Critical China United Network Communications Group Co Ltd
Priority to CN202311418492.1A priority Critical patent/CN117473366A/en
Publication of CN117473366A publication Critical patent/CN117473366A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • 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
    • G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • General Physics & Mathematics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Technology Law (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application provides a method, a device, equipment and a storage medium for processing overdue data of a user. The method comprises the following steps: and acquiring the original business data of a preset number of users in a first time period. And calculating overdue grade characteristics of each user according to the original service data of each user, wherein the overdue grade characteristics are used for representing the severity of overdue arrearages of the users. The service characteristics of each user are obtained from the original service data. And carrying out iterative training on the initial overdue prediction model according to overdue grade characteristics and service characteristics of each user and the pre-marked overdue result of the user so as to obtain a trained overdue prediction model. The trained overdue prediction model is used for predicting overdue behaviors of any target user. The method can be used for accurately predicting the overdue behavior of the user.

Description

User overdue data processing method, device, equipment and storage medium
Technical Field
The present disclosure relates to the field of artificial intelligence, and in particular, to a method, an apparatus, a device, and a storage medium for processing overdue data of a user.
Background
When the arrearages of customers of telecom operators, government enterprises and government enterprises are common, the overdue of the customers has obvious influence on the refund amount, so that the account occupation ratio is high, and the overdue can influence the group performance as an important financial index, so that the overdue arrearages of the customers are required to be controlled.
In the prior art, the overdue risk is predicted by taking the amount of arrearages or the length of arrearages of users as characteristics and inputting the characteristics into the overdue prediction model.
However, the existing overdue prediction model has a problem of inaccurate overdue behavior prediction.
Disclosure of Invention
The application provides a method, a device, equipment and a storage medium for processing overdue data of a user, which are used for solving the technical problem of inaccurate overdue risk behavior prediction.
In a first aspect, the present application provides a method for processing user overdue data, including:
acquiring original business data of a preset number of users in a first time period;
calculating overdue grade characteristics of each user according to the original service data of each user, wherein the overdue grade characteristics are used for representing the severity of overdue arrearages of the users;
acquiring service characteristics of each user from the original service data;
according to the overdue grade characteristics and the service characteristics of each user and the overdue results of the pre-marked users, performing iterative training on the initial overdue prediction model to obtain a trained overdue prediction model; the trained overdue prediction model is used for predicting overdue behaviors of any target user.
In one possible implementation, the raw service data for each user includes: the arrearage amount of each user in a preset time period; correspondingly, calculating the overdue grade characteristic of each user according to the original service data of each user comprises the following steps: acquiring arrearage amount of each user in a preset time period; and determining the overdue grade characteristic of each user in the preset time period according to the arrearage amount in the preset time period.
In one possible implementation, determining the overdue class feature of each user in the preset time period according to the arrearage amount of the preset time period includes: judging whether the arrearage amount in the preset time period is larger than 0; if the arrearage amount in the preset time period is not more than 0, judging that the overdue grade characteristic of each user in the preset time period is a first overdue grade; if the arrearage amount of the preset time period is greater than 0, judging whether the arrearage amount of each user in the last preset time period is greater than 0; if the arrearage amount of the last preset time period is not more than 0, judging that the overdue grade characteristic of each user in the preset time period is a second overdue grade, wherein the higher the grade of the overdue grade characteristic is, the greater the severity of overdue arrearage of the user is represented; if the arrearage amount of the last preset time period is greater than 0, calculating the ratio of the arrearage amount of each user in the preset time period to the arrearage amount of the last preset time period; and determining the overdue grade characteristic of each user in a preset time period according to the ratio.
In one possible implementation, determining the overdue ranking characteristic of each user over a preset period of time based on the ratio includes: if the ratio is smaller than the first threshold, determining that the overdue grade characteristic of each user in the preset time period is the overdue grade characteristic of the last preset time period minus 1; if the ratio is greater than or equal to the first threshold and less than the second threshold, determining that the overdue grade characteristic of each user in the preset time period is the overdue grade characteristic of the last preset time period; if the ratio is greater than the second threshold, determining that the overdue grade feature of each user in the preset time period is the overdue grade feature of the last preset time period plus 1.
In one possible implementation, after obtaining the trained overdue prediction model, the method further includes: acquiring business data of a preset number of users in a second time period; inputting the business data of each user into a trained overdue prediction model to obtain a predicted overdue result corresponding to each user; calculating an error according to the pre-marked user overdue result and the predicted overdue result corresponding to each user; and based on the error, adjusting the trained overdue prediction model to obtain a final overdue prediction model.
In a second aspect, the present application provides a user overdue data processing apparatus, including:
the first service data acquisition module is used for acquiring original service data of a preset number of users in a first time period;
the overdue grade calculation module is used for calculating overdue grade characteristics of each user according to the original business data of each user, wherein the overdue grade characteristics are used for representing the severity of overdue arrearages of the users;
the service feature extraction module is used for acquiring the service features of each user from the original service data;
the model training module is used for carrying out iterative training on the initial overdue prediction model according to overdue grade characteristics and service characteristics of each user and the overdue result of the pre-marked user so as to obtain a trained overdue prediction model; the trained overdue prediction model is used for predicting overdue behaviors of any target user.
In a third aspect, the present application provides a computer device comprising: a processor, and a memory communicatively coupled to the processor. The memory stores computer-executable instructions. The processor executes computer-executable instructions stored in the memory to implement the method as described above in the first aspect.
In a fourth aspect, the present application provides a computer-readable storage medium having stored therein computer-executable instructions which, when executed by a processor, are adapted to carry out the method of the first aspect as described above.
According to the user overdue data processing method, device, equipment and storage medium, the initial overdue prediction model is input into the original business data of a preset number of users in a first time period, overdue grade characteristics of each user and the preset user overdue results of each user to conduct iterative training, a trained overdue prediction model is obtained, overdue behaviors of any user are predicted by using the trained overdue prediction model, and the effect of accurately predicting the overdue behaviors of the users can be achieved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
Fig. 1 is a schematic system structure of a computer device according to an embodiment of the present application;
FIG. 2 is a flowchart illustrating a method for processing user overdue data according to an embodiment of the present application;
FIG. 3 is a schematic diagram illustrating a structure of a user overdue data processing apparatus according to an embodiment of the present application;
fig. 4 is a schematic hardware structure of a computer device according to an embodiment of the present application.
Specific embodiments thereof have been shown by way of example in the drawings and will herein be described in more detail. These drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.
When the arrearages of government enterprise customers of telecom operators are common, the overdue effect of users on the arrearages is remarkable, so that the account occupation ratio is high, and the overdue effect can influence the group performance as an important financial index, so that the overdue arrearages of users are required to be controlled. By evaluating the overdue arrearage risk of the user, high-quality users with good credit are preferentially developed, the development of low-quality users is limited, and the increment of overdue accounts receivable can be controlled from the source, so that the group performance is improved. In the prior art, the overdue grade of the customer is divided directly according to the amount of arrearage of the customer or the time spent on arrearage, for example, 1-30 days of arrearage is marked as overdue grade 1,31-60 days is marked as overdue grade 2, and the like. However, the overdue grade features constructed by the method have no potential relation among the mining features, and have the problem of inaccurate overdue behavior prediction.
In order to solve the technical problems, the embodiment of the application provides the following technical ideas: the method comprises the steps of inputting the original business data of a preset number of users in a first time period, overdue grade characteristics of each user and overdue results of each user preset mark into an initial overdue prediction model for iterative training to obtain a trained overdue prediction model, and predicting overdue behaviors of any user by using the trained overdue prediction model, so that the effect of accurately predicting the overdue behaviors of the users can be achieved.
The following describes the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Fig. 1 is a schematic system structure of a computer device according to an embodiment of the present application. As shown in fig. 1, the computer device includes: a receiving device 101, a processor 102 and a display device 103.
It should be understood that the structures illustrated in the embodiments of the present application do not constitute a specific limitation on the method of identifying an article. In other possible embodiments of the present application, the architecture may include more or fewer components than those illustrated, or some components may be combined, some components may be separated, or different component arrangements may be specifically determined according to the actual application scenario, and the present application is not limited herein. The components shown in fig. 1 may be implemented in hardware, software, or a combination of software and hardware.
In a specific implementation process, the receiving device 101 may be an input/output interface or a communication interface, and may acquire original service data of a preset number of users in a first period of time.
The processor 102 may calculate the overdue grade feature of each user according to the original service data of each user, obtain the service feature of each user from the original service data, and iteratively train the initial overdue prediction model according to the overdue grade feature and the service feature of each user and the pre-marked overdue result of the user, to obtain a trained overdue prediction model.
The display device 103 may be configured to display a predicted result of overdue behavior of any target user.
The display device may also be a touch display screen for receiving user instructions while displaying the above to enable operational interaction with the user.
It should be understood that the above-described processor may be implemented by a processor that reads instructions in a memory and executes the instructions, or may be implemented by a chip circuit.
In addition, the network architecture and the service scenario described in the embodiments of the present application are for more clearly describing the technical solution of the embodiments of the present application, and do not constitute a limitation on the technical solution provided in the embodiments of the present application, and as a person of ordinary skill in the art can know, with evolution of the network architecture and appearance of a new service scenario, the technical solution provided in the embodiments of the present application is also applicable to similar technical problems.
Fig. 2 is a flow chart of a user overdue data processing method according to an embodiment of the present application, and the execution subject of the embodiment may be a computer device in the embodiment shown in fig. 1, or may be another service device with similar functions, which is not particularly limited herein. As shown in fig. 2, the method includes:
s201: and acquiring the original business data of a preset number of users in a first time period.
The raw business data may include, but is not limited to, the user's credit line, time to open an account, average monthly consumption, number of arrearages, amount arrearages, and average duration of arrearages, among others.
Specifically, original service data of a preset number of users in a first time period is obtained to serve as a training set.
Specifically, after obtaining the original service data of the preset number of users in the first period, the method further includes: and cleaning the data of the original business data. Typically, data cleansing requires processing in 7 steps, selecting subsets, renaming column names, deleting duplicate values, missing value processing, reconciliation processing, data ordering processing, and outlier processing. Selecting a subset: that is, the data columns in the data set to be analyzed are selected, and other data columns not participating in the analysis can be hidden to avoid interference. Column name renaming: if the same column name appears in the data set or two column names with the same meaning, the column name of a certain data column needs to be renamed to avoid interference with the analysis result. Deleting duplicate values: deleting duplicate data values in the data, taking care that only the first piece of data of the duplicate data will be retained. Missing value processing: the original service data may have missing data values, that is, there are no data cells in the data set, which affects the result during data analysis, and the missing data values need to be complemented. And (3) carrying out unification treatment: in the data set, the data value standard of a certain data column is inconsistent or the naming rule is inconsistent, and the data value in the inconsistent data column can be split by using a column splitting function. Data sorting processing: and screening and sorting the data in the data set, and arranging the data in ascending order or descending order. Outlier processing: processing is performed by a method of processing missing values. Different treatments are performed for different cases of whether the outlier is completely random missing, random missing or non-random missing.
S202: and calculating overdue grade characteristics of each user according to the original service data of each user, wherein the overdue grade characteristics are used for representing the severity of overdue arrearages of the users.
The original business data of each user comprises arrearage amount of each user in a preset time period.
Illustratively, the original business data of each user includes an overdue arrearage amount accumulated by each user in the month.
Specifically, step S202 includes S2021 to S2022:
s2021: and obtaining the arrearage amount of each user in a preset time period.
Specifically, the arrearage amount of each user in a preset time period is extracted from the original business data of each user.
S2022: and determining the overdue grade characteristic of each user in the preset time period according to the arrearage amount in the preset time period.
The overdue grade characteristic of each user in the preset time period is used for representing the severity of overdue arrearages of each user in the preset time period, and the higher the grade of the overdue grade characteristic is, the greater the severity of overdue arrearages of the user in the preset time period is.
Specifically, step S2022 includes Sa to Se:
sa: and judging whether the arrearage amount in the preset time period is larger than 0.
Sb: if the arrearage amount in the preset time period is not more than 0, judging that the overdue grade characteristic of each user in the preset time period is a first overdue grade; if the arrearage amount of the preset time period is greater than 0, judging whether the arrearage amount of each user in the last preset time period is greater than 0.
Sc: if the arrearage amount of the last preset time period is not more than 0, judging that the overdue grade characteristic of each user in the preset time period is a second overdue grade, wherein the higher the grade of the overdue grade characteristic is, the greater the severity of overdue arrearage of the user is indicated.
Sd: if the arrearage amount of the last preset time period is larger than 0, calculating the ratio of the arrearage amount of each user in the preset time period to the arrearage amount of the last preset time period.
Se: and determining the overdue grade characteristic of each user in a preset time period according to the ratio.
Specifically, the step Se comprises Se1 to Se3:
se1: if the ratio is smaller than the first threshold, determining that the overdue grade characteristic of each user in the preset time period is the overdue grade characteristic of the last preset time period minus 1.
Se2: if the ratio is greater than or equal to the first threshold and less than the second threshold, determining that the overdue grade characteristic of each user in the preset time period is the overdue grade characteristic of the last preset time period.
Se3: if the ratio is greater than the second threshold, determining that the overdue grade feature of each user in the preset time period is the overdue grade feature of the last preset time period plus 1.
Exemplary, it is determined whether the accumulated overdue arrears of any user are greater than 0, and if the accumulated overdue arrears of any user are not greater than 0, the overdue rank of any user is determined to be characterized as L 0 If the accumulated overdue arrearage of any user in the current month is greater than 0, continuously judging whether the accumulated overdue arrearage of any user in the current month is greater than 0; if the accumulated overdue arrearage of any user is not more than 0 in the last month, determining that the overdue grade characteristic of any user is L 1 If the accumulated overdue arrearage of any user in the month is larger than 0, calculating the ratio of the accumulated overdue arrearage of any user in the month to the accumulated overdue arrearage in the month, if the ratio is larger than or equal to 1, judging that the overdue grade of any user is characterized by adding 1 to the overdue grade in the month, if the ratio is larger than 0.7 and smaller than 1, judging that the overdue grade of any user is characterized by not changing the overdue grade in the month, and if the ratio is smaller than or equal to 0.7, judging that the overdue grade of any user is characterized by subtracting 1 from the overdue grade in the month. When the user's overdue ranking features drop to L 1 And no further decline.
S203: the service characteristics of each user are obtained from the original service data.
S204: according to the overdue grade characteristics and the service characteristics of each user and the overdue results of the pre-marked users, performing iterative training on the initial overdue prediction model to obtain a trained overdue prediction model; the trained overdue prediction model is used for predicting overdue behaviors of any target user.
Specifically, the overdue grade feature and service feature of each user and the pre-marked overdue result of the user are input into an initial overdue prediction model, for example, a Logit model (assessment model) for iterative training, so as to obtain a trained overdue prediction model.
In summary, the initial overdue prediction model is input into the initial overdue prediction model for iterative training through the original business data of the preset number of users in the first time period, the overdue grade characteristics of each user and the overdue result of each user preset mark, the trained overdue prediction model is obtained, overdue behaviors of any user are predicted through the trained overdue prediction model, and the effect of accurately predicting the overdue behaviors of the users can be achieved.
On the basis of the above embodiment, after obtaining the trained overdue prediction model in step S204, the method further includes Sh to Sk:
sh: and acquiring service data of a preset number of users in a second time period.
Wherein the business data of the user in the second time period can include, but is not limited to, credit line of the user, account opening time, average month consumption, arrearage number, arrearage amount and average arrearage duration.
Specifically, service data of a preset number of users in a second time period is obtained as a test set.
Si: and inputting the service data of each user into the trained overdue prediction model to obtain a predicted overdue result corresponding to each user.
Specifically, according to the arrearage amount of the preset time period in the service data of each user, the overdue grade characteristic of each user is calculated, and the overdue grade characteristic of each user and the service data are input into a trained overdue prediction model to obtain a predicted overdue result corresponding to each user.
Sj: and calculating an error according to the pre-marked user overdue result and the predicted overdue result corresponding to each user.
The error is used to measure the performance of the overdue prediction model, and the deviation and variance can be used as the basis. A highly biased model always makes strong assumptions about the data distribution, while a highly biased model always relies heavily on its training set, thus requiring a trade-off between the two.
Specifically, a mlxtend library is installed, and bias and variance are evaluated using the bias_variance_decomp () function on the model in a multiple self-sampling manner.
Sk: and based on the error, adjusting the trained overdue prediction model to obtain a final overdue prediction model.
Specifically, if the overdue prediction model is fitted excessively, more business data of the user in the second time period are obtained from the data, so that the overdue prediction model learns more effective features, and the influence of noise is reduced. When the data is less, the complexity of the overdue prediction model is properly reduced. If the overdue predictive model is not fit, new features are added, or the model complexity is increased.
In summary, the overdue prediction model is tested by using the test set, and the comparison analysis is performed on the pre-marked user overdue result and the predicted overdue result corresponding to each user according to the pre-marked user overdue result and the error of the predicted overdue result corresponding to each user, so that the trained overdue prediction model is adjusted to obtain a final overdue prediction model, and the accuracy of the overdue prediction model can be further enhanced.
FIG. 3 is a schematic diagram illustrating a structure of a user overdue data processing apparatus according to an embodiment of the present application. As shown in fig. 3, the user overdue data processing apparatus includes: the system comprises a first business data acquisition module 301, an overdue class calculation module 302, a business feature extraction module 303 and a model training module 304.
The first service data obtaining module 301 is configured to obtain original service data of a preset number of users in a first period of time.
The overdue class calculation module 302 is configured to calculate overdue class characteristics of each user according to original service data of each user, where the overdue class characteristics are used to characterize severity of overdue arrearages of the users.
The service feature extraction module 303 is configured to obtain a service feature of each user from the original service data.
The model training module 304 is configured to iteratively train the initial overdue prediction model according to overdue class characteristics and service characteristics of each user and the pre-labeled overdue result of the user, so as to obtain a trained overdue prediction model; the trained overdue prediction model is used for predicting overdue behaviors of any target user.
In one possible implementation, the overdue level calculation module 302 is specifically configured to obtain an arrearage amount of each user in a preset period of time; and determining the overdue grade characteristic of each user in the preset time period according to the arrearage amount in the preset time period.
In one possible implementation, the overdue level calculation module 302 is specifically configured to determine whether the arrearage amount in the preset time period is greater than 0; if the arrearage amount in the preset time period is not more than 0, judging that the overdue grade characteristic of each user in the preset time period is a first overdue grade; if the arrearage amount of the preset time period is greater than 0, judging whether the arrearage amount of each user in the last preset time period is greater than 0; if the arrearage amount of the last preset time period is not more than 0, judging that the overdue grade characteristic of each user in the preset time period is a second overdue grade, wherein the higher the grade of the overdue grade characteristic is, the greater the severity of overdue arrearage of the user is represented; if the arrearage amount of the last preset time period is greater than 0, calculating the ratio of the arrearage amount of each user in the preset time period to the arrearage amount of the last preset time period; and determining the overdue grade characteristic of each user in a preset time period according to the ratio.
In one possible implementation, the overdue level calculation module 302 is specifically configured to determine that the overdue level characteristic of each user in the preset time period is the overdue level characteristic of the previous preset time period minus 1 if the ratio is smaller than the first threshold. If the ratio is greater than or equal to the first threshold and less than the second threshold, determining that the overdue grade characteristic of each user in the preset time period is the overdue grade characteristic of the last preset time period. If the ratio is greater than the second threshold, determining that the overdue grade feature of each user in the preset time period is the overdue grade feature of the last preset time period plus 1.
In one possible implementation, the user overdue data processing apparatus further includes: a second business data acquisition module 305, an expected result prediction module 306, an error calculation module 307, and a model adjustment module 308.
A second service data obtaining module 305, configured to obtain service data of a preset number of users in a second period of time.
The expected result prediction module 306 is configured to input the service data of each user into the trained overdue prediction model, so as to obtain a predicted overdue result corresponding to each user.
The error calculation module 307 is configured to calculate an error according to the pre-marked user overdue result and the predicted overdue result corresponding to each user.
The model adjustment module 308 is configured to adjust the trained overdue prediction model based on the error, so as to obtain a final overdue prediction model.
The device provided in this embodiment may be used to implement the technical solution of the foregoing method embodiment, and its implementation principle and technical effects are similar, and this embodiment will not be described herein again.
Fig. 4 is a schematic hardware structure of a computer device according to an embodiment of the present application. As shown in fig. 4, the computer device of the present embodiment includes: at least one processor 401 and a memory 402; the memory stores computer-executable instructions; at least one processor executes computer-executable instructions stored in the memory that cause the at least one processor to perform the user-overdue data processing method as described above.
Alternatively, the memory 402 may be separate or integrated with the processor 401.
When the memory 402 is provided separately, the service device further comprises a bus 403 for connecting said memory 402 and the processor 401.
The embodiment of the application also provides a computer readable storage medium, wherein computer execution instructions are stored in the computer readable storage medium, and when a processor executes the computer execution instructions, the overdue data processing method for the user is realized.
Embodiments of the present application also provide a computer program product comprising a computer program which, when executed by a processor, implements a user overdue data processing method as described above.
It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all alternative embodiments, and that the acts and modules referred to are not necessarily required in the present application.
It should be further noted that, although the steps in the flowchart are sequentially shown as indicated by arrows, the steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least a portion of the steps in the flowcharts may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order in which the sub-steps or stages are performed is not necessarily sequential, and may be performed in turn or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
It should be understood that the above-described device embodiments are merely illustrative, and that the device of the present application may be implemented in other ways. For example, the division of the units/modules in the above embodiments is merely a logic function division, and there may be another division manner in actual implementation. For example, multiple units, modules, or components may be combined, or may be integrated into another system, or some features may be omitted or not performed.
In addition, each functional unit/module in each embodiment of the present application may be integrated into one unit/module, or each unit/module may exist alone physically, or two or more units/modules may be integrated together, unless otherwise specified. The integrated units/modules described above may be implemented either in hardware or in software program modules.
The integrated units/modules, if implemented in hardware, may be digital circuits, analog circuits, etc. Physical implementations of hardware structures include, but are not limited to, transistors, memristors, and the like. The processor may be any suitable hardware processor, such as CPU, GPU, FPGA, DSP and ASIC, etc., unless otherwise specified. Unless otherwise indicated, the storage elements may be any suitable magnetic or magneto-optical storage medium, such as resistive Random Access Memory RRAM (Resistive Random Access Memory), dynamic Random Access Memory DRAM (Dynamic Random Access Memory), static Random Access Memory SRAM (Static Random-Access Memory), enhanced dynamic Random Access Memory EDRAM (Enhanced Dynamic Random Access Memory), high-Bandwidth Memory HBM (High-Bandwidth Memory), hybrid Memory cube HMC (Hybrid Memory Cube), etc.
The integrated units/modules may be stored in a computer readable memory if implemented in the form of software program modules and sold or used as a stand-alone product. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a memory, including several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned memory includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments. The technical features of the foregoing embodiments may be arbitrarily combined, and for brevity, all of the possible combinations of the technical features of the foregoing embodiments are not described, however, all of the combinations of the technical features should be considered as being within the scope of the disclosure.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims (10)

1. A method for processing overdue data of a user, comprising:
acquiring original business data of a preset number of users in a first time period;
calculating overdue grade characteristics of each user according to the original service data of each user, wherein the overdue grade characteristics are used for representing the severity of overdue arrearages of the users;
acquiring service characteristics of each user from the original service data;
according to the overdue grade characteristics and the service characteristics of each user and the preset overdue results of the users, performing iterative training on the initial overdue prediction model to obtain a trained overdue prediction model;
the trained overdue prediction model is used for predicting overdue behaviors of any target user.
2. The method of claim 1, wherein the original service data of each user comprises: the arrearage amount of each user in a preset time period;
correspondingly, the calculating the overdue grade characteristic of each user according to the original business data of each user comprises the following steps:
acquiring the arrearage amount of each user in a preset time period;
and determining the overdue grade characteristic of each user in the preset time period according to the arrearage amount in the preset time period.
3. The method of claim 2, wherein determining the overdue ranking characteristic of each user for the preset time period based on the arrearage amount for the preset time period comprises:
judging whether the arrearage amount of the preset time period is larger than 0;
if the arrearage amount in the preset time period is not more than 0, judging that the overdue grade characteristic of each user in the preset time period is a first overdue grade; if the arrearage amount of the preset time period is greater than 0, judging whether the arrearage amount of each user in the last preset time period is greater than 0;
if the arrearage amount of the last preset time period is not more than 0, judging that the overdue grade characteristic of each user in the preset time period is a second overdue grade, wherein the higher the grade of the overdue grade characteristic is, the greater the severity of overdue arrearages of the users is represented;
if the arrearage amount of the last preset time period is greater than 0, calculating the ratio of the arrearage amount of each user in the preset time period to the arrearage amount of each user in the last preset time period;
and determining the overdue grade characteristic of each user in the preset time period according to the ratio.
4. The method of claim 3, wherein said determining the overdue ranking characteristic of each user for the preset time period based on the ratio comprises:
if the ratio is smaller than a first threshold, determining that the overdue grade characteristic of each user in the preset time period is 1 less than the overdue grade characteristic of the last preset time period;
if the ratio is greater than or equal to a first threshold and less than a second threshold, determining that the overdue grade characteristic of each user in the preset time period is the overdue grade characteristic of the last preset time period;
if the ratio is greater than a second threshold, determining that the overdue grade characteristic of each user in the preset time period is the overdue grade characteristic of the last preset time period plus 1.
5. The method of any one of claims 1 to 4, further comprising, after the obtaining the trained overdue prediction model:
acquiring business data of a preset number of users in a second time period;
inputting the service data of each user into the trained overdue prediction model to obtain a predicted overdue result corresponding to each user;
calculating an error according to the preset marked user overdue result and the preset overdue result corresponding to each user;
and based on the error, adjusting the trained overdue prediction model to obtain a final overdue prediction model.
6. A user overdue data processing apparatus, comprising:
the first service data acquisition module is used for acquiring original service data of a preset number of users in a first time period;
the overdue grade calculation module is used for calculating overdue grade characteristics of each user according to original service data of each user, wherein the overdue grade characteristics are used for representing the severity of overdue arrearages of the users;
the service feature extraction module is used for acquiring the service features of each user from the original service data;
the model training module is used for carrying out iterative training on the initial overdue prediction model according to the overdue grade characteristics and the service characteristics of each user and the preset overdue result of the user so as to obtain a trained overdue prediction model; the trained overdue prediction model is used for predicting overdue behaviors of any target user.
7. The apparatus of claim 6, wherein the original service data of each user comprises: the arrearage amount of each user in a preset time period;
correspondingly, the overdue grade calculation module is specifically configured to obtain an arrearage amount of each user in a preset time period; and determining the overdue grade characteristic of each user in the preset time period according to the arrearage amount in the preset time period.
8. The apparatus of claim 7, wherein the device comprises a plurality of sensors,
the overdue grade calculation module is specifically configured to determine whether an arrearage amount in the preset time period is greater than 0; if the arrearage amount in the preset time period is not more than 0, judging that the overdue grade characteristic of each user in the preset time period is a first overdue grade; if the arrearage amount of the preset time period is greater than 0, judging whether the arrearage amount of each user in the last preset time period is greater than 0; if the arrearage amount of the last preset time period is not more than 0, judging that the overdue grade characteristic of each user in the preset time period is a second overdue grade, wherein the higher the grade of the overdue grade characteristic is, the greater the severity of overdue arrearages of the users is represented; if the arrearage amount of the last preset time period is greater than 0, calculating the ratio of the arrearage amount of each user in the preset time period to the arrearage amount of each user in the last preset time period; and determining the overdue grade characteristic of each user in the preset time period according to the ratio.
9. A computer device, comprising: a processor, and a memory communicatively coupled to the processor;
the memory stores computer-executable instructions;
the processor executes computer-executable instructions stored in the memory to implement the method of any one of claims 1 to 5.
10. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1 to 5.
CN202311418492.1A 2023-10-30 2023-10-30 User overdue data processing method, device, equipment and storage medium Pending CN117473366A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311418492.1A CN117473366A (en) 2023-10-30 2023-10-30 User overdue data processing method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311418492.1A CN117473366A (en) 2023-10-30 2023-10-30 User overdue data processing method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN117473366A true CN117473366A (en) 2024-01-30

Family

ID=89626800

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311418492.1A Pending CN117473366A (en) 2023-10-30 2023-10-30 User overdue data processing method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117473366A (en)

Similar Documents

Publication Publication Date Title
Hertz Trends in the intergenerational elasticity of family income in the United States
Martin et al. Return migration: the experience of Eastern Europe 1
Blanden et al. Educational inequality and the expansion of UK higher education
Vishwanath Impact of personality on technology adoption: An empirical model
Blume et al. Welfare dependency among Danish immigrants
Hermanto et al. Waiting-time estimation in bank customer queues using RPROP neural networks
CN110069545B (en) Behavior data evaluation method and device
Kapur et al. Bayesian mixed‐effects location and scale models for multivariate longitudinal outcomes: an application to ecological momentary assessment data
El-Attar Trust, child care technology choice and female labor force participation
Kujala et al. The Cross-Sequential Approach: A Short-Term Method for Studying Long-Term User Experience.
Belzil et al. A structural analysis of the correlated random coefficient wage regression model
Summerfield et al. The effects of macroeconomic conditions at graduation on overeducation
de Bresser et al. Survey response in probabilistic questions and its impact on inference
Kaneko A time-series analysis of how google trends searches affect cryptocurrency prices for decentralized finance and non-fungible tokens
Ogawa et al. Effects of cognitive ability and age on giving in dictator game experiments
Winsberg Communicating uncertainty to policymakers: the ineliminable role of values
CN117473366A (en) User overdue data processing method, device, equipment and storage medium
Vanhuele et al. Probability Models for Duration: The Data Don′ t Tell the Whole Story
Carleton et al. Radiocarbon dating uncertainty and the reliability of the PEWMA method of time-series analysis for research on long-term human-environment interaction
Jensen et al. Do long swings in the business cycle lead to strong persistence in output?
Pak et al. The rich get richer? Limited learning in charitable giving on donorschoose. org
Cockx et al. The exhaustion of unemployment benefits in Belgium: Does it enhance the probability of employment?
Mendelson et al. Growth and customer loyalty: Evidence from the app economy
Gandhi et al. Estimating reliability for OSS: An approach with change-point in operational phase
CN112150276A (en) Training method, using method, device and equipment of machine learning model

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