Analysis methods, apparatus, equipment and media for vintage-like indicators

Abstract

This invention discloses a method, apparatus, device, and computer-readable storage medium for analyzing vintage-like indicators, relating to the field of risk data analysis technology. The method includes: acquiring underlying raw data; for each key value under the detailed primary key in the underlying raw data, calculating the wide table row information corresponding to each key value based on the detailed data corresponding to each key value in the underlying raw data, to obtain a target wide table composed of the wide table row information of each key value; upon receiving a statistical instruction for a vintage-like indicator, searching in the target wide table for each target key value corresponding to the target statistical dimension indicated by the statistical instruction, and calculating the vintage-like indicator value under the target statistical dimension according to the intermediate data corresponding to each target key value. This invention proposes an analysis scheme for vintage-like indicators, reducing the complexity of vintage indicator analysis operations and improving analysis efficiency.

Description

Technical Field

[0001] This invention relates to the field of risk data analysis technology, and in particular to a method, apparatus, device, and computer-readable storage medium for analyzing vintage-like indicators. Background Technology

[0002] Vintage-like metrics are a commonly used analytical method in the field of data analysis. By comparing the results of customers in different performance periods during the same period, problems can be identified in a timely manner. Vintage-like metrics are characterized by complex calculations, large computational load, and flexible and variable definitions. In practice, many business personnel lack SQL writing skills and cannot flexibly compare vintage metric values ​​across different dimensions. Even analysts with SQL skills need to run data analyses frequently due to the complexity of vintage metrics, resulting in low analytical efficiency. Summary of the Invention

[0003] The main objective of this invention is to provide a method, apparatus, device, and computer-readable storage medium for analyzing vintage-like indicators, aiming to propose an analysis scheme for vintage-like indicators, reduce the complexity of vintage indicator analysis operations, and improve analysis efficiency.

[0004] To achieve the above objectives, this invention provides an analysis method for vintage-like indicators, the method comprising:

[0005] Obtain the underlying raw data;

[0006] For each key value under the detailed primary key in the underlying original data, the wide table row information corresponding to each key value is calculated based on the detailed data corresponding to each key value in the underlying original data, so as to obtain the target wide table composed of the wide table row information of each key value. The wide table row information includes time information, aging information and intermediate data used to calculate the vintage index value corresponding to the key value.

[0007] Upon receiving a statistical instruction for a vintage-like metric, the system searches the target wide table for each target key value corresponding to the target statistical dimension indicated by the statistical instruction, and calculates the vintage-like metric value under the target statistical dimension according to the intermediate data corresponding to each target key value.

[0008] Optionally, the wide table row information also includes dimension information corresponding to the key value, and the dimension information includes field values ​​under at least one dimension field corresponding to the key value;

[0009] After the step of calculating the wide table row information corresponding to each key value based on the detailed data corresponding to each key value in the underlying original data, to obtain the target wide table composed of the wide table row information of each key value, the method further includes:

[0010] Use the time field, the aforementioned dimension field, and the aging field as selectable statistical dimensions.

[0011] Optionally, after the step of selecting the time field, the dimension field, and the aging field as selectable statistical dimensions, the method further includes:

[0012] The statistical instruction is triggered in response to the selection operation of each of the selected statistical dimensions, wherein the statistical instruction indicates the statistical dimension selected by the selection operation as the target statistical dimension, and the selection operation is an operation of dragging the visual control corresponding to the selected statistical dimension to the target area or an operation of entering the selected statistical dimension in the input window.

[0013] Optionally, after the step of calculating the wide table row information corresponding to each key value based on the detailed data corresponding to each key value in the underlying original data to obtain the target wide table composed of the wide table row information of each key value, the method further includes:

[0014] Upon receiving a table association instruction, the table to be associated as indicated by the table association instruction is associated with the target wide table according to the detailed primary key. The table to be associated includes dimension information corresponding to each key value, and the dimension information includes field values ​​under at least one dimension field corresponding to the key value.

[0015] Optionally, after the step of calculating the vintage-like index value under the target statistical dimension according to the intermediate data corresponding to each target key value, the method further includes:

[0016] Using the time information and the aging information as two display dimensions, the vintage-like indicator value under the target statistical dimension is visualized and output.

[0017] Optionally, the intermediate data includes intermediate data for calculating vintage-like indicator values ​​with different statistical calibers; the step of calculating the vintage-like indicator value under the target statistical dimension according to the intermediate data corresponding to each target key value includes:

[0018] Determine the target statistical caliber indicated in the statistical instruction, and calculate the target statistical dimension and the vintage index value under the target statistical caliber according to the intermediate data corresponding to the intermediate data of each target key value.

[0019] Optionally, when the vintage-like indicator value is the delinquency rate, the intermediate data corresponding to the key value used to calculate the vintage-like indicator value includes data indicating whether each month of the loan is overdue and / or data indicating the overdue amount and total loan amount for each month of the loan.

[0020] The step of calculating the vintage-like index value under the target statistical dimension according to the intermediate data corresponding to each target key value includes:

[0021] Based on the data corresponding to each target key value, which indicates whether the payment is overdue for each month, calculate the customer delinquency rate under the target statistical dimension; and / or,

[0022] Calculate the overdue rate under the target statistical dimension based on the data corresponding to each target key value, which indicates the overdue amount and total loan amount for each month of the outstanding balance.

[0023] To achieve the above objectives, the present invention also provides an analysis device for a type of vintage index, the device comprising:

[0024] The acquisition module is used to acquire the raw data from the underlying data warehouse.

[0025] The calculation module is used to calculate the wide table row information corresponding to each key value under the detailed primary key in the underlying original data, based on the detailed data corresponding to each key value in the underlying original data, so as to obtain a target wide table composed of the wide table row information of each key value. The wide table row information includes time information, aging information and intermediate data for calculating the vintage index value corresponding to the key value.

[0026] The statistics module is used to, upon receiving a statistical instruction for a vintage-like indicator, search the target wide table for each target key value corresponding to the target statistical dimension indicated by the statistical instruction, and calculate the vintage-like indicator value under the target statistical dimension according to the intermediate data corresponding to each target key value.

[0027] To achieve the above objectives, the present invention also provides a device for analyzing vintage-like indicators. The device includes a memory, a processor, and a program for analyzing vintage-like indicators stored in the memory and executable on the processor. When the program for analyzing vintage-like indicators is executed by the processor, it implements the steps of the method for analyzing vintage-like indicators as described above.

[0028] Furthermore, to achieve the above objectives, the present invention also proposes a computer-readable storage medium storing an analysis program for a type of vintage index, wherein when the analysis program for the type of vintage index is executed by a processor, it implements the steps of the analysis method for the type of vintage index as described above.

[0029] In this embodiment of the invention, by acquiring the underlying raw data, for each key value under the detailed primary key in the underlying raw data, the wide table row information corresponding to each key value is calculated based on the detailed data corresponding to each key value in the underlying raw data, to obtain a target wide table composed of the wide table row information of each key value. The wide table row information includes time information, aging information, and intermediate data used to calculate the vintage-like indicator value corresponding to the key value. After receiving the statistical instruction for the vintage-like indicator, the target wide table is searched for each target key value corresponding to the target statistical dimension indicated by the statistical instruction, and the vintage-like indicator value under the target statistical dimension is calculated according to the intermediate data corresponding to each target key value. In this embodiment of the invention, the underlying raw data is processed to form a basic wide table. When business personnel need to analyze the vintage-like indicator, the vintage-like indicator value can be obtained by simple addition and subtraction based on the wide table. Compared to directly calculating various vintage indicator values ​​and providing them to business personnel, this embodiment provides intermediate data corresponding to each key value under the detailed primary key for calculating vintage indicator values. Business personnel can then select the required statistical dimensions and statistical standards for analysis, making it more convenient and flexible. Attached Figure Description

[0030] Figure 1 This is a schematic diagram of the hardware operating environment involved in the embodiments of the present invention;

[0031] Figure 2 This is a flowchart illustrating the first embodiment of the vintage index analysis method of the present invention;

[0032] Figure 3 This is a schematic diagram illustrating a method for displaying vintage index values ​​according to an embodiment of the present invention;

[0033] Figure 4 This is an example diagram of a target wide table according to an embodiment of the present invention;

[0034] Figure 5 This is a schematic diagram of the functional modules of a preferred embodiment of the vintage index analysis device of the present invention.

[0035] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0036] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0037] like Figure 1 As shown, Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiments of the present invention.

[0038] It should be noted that the analysis device for the vintage index in this embodiment of the invention can be a smartphone, personal computer, server, or other device, and no specific limitation is made here.

[0039] like Figure 1 As shown, the device for analyzing this type of vintage metric may include: a processor 1001, such as a CPU; a network interface 1004; a user interface 1003; a memory 1005; and a communication bus 1002. The communication bus 1002 is used to establish communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or stable, non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0040] Those skilled in the art will understand that Figure 1 The device structure shown does not constitute a limitation on the analysis device for vintage-like indicators, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0041] like Figure 1 As shown, the memory 1005, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a vintage-style indicator analysis program. The operating system is a program that manages and controls the device's hardware and software resources, supporting the operation of the vintage-style indicator analysis program and other software or programs. Figure 1 In the device shown, the user interface 1003 is mainly used for data communication with the client; the network interface 1004 is mainly used for establishing a communication connection with the server; and the processor 1001 can be used to call the vintage-type indicator analysis program stored in the memory 1005 and perform the following operations:

[0042] Obtain the underlying raw data;

[0043] For each key value under the detailed primary key in the underlying original data, the wide table row information corresponding to each key value is calculated based on the detailed data corresponding to each key value in the underlying original data, so as to obtain the target wide table composed of the wide table row information of each key value. The wide table row information includes time information, aging information and intermediate data used to calculate the vintage index value corresponding to the key value.

[0044] Upon receiving a statistical instruction for a vintage-like metric, the system searches the target wide table for each target key value corresponding to the target statistical dimension indicated by the statistical instruction, and calculates the vintage-like metric value under the target statistical dimension according to the intermediate data corresponding to each target key value.

[0045] In one feasible implementation, the wide table row information further includes dimension information corresponding to the key value, and the dimension information includes field values ​​under at least one dimension field corresponding to the key value;

[0046] After the step of calculating the wide table row information corresponding to each key value based on the detailed data corresponding to each key value in the underlying raw data to obtain the target wide table composed of the wide table row information of each key value, the processor 1001 can also call the analysis program of the vintage index stored in the memory 1005 to perform the following operations:

[0047] Use the time field, the aforementioned dimension field, and the aging field as selectable statistical dimensions.

[0048] In one feasible implementation, after the operation of selecting the time field, the dimension field, and the aging field as selectable statistical dimensions, the processor 1001 can also be used to call the analysis program for the vintage-like indicator stored in the memory 1005 to perform the following operations:

[0049] The statistical instruction is triggered in response to the selection operation of each of the selected statistical dimensions, wherein the statistical instruction indicates the statistical dimension selected by the selection operation as the target statistical dimension, and the selection operation is an operation of dragging the visual control corresponding to the selected statistical dimension to the target area or an operation of entering the selected statistical dimension in the input window.

[0050] In one feasible implementation, after the operation of calculating the wide table row information corresponding to each key value based on the detailed data corresponding to each key value in the underlying raw data to obtain the target wide table composed of the wide table row information of each key value, the processor 1001 can also be used to call the analysis program of the vintage index stored in the memory 1005 to perform the following operations:

[0051] Upon receiving a table association instruction, the table to be associated as indicated by the table association instruction is associated with the target wide table according to the detailed primary key. The table to be associated includes dimension information corresponding to each key value, and the dimension information includes field values ​​under at least one dimension field corresponding to the key value.

[0052] In one feasible implementation, after the operation of calculating the vintage-like index value under the target statistical dimension according to the intermediate data corresponding to each target key value, the processor 1001 can also be used to call the vintage-like index analysis program stored in the memory 1005 to perform the following operations:

[0053] Using the time information and the aging information as two display dimensions, the vintage-like indicator value under the target statistical dimension is visualized and output.

[0054] In one feasible implementation, the intermediate data includes intermediate data for calculating vintage-like indicator values ​​with different statistical calibers; the operation of calculating the vintage-like indicator value under the target statistical dimension according to the intermediate data corresponding to each target key value includes:

[0055] Determine the target statistical caliber indicated in the statistical instruction, and calculate the target statistical dimension and the vintage index value under the target statistical caliber according to the intermediate data corresponding to the intermediate data of each target key value.

[0056] In one feasible implementation, when the vintage-like indicator value is the delinquency rate, the intermediate data corresponding to the key value used to calculate the vintage-like indicator value includes data indicating whether each month of the loan is overdue and / or data indicating the overdue amount and total loan amount for each month of the loan.

[0057] The operation of calculating the vintage-like index value under the target statistical dimension according to the intermediate data corresponding to each target key value includes:

[0058] Based on the data corresponding to each target key value, which indicates whether the payment is overdue for each month, calculate the customer delinquency rate under the target statistical dimension; and / or,

[0059] Calculate the overdue rate under the target statistical dimension based on the data corresponding to each target key value, which indicates the overdue amount and total loan amount for each month of the outstanding balance.

[0060] Based on the above structure, various embodiments of the analysis method for vintage-like indicators are proposed.

[0061] Reference Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the vintage index analysis method of the present invention.

[0062] This invention provides an embodiment of a method for analyzing vintage-like metrics. It should be noted that although the flowchart shows a logical order, in some cases, the steps shown or described may be executed in a different order. In this embodiment, the executing entity of the method for analyzing vintage-like metrics can be a personal computer, server, smartphone, or other device; no limitation is made in this embodiment. For ease of description, the execution entity is omitted from the following description of each embodiment. In this embodiment, the method for analyzing vintage-like metrics includes steps S10 to S30:

[0063] Step S10: Obtain the underlying raw data.

[0064] Vintage-like metrics are a commonly used analytical method in the field of data analytics. By comparing the results of customers in the same period at different performance periods, problems can be identified in a timely manner. In actual business scenarios, there are various types of vintage-like metrics, such as delinquency rate, default rate, and customer retention rate. Different business scenarios have different metric requirements. For example, the marketing side will look at customer retention rate; the risk side will look at default or delinquency rates at different withdrawal points; and when calculating the overall accounts for operations management, metrics such as risk cost ratio will be considered. In this embodiment, there is no restriction on what specific type of vintage-like metric is used.

[0065] The underlying raw data is the original data used to calculate vintage-type metric values. It has not undergone aggregation or processing and contains some detailed data, with a primary key consisting of a specific field, such as customer number or order number. This will be referred to as the detailed primary key. The key values ​​under the detailed primary key are, for example, customer numbers or order numbers recorded in the business system. The detailed data corresponding to these key values ​​includes the raw data used to calculate vintage-type metric values, such as the loan amount, loan period, repayment duration, repayment amount at various time points, and overdue amount for a specific customer number. It should be noted that the detailed data listed above is only a simple example. For users to flexibly analyze different vintage-type metrics, metric values ​​under different dimensions and definitions from the underlying raw data, even with SQL capabilities, frequent data analysis runs are required, leading to complex operations and low analysis efficiency.

[0066] Step S20: For each key value under the detailed primary key in the underlying original data, calculate the wide table row information corresponding to each key value according to the detailed data corresponding to each key value in the underlying original data, so as to obtain the target wide table composed of the wide table row information of each key value. The wide table row information includes time information, aging information and intermediate data used to calculate the vintage index value corresponding to the key value.

[0067] To address the inefficiency caused by the complexity of performing vintage-like indicator analysis on underlying raw data, this embodiment processes the raw data into a basic wide table. When business personnel need to analyze vintage-like indicators, they can obtain the indicator values ​​simply by adding or subtracting from the wide table. Compared to directly providing pre-calculated vintage-like indicator values, this embodiment provides intermediate data corresponding to each key value under the detailed primary key for calculating vintage-like indicator values. Business personnel can then select the required statistical dimensions and definitions for analysis, making the process more convenient and flexible.

[0068] Specifically, taking each key value under the primary key in the underlying raw data as a unit, the wide table row information corresponding to each key value is calculated based on the detailed data corresponding to each key value in the underlying raw data. The wide table row information corresponding to a key value includes time information, aging information, and intermediate data used to calculate the value of the vintage-like indicator. Among them, time information and aging information are two display dimensions when analyzing the vintage-like indicator value. However, the specific meanings of time information and aging information will be different depending on the vintage-like indicator to be analyzed. For example, when the vintage-like indicator to be analyzed is the delinquency rate, time information can refer to the loan disbursement time, and aging information can refer to the time between a certain observation point after the loan and the loan disbursement time. Intermediate data used to calculate vintage-like metric values ​​is generally expressed as a numerator / denominator. That is, a vintage metric value is essentially a statistically derived overall proportion, such as the delinquency rate. For each key-value pair, the numerator / denominator can be calculated first. During the statistical analysis, after determining the statistical dimensions, the sum of the numerators corresponding to multiple key-value pairs under each dimension is divided by the sum of their denominators to obtain the overall proportion. For example, when the vintage-like metric to be analyzed is the delinquency rate, and the key-value pair is the customer number, the delinquency amount and total loan amount for each customer number at a specific loan disbursement time and in a specific month of outstanding payments can be calculated based on the detailed data corresponding to that customer number. This yields a wide table row for that customer number.

[0069] It should be noted that the wide table row information may also include other information, which is not limited in this embodiment. For example, it may also include dimension information.

[0070] It should be noted that when the key values ​​and detailed data under the detailed primary key in the underlying original data are dynamically added, the wide table row information corresponding to the key value can be calculated and added to the target wide table after the key value and its detailed data are added. In other words, the wide table row information in the target wide table can be dynamically added or removed.

[0071] Step S30: After receiving the statistical instruction for the vintage-like index, search the target wide table for each target key value corresponding to the target statistical dimension indicated by the statistical instruction, and calculate the vintage-like index value under the target statistical dimension according to the intermediate data corresponding to each target key value.

[0072] After calculating the target wide table, corresponding vintage-like indicator values ​​can be obtained based on statistical commands for vintage-like indicators. These commands can be triggered by business personnel using visual analytics tools. In one feasible implementation, the target wide table can also be output and displayed to business personnel within the analytics tool.

[0073] Statistical instructions can specify the desired statistical dimension (hereinafter referred to as the target statistical dimension) to business personnel. The instructions then search the target wide table for the corresponding target key values ​​and calculate the vintage-like indicator value for each target key value based on the intermediate data. For example, to calculate the delinquency rate for each month's outstanding balance, one can search the target wide table for all customer numbers (i.e., the target key values) whose loan disbursement dates fall within a given month. Then, based on the delinquency amount and total loan amount (intermediate data) for each customer number in that month's outstanding balance, the delinquency rate for that month's outstanding balance can be calculated. This process can be repeated to calculate the delinquency rate for each month's outstanding balance.

[0074] In one possible implementation, after step S30, step S40 is further included:

[0075] Step S40: Using the time information and the aging information as two display dimensions, visually output the vintage-like indicator value under the target statistical dimension.

[0076] The method of visualization output is not limited in this implementation; it can use vintage data tables or vintage curves, etc. For example... Figure 3 As shown, a method for displaying vintage-type indicator values ​​in a tabular format is given. Taking the delinquency rate as an example of the vintage indicator to be analyzed, the time information refers to the loan disbursement date, and the aging information is the aging in months (Mob).

[0077] In this embodiment, by acquiring the underlying raw data, for each key value under the detailed primary key in the underlying raw data, the wide table row information corresponding to each key value is calculated based on the detailed data corresponding to each key value in the underlying raw data, to obtain a target wide table composed of the wide table row information of each key value. The wide table row information includes time information, aging information, and intermediate data used to calculate the vintage-like indicator value corresponding to the key value. After receiving the statistical instruction for the vintage-like indicator, the target wide table is searched for each target key value corresponding to the target statistical dimension indicated by the statistical instruction, and the vintage-like indicator value under the target statistical dimension is calculated according to the intermediate data corresponding to each target key value. In this embodiment, the underlying raw data is processed to form a basic wide table. When business personnel need to analyze the vintage-like indicator, the vintage-like indicator value can be obtained by simple addition and subtraction based on the wide table. Compared to directly calculating various vintage indicator values ​​and providing them to business personnel, this embodiment provides intermediate data corresponding to each key value under the detailed primary key for calculating vintage indicator values. Business personnel can then select the required statistical dimensions and statistical standards for analysis, making it more convenient and flexible.

[0078] Based on the first embodiment described above, a second embodiment of the analysis method for vintage-type indicators of the present invention is proposed. In this embodiment, the wide table row information corresponding to the key value under the detailed primary key also includes the dimension information corresponding to the key value. The dimension information includes the field values ​​under at least one dimension field corresponding to the key value. This may include dimension fields corresponding to statistical dimensions commonly used by business personnel, such as customer age, industry, province, etc. In specific implementations, the required dimension fields can be selected as needed. Figure 4 As shown, an example of a target wide table is provided. In this example, the vintage-type indicator to be analyzed is the delinquency rate, the primary key is the customer number, the dimension fields in the dimension information include the customer's age and province, and the intermediate data includes the total loan amount and the delinquency amount.

[0079] In one feasible implementation, after step S20, the method further includes:

[0080] Step S50: Select the time field, the dimension field, and the aging field as statistical dimensions to choose from.

[0081] After constructing the target wide table, time, dimension, and aging fields can be selected as statistical dimensions. In a specific implementation, each field can be displayed visually, allowing business personnel to select them using visual analysis tools. Then, based on the selected statistical dimensions, vintage-like metric values ​​can be calculated on the target wide table. For example, business personnel can choose to calculate the delinquency rate for customers in a specific age group.

[0082] In one possible implementation, after step S50, step S60 is further included:

[0083] Step S60: In response to the selection operation of each of the selectable statistical dimensions, the statistical instruction is triggered, wherein the statistical instruction indicates the statistical dimension selected by the selection operation as the target statistical dimension, and the selection operation is an operation of dragging the visual control corresponding to the selected statistical dimension to the target area or an operation of entering the selected statistical dimension in the input window.

[0084] Visualization tools can display visual controls and target areas for each field, or display input windows. Business users can drag and drop the visual controls corresponding to the selected statistical dimensions to the target area to trigger statistical commands, or enter the selected statistical dimensions in the input window to trigger statistical commands.

[0085] This implementation does not limit the specific type of visualization analysis tool. For example, it can be a BI (Business Intelligence) visualization tool, such as Tableau (a simple desktop business intelligence tool software).

[0086] In one possible implementation, after step S20, step S70 is further included:

[0087] Step S70: After receiving the table association instruction, the table to be associated as indicated by the table association instruction is associated with the target wide table according to the detail primary key. The table to be associated includes dimension information corresponding to each key value. The dimension information includes field values ​​under at least one dimension field corresponding to the key value.

[0088] Table join commands can be triggered by business users through visual analytics tools. The command specifies the table to be joined, where the primary key is the same as the primary key of the target wide table (e.g., both are customer numbers). Therefore, the table to be joined can be linked to the target wide table based on the detail primary key. It's worth noting that when the target wide table lacks the dimension fields the business user wants to select (e.g., some commonly used dimension fields), table joins can be used to link the dimension information corresponding to the desired dimension fields to the target wide table. This allows business users to flexibly analyze vintage-like indicator values ​​under the required statistical dimensions.

[0089] Based on the first and / or second embodiments described above, a third embodiment of the vintage index analysis method of the present invention is proposed. In this embodiment, the step S30, which calculates the vintage index value under the target statistical dimension according to the intermediate data corresponding to each target key value, includes S302:

[0090] Step S302: Determine the target statistical caliber indicated in the statistical instruction, and calculate the target statistical dimension and the vintage index value under the target statistical caliber according to the intermediate data corresponding to the intermediate data of each target key value.

[0091] Because business personnel may require different statistical definitions in different business scenarios—for example, for delinquency rates, there are order-based and amount-based definitions—this embodiment supports the analytical needs of business personnel for different statistical definitions. Specifically, intermediate data includes intermediate data used to calculate vintage-like indicator values ​​for different statistical definitions. For example, when the vintage-like indicator to be analyzed is the delinquency rate, the intermediate data may include data indicating whether each month of payment is overdue, i.e., intermediate data corresponding to the customer definition, and may also include data indicating the overdue amount and total loan amount for each month of payment, i.e., intermediate data corresponding to the amount definition.

[0092] The statistical instructions can also specify the required statistical scope (hereinafter referred to as the target statistical scope for distinction). After receiving the statistical instructions, the target statistical scope can be determined, and the target statistical dimension and vintage-like indicator values ​​under the target statistical scope can be calculated according to the intermediate data corresponding to the target key value and the intermediate data corresponding to the target statistical scope. For example, the delinquency rate of each month for each billing age of customers in a certain age group can be calculated.

[0093] In one feasible implementation, step S30, which calculates the vintage-like index value under the target statistical dimension according to the intermediate data corresponding to each target key value, includes S303 and / or S304:

[0094] Step S303: Calculate the customer delinquency rate under the target statistical dimension according to the data corresponding to each target key value that indicates whether each month of payment is overdue.

[0095] Step S304: Calculate the overdue rate under the target statistical dimension according to the data corresponding to each target key value, which indicates the overdue amount and total loan amount for each month of the outstanding balance.

[0096] Furthermore, embodiments of the present invention also propose an analysis device for a vintage-like index, referring to... Figure 5 The analysis device for the vintage-like index includes:

[0097] Module 10 is used to acquire the raw data from the underlying data warehouse.

[0098] The calculation module 20 is used to calculate the wide table row information corresponding to each key value under the detailed primary key in the underlying original data, based on the detailed data corresponding to each key value in the underlying original data, so as to obtain a target wide table composed of the wide table row information of each key value. The wide table row information includes time information, aging information and intermediate data for calculating the vintage index value corresponding to the key value.

[0099] The statistics module 30 is used to, after receiving a statistical instruction for a vintage-like indicator, search the target wide table for each target key value corresponding to the target statistical dimension indicated by the statistical instruction, and calculate the vintage-like indicator value under the target statistical dimension according to the intermediate data corresponding to each target key value.

[0100] In one feasible implementation, the wide table row information further includes dimension information corresponding to the key value, and the dimension information includes field values ​​under at least one dimension field corresponding to the key value;

[0101] The device further includes:

[0102] The first output module is used to select the time field, the dimension field, and the aging field as statistical dimensions.

[0103] In one feasible embodiment, the device further includes:

[0104] A triggering module is used to trigger the statistical instruction in response to the selection operation of each of the selectable statistical dimensions, wherein the statistical instruction indicates the statistical dimension selected by the selection operation as the target statistical dimension, and the selection operation is an operation of dragging the visual control corresponding to the selected statistical dimension to the target area or an operation of entering the selected statistical dimension in the input window.

[0105] In one feasible embodiment, the device further includes:

[0106] The association module is used to associate the table to be associated with the table indicated by the table association instruction with the target wide table according to the detail primary key after receiving the table association instruction. The table to be associated includes dimension information corresponding to each key value. The dimension information includes field values ​​under at least one dimension field corresponding to the key value.

[0107] In one feasible embodiment, the device further includes:

[0108] The second output module is used to visualize and output the vintage-like indicator value under the target statistical dimension, using the time information and the account aging information as two display dimensions.

[0109] In one feasible implementation, the intermediate data includes intermediate data for calculating vintage-like indicator values ​​with different statistical calibers; the statistical module 30 is further configured to:

[0110] Determine the target statistical caliber indicated in the statistical instruction, and calculate the target statistical dimension and the vintage index value under the target statistical caliber according to the intermediate data corresponding to the intermediate data of each target key value.

[0111] In one feasible implementation, when the vintage-like indicator value is the delinquency rate, the intermediate data corresponding to the key value used to calculate the vintage-like indicator value includes data indicating whether each month of the loan is overdue and / or data indicating the overdue amount and total loan amount for each month of the loan.

[0112] The statistics module 30 is also used for:

[0113] Based on the data corresponding to each target key value, which indicates whether the payment is overdue for each month, calculate the customer delinquency rate under the target statistical dimension; and / or,

[0114] Calculate the overdue rate under the target statistical dimension based on the data corresponding to each target key value, which indicates the overdue amount and total loan amount for each month of the outstanding balance.

[0115] The extended content of the specific implementation of the analysis device for vintage indicators of the present invention is basically the same as the various embodiments of the analysis method for vintage indicators described above, and will not be repeated here.

[0116] Furthermore, embodiments of the present invention also propose a computer-readable storage medium storing an analysis program for a type of vintage index, wherein when the analysis program for the type of vintage index is executed by a processor, it implements the steps of the analysis method for the type of vintage index as described below.

[0117] The various embodiments of the analysis device and computer-readable storage medium for the vintage index of the present invention can be referred to the various embodiments of the analysis method for the vintage index of the present invention, and will not be described again here.

[0118] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0119] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0120] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0121] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. An analytical method for a vintage-like index, characterized in that, The analysis method for the vintage-like index includes the following steps: Obtain the underlying raw data; For each key value under the detailed primary key in the underlying raw data, the wide table row information corresponding to each key value is calculated based on the detailed data corresponding to each key value in the underlying raw data, so as to obtain a target wide table composed of the wide table row information of each key value. The wide table row information includes time information, aging information and intermediate data for calculating the vintage index value corresponding to the key value; the wide table row information also includes dimension information corresponding to the key value, and the dimension information includes field values ​​under at least one dimension field corresponding to the key value. Use the time field, the aforementioned dimension field, and the aging field as selectable statistical dimensions; A statistical instruction is triggered in response to a selection operation of each of the selectable statistical dimensions, wherein the statistical instruction indicates the statistical dimension selected by the selection operation as the target statistical dimension, and the selection operation is an operation of dragging the visual control corresponding to the selected statistical dimension to the target area or an operation of entering the selected statistical dimension in the input window; Upon receiving the statistical instruction for the vintage-like metric, the system searches the target wide table for each target key value corresponding to the target statistical dimension indicated by the statistical instruction, and calculates the vintage-like metric value under the target statistical dimension according to the intermediate data corresponding to each target key value.

2. The method for analyzing vintage-like indicators as described in claim 1, characterized in that, After the step of calculating the wide table row information corresponding to each key value based on the detailed data corresponding to each key value in the underlying original data, to obtain the target wide table composed of the wide table row information of each key value, the method further includes: Upon receiving a table association instruction, the table to be associated as indicated by the table association instruction is associated with the target wide table according to the detailed primary key. The table to be associated includes dimension information corresponding to each key value, and the dimension information includes field values ​​under at least one dimension field corresponding to the key value.

3. The method for analyzing vintage-like indicators as described in claim 1, characterized in that, After the step of calculating the vintage-like index value under the target statistical dimension according to the intermediate data corresponding to each target key value, the method further includes: Using the time information and the aging information as two display dimensions, the vintage-like indicator value under the target statistical dimension is visualized and output.

4. The method for analyzing vintage-like indicators as described in claim 1, characterized in that, The intermediate data includes intermediate data used to calculate vintage-like index values ​​under different statistical calibers; the step of calculating the vintage-like index value under the target statistical dimension according to the intermediate data corresponding to each target key value includes: Determine the target statistical caliber indicated in the statistical instruction, and calculate the target statistical dimension and the vintage index value under the target statistical caliber according to the intermediate data corresponding to the intermediate data of each target key value.

5. The method for analyzing vintage-like indicators as described in any one of claims 1 to 4, characterized in that, When the vintage-type indicator value is the delinquency rate, the intermediate data corresponding to the key value used to calculate the vintage-type indicator value includes data indicating whether each month of the loan is overdue and / or data indicating the overdue amount and total loan amount for each month of the loan. The step of calculating the vintage-like index value under the target statistical dimension according to the intermediate data corresponding to each target key value includes: Calculate the customer delinquency rate under the target statistical dimension based on the data corresponding to each target key value that indicates whether each month of payment is overdue. And / or, Calculate the overdue rate under the target statistical dimension based on the data corresponding to each target key value, which indicates the overdue amount and total loan amount for each month of the outstanding balance.

6. An analysis device for a vintage-like index, characterized in that, The analysis device for the vintage-like index includes: The acquisition module is used to acquire the raw data from the underlying data warehouse. The calculation module is used to calculate the wide table row information corresponding to each key value under the detailed primary key in the underlying raw data, based on the detailed data corresponding to each key value in the underlying raw data, to obtain a target wide table composed of the wide table row information of each key value. The wide table row information includes time information, aging information, and intermediate data used to calculate vintage-type indicator values ​​corresponding to the key value. The wide table row information also includes dimension information corresponding to the key value, and the dimension information includes field values ​​under at least one dimension field corresponding to the key value. The first output module is used to select the time field, the dimension field, and the aging field as statistical dimensions; A triggering module is used to trigger a statistical instruction in response to a selection operation of each of the selectable statistical dimensions, wherein the statistical instruction indicates the statistical dimension selected by the selection operation as the target statistical dimension, and the selection operation is an operation of dragging the visual control corresponding to the selected statistical dimension to the target area or an operation of entering the selected statistical dimension in the input window. The statistics module is used to, upon receiving the statistical instruction for the vintage-like indicator, search the target wide table for each target key value corresponding to the target statistical dimension indicated by the statistical instruction, and calculate the vintage-like indicator value under the target statistical dimension according to the intermediate data corresponding to each target key value.

7. An analysis device for a type of vintage index, characterized in that, The device for analyzing vintage-like metrics includes: a memory, a processor, and a program for analyzing vintage-like metrics stored in the memory and executable on the processor. When the program for analyzing vintage-like metrics is executed by the processor, it implements the steps of the method for analyzing vintage-like metrics as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an analysis program for a vintage-like index, which, when executed by a processor, implements the steps of the analysis method for a vintage-like index as described in any one of claims 1 to 5.

Images