Term mismatch risk assessment method, device, equipment, medium and product

Abstract

The application discloses a term mismatch risk assessment method, device, equipment, medium and product. The term mismatch risk assessment method comprises: for each business index in a plurality of business indexes, obtaining business data corresponding to a plurality of enterprises under each business index, wherein the business index is a candidate index for assessing the term mismatch risk of the enterprise; calculating an information value IV value corresponding to each business index according to the business data corresponding to the plurality of enterprises under each business index; obtaining a business index with an IV value greater than a preset threshold from the plurality of business indexes to obtain a first business index; constructing a logistic regression model according to the business data corresponding to the plurality of enterprises under the first business index to obtain a plurality of second business indexes; and assessing the term mismatch risk of a target enterprise based on the plurality of second business indexes. According to the embodiment of the application, the assessment accuracy of the term mismatch risk can be improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of risk assessment and the technical field of big data, and particularly relates to a term mismatch risk assessment method, device, equipment, medium and product. BACKGROUND

[0002] Term mismatch refers to the mismatch between the term of assets and the term of liabilities, that is, the short-termization of fund sources and the long-termization of fund use. Term mismatch is one of the biggest factors affecting the liquidity risk and profit of a financial institution, which enhances the liquidity of funds and realizes rapid financing, but also involves huge risks.

[0003] At present, for the assessment of term mismatch risk, a single index is usually used to represent the term mismatch risk. However, term mismatch is a problem of asset and liability allocation, involving the amount and time of deposits and loans and other factors. A single index cannot accurately represent the term mismatch risk, resulting in low accuracy of term mismatch risk assessment. SUMMARY

[0004] The embodiments of the application provide a term mismatch risk assessment method, device, equipment, medium and product, which can improve the accuracy of term mismatch risk assessment.

[0005] In a first aspect, the embodiments of the application provide a term mismatch risk assessment method, which comprises:

[0006] For each business index in the plurality of business indexes, the business data corresponding to each business index of the plurality of enterprises is obtained, wherein the business index is a candidate index for assessing the term mismatch risk of the enterprise;

[0007] According to the business data corresponding to each business index of the plurality of enterprises, the information value (IV) value corresponding to each business index is calculated;

[0008] The business index with an IV value greater than a preset threshold is obtained from the plurality of business indexes, and a first business index is obtained;

[0009] According to the business data corresponding to the first business index of the plurality of enterprises, a logistic regression model is constructed, and a plurality of second business indexes are obtained;

[0010] Based on the plurality of second business indexes, the term mismatch risk of the target enterprise is assessed.

[0011] In a second aspect, the embodiments of the application provide a term mismatch risk assessment device, which comprises:

[0012] The first obtaining module is configured to obtain, for each of a plurality of business indexes, business data corresponding to a plurality of enterprises respectively under each business index, wherein the business index is an alternative index for evaluating the term mismatch risk of the enterprise;

[0013] The computing module is configured to calculate an information value IV value corresponding to each business index according to the business data corresponding to the plurality of enterprises respectively under each business index;

[0014] The first determining module is configured to obtain a business index with an IV value greater than a preset threshold from the plurality of business indexes, to obtain a first business index;

[0015] The constructing module is configured to construct a logistic regression model according to the business data corresponding to the plurality of enterprises respectively under the first business index, to obtain a plurality of second business indexes;

[0016] The evaluating module is configured to evaluate the term mismatch risk of the target enterprise based on the plurality of second business indexes.

[0017] In a third aspect, an electronic device is provided, which includes a processor and a memory storing computer program instructions;

[0018] The processor, when executing the computer program instructions, implements the steps of the term mismatch risk evaluation method according to any one of the embodiments of the first aspect.

[0019] In a fourth aspect, a computer readable storage medium is provided, which stores computer program instructions. When the computer program instructions are executed by a processor, the steps of the term mismatch risk evaluation method according to any one of the embodiments of the first aspect are implemented.

[0020] In a fifth aspect, a computer program product is provided. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device performs the steps of the term mismatch risk evaluation method according to any one of the embodiments of the first aspect.

[0021] The term mismatch risk assessment method, device, equipment, medium and product provided in the embodiments of the present application, by acquiring the business data corresponding to each business index of a plurality of enterprises, and then calculating the IV value corresponding to the business index according to the business data corresponding to each business index of a plurality of enterprises, obtaining the first business index by acquiring the business index with an IV value greater than a preset threshold from the business index, and constructing a logistic regression model according to the business data corresponding to the first business index of a plurality of enterprises, obtaining a plurality of second business indexes. In this way, the term mismatch risk of the target enterprise is assessed based on the plurality of second business indexes obtained from a plurality of alternative indexes for assessing the term mismatch risk of the enterprise, which improves the accuracy of the term mismatch risk assessment compared with the prior art which only uses a single index to assess the term mismatch risk of the enterprise. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments of the present application will be briefly introduced. Those skilled in the art can obtain other drawings based on these drawings without creating any creative labor.

[0023] Figure 1 is a flowchart of a term mismatch risk assessment method provided by the embodiments of the present application;

[0024] Figure 2 is a flowchart of a method for assessing the term mismatch risk of a target enterprise provided by the embodiments of the present application

[0025] Figure 3 is a flowchart of another term mismatch risk assessment method provided by the embodiments of the present application;

[0026] Figure 4 is a structural diagram of a term mismatch risk assessment device provided by the embodiments of the present application;

[0027] Figure 5 is a structural diagram of an electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0028] The features and exemplary embodiments of various aspects of the present application will be described in detail below, in order to make the purposes, technical solutions and advantages of the present application more clear and apparent, the present application will be further described in detail below in combination with the drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, but not to limit the present application. The present application can be implemented without some of these specific details by those skilled in the art. The following description of the embodiments is only to provide a better understanding of the present application by showing examples of the present application.

[0029] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, 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. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0030] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0031] As described in the background section, in existing technologies, methods for assessing maturity mismatch risk typically use a single indicator to represent it. The assessment model for maturity mismatch risk is based solely on this single indicator. However, maturity mismatch is an asset-liability allocation issue for financial institutions, involving multiple aspects such as the amount and duration of deposits and loans. Therefore, a combination of indicators is needed to represent it. A single indicator cannot accurately represent maturity mismatch risk, resulting in low accuracy in the assessment of maturity mismatch risk.

[0032] To address the problems in the prior art, embodiments of this application provide a method, apparatus, device, and computer-readable storage medium for assessing maturity mismatch risk.

[0033] The maturity mismatch risk assessment method provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0034] Figure 1 This is a flowchart illustrating a maturity mismatch risk assessment method provided in an embodiment of this application. Figure 1 As shown, this method for assessing maturity mismatch risk may specifically include the following steps:

[0035] S110. For each of the multiple business indicators, obtain the business data corresponding to each business indicator for multiple enterprises. The business indicators are alternative indicators used to assess the maturity mismatch risk of enterprises.

[0036] S120. Based on the business data of multiple enterprises under each business indicator, calculate the information value (IV) corresponding to each business indicator.

[0037] S130, obtaining a business indicator with an IV value greater than a preset threshold from the plurality of business indicators, to obtain a first business indicator;

[0038] S140, constructing a logistic regression model according to the business data of the plurality of enterprises respectively corresponding to the first business indicator, to obtain a plurality of second business indicators;

[0039] S150, evaluating the term mismatch risk of the target enterprise based on the plurality of second business indicators.

[0040] Thus, for each business indicator in the plurality of business indicators, the business data of the plurality of enterprises respectively corresponding to each business indicator is obtained, and then the IV value (Information Value) corresponding to the business indicator is calculated according to the business data of the plurality of enterprises respectively corresponding to the business indicator. The first business indicator is obtained by obtaining the business indicator with the IV value greater than the preset threshold from the business indicators. The plurality of second business indicators is obtained by constructing a logistic regression model according to the business data of the plurality of enterprises respectively corresponding to the first business indicator. In this way, the term mismatch risk of the target enterprise is evaluated based on the plurality of second business indicators obtained from the plurality of alternative indicators for evaluating the term mismatch risk of the enterprise. Compared with the prior art in which only a single indicator is used to evaluate the term mismatch risk of the enterprise, the evaluation accuracy of the term mismatch risk is improved.

[0041] The specific implementation of each step is described below.

[0042] In some embodiments, in S110, the plurality of business indicators may, for example, be indicators related to the term mismatch risk or indicators unrelated to the term mismatch risk, and indicators derived from the features of the obtained indicators, which are alternative indicators for evaluating the term mismatch risk of the enterprise. Each business indicator corresponds to business data.

[0043] In some embodiments, in S120, the IV value corresponding to each business indicator can be calculated according to the number of good enterprises and bad enterprises after binning.

[0044] In some embodiments, in S130, the preset threshold can be that the IV value reaches a certain value, for example, 0.2, that is, the first business indicator is obtained by obtaining the business indicator with the IV value greater than 0.2 from the plurality of business indicators.

[0045] In some embodiments, after obtaining the first business indicators with IV values greater than the preset threshold in S140, a logistic regression model can be constructed according to the business data corresponding to the first business indicators, so that the second business indicators for evaluating the term mismatch risk of the enterprise can be obtained according to the input variables in the constructed logistic regression model.

[0046] In some embodiments, after obtaining the second business indicators for evaluating the term mismatch risk of the enterprise in S150, the term mismatch risk of the target enterprise can be evaluated based on the second business indicators, for example, by comprehensively considering the business data corresponding to the second business indicators to determine whether the target enterprise has a term mismatch risk.

[0047] Based on this, in some embodiments, S140 can specifically include:

[0048] According to the business data corresponding to the first business indicators of the plurality of enterprises, the correlation coefficient between any at least two of the plurality of first business indicators is determined.

[0049] In the case where the correlation coefficient between the at least two first business indicators is greater than a preset threshold, the first business indicator with a smaller IV value among the at least two first business indicators is removed to obtain a third business indicator.

[0050] According to the business data corresponding to the third business indicator of the plurality of enterprises, a logistic regression model is constructed to obtain a plurality of second business indicators.

[0051] The correlation coefficient between any at least two first business indicators is obtained by dividing the covariance of the business data corresponding to the at least two business indicators by the product of the standard deviations of the business data corresponding to the at least two business indicators.

[0052] In this way, after determining the correlation coefficient between the at least two first business indicators, the first business indicator with a smaller IV value among the at least two first business indicators can be removed in the case where the correlation coefficient between the at least two business indicators is greater than a preset threshold, to filter out the same type of business indicators. The preset threshold can be a numerical value of the correlation coefficient, for example, it can be 0.7. In this way, the third business indicator after screening can be obtained, and a logistic regression model can be constructed based on the third business indicator.

[0053] In some embodiments, the plurality of enterprises include good enterprises and bad enterprises, as shown in Figure 2 S150 can specifically include steps S151-S157.

[0054] S151, converting the parameters corresponding to the logistic regression model into a standard score card, scoring the plurality of enterprises to obtain scores corresponding to the plurality of enterprises, respectively.

[0055] S152, rank the plurality of enterprises in order according to the scores, and divide the plurality of enterprises into equal intervals according to the scores to obtain a plurality of equal interval.

[0056] Here, after obtaining the scores corresponding to the plurality of enterprises respectively, the plurality of enterprises can be ranked in order according to the scores from large to small, and can be divided into equal intervals according to the scores, for example, can be divided into ten equal intervals.

[0057] S153, determine the enterprise recall rate and the enterprise false negative rate corresponding to the threshold line of the plurality of equal intervals according to the number of good enterprises and the number of bad enterprises in the plurality of equal intervals, the threshold line being a judgment standard boundary between good enterprises and bad enterprises.

[0058] S154, determine the threshold line corresponding to the enterprise recall rate and the enterprise false negative rate that meets the preset risk control condition from the threshold lines of the plurality of equal intervals as the target threshold line.

[0059] Here, the preset risk control condition may be, for example, that the false negative rate of the good enterprises corresponding to the threshold line and the recall rate of the bad enterprises meet the preset condition. After determining the enterprise recall rate and the enterprise false negative rate corresponding to the threshold line of the plurality of equal intervals, the target threshold line meeting the preset risk control condition is determined from the threshold lines of the plurality of equal intervals.

[0060] S155, determine the number of good enterprises and the number of bad enterprises above and below the target threshold line in the plurality of enterprises according to the target threshold line.

[0061] Here, after the target threshold line is determined, the number of good enterprises and the number of bad enterprises above and below the target threshold line in the plurality of enterprises can be obtained, for example, the number of good enterprises and the number of bad enterprises above the target threshold line and the number of good enterprises and the number of bad enterprises below the target threshold line.

[0062] S156, determine the warning line corresponding to the second business index according to the number of good enterprises and the number of bad enterprises above and below the target threshold line.

[0063] S157, evaluate the term mismatch risk of the target enterprise based on the warning lines corresponding to the plurality of second business indexes respectively.

[0064] Wherein, after determining the number of good enterprises and the number of bad enterprises above and below the target threshold line in the plurality of enterprises, this can be used as a standard for determining the warning line. The warning line is determined according to the number of good enterprises and the number of bad enterprises on both sides corresponding to a plurality of business data of any business index in the plurality of second business indexes, and the number of good enterprises and the number of bad enterprises closest to the target threshold line.

[0065] Based on this, as an example, the above S156 may specifically include:

[0066] Obtain multiple business data corresponding to multiple enterprises under a target business indicator, wherein the target business indicator is any one of multiple second business indicators;

[0067] Determine the number of good companies and bad companies among the multiple enterprises corresponding to each of the multiple business data points;

[0068] From the number of good companies and the number of bad companies among multiple companies, determine the target segment number that is closest to the number of good companies and the number of bad companies above and below the target threshold.

[0069] The business data corresponding to the number of target divisions is used as the early warning line for the target business indicators.

[0070] In this way, we can determine the number of good and bad companies among multiple enterprises that are located above and below the target threshold. Then, we can traverse all the business data of the target business indicator and find the number of good and bad companies on both sides of each business data point. The value point of the target business indicator that is closest to the number of good and bad companies on both sides of the target threshold is taken as the warning line corresponding to the target business indicator.

[0071] Therefore, by setting early warning lines for multiple secondary business indicators that can be used to assess the maturity mismatch risk of a company, it is possible to detect whether the business data corresponding to the secondary business indicators of the target company is close to or exceeds the early warning line, thereby assessing the maturity mismatch risk of the target company and increasing the accuracy of maturity mismatch risk assessment.

[0072] In order to obtain multiple business indicators, as another implementation of the embodiment of this application, this application also provides another implementation of the maturity mismatch risk assessment method, as detailed in the following embodiments.

[0073] like Figure 3 As shown, prior to S110 above, another method for determining the present value of enterprise assets provided in this application may also include the following steps: S310-S330, which will be explained in detail below.

[0074] S310: Obtain multiple maturity mismatch indicators and multiple non-maturity mismatch indicators.

[0075] The plurality of term mismatch indicators can be the amount, proportion, interest, and term of core business loan services of different risk levels, and the amount, proportion, interest, and term of non-core other loan services of different risk levels. The business can be the amount and proportion of various deposits, the amount and proportion of long-term deposits, the amount and proportion of sporadic deposits, the amount and proportion of wholesale deposits, the amount and proportion of short-term time deposits, the amount and proportion of current deposits, the amount and proportion of agreement deposits, the amount and proportion of notice deposits, the amount and proportion of time deposits, the amount and proportion of various securitized assets, and the amount and proportion of asset-backed bonds. The non-term mismatch indicators can include financial institution profitability, operational capability indicators, financial institution nature, and economic cycle indicators that have an impact on liquidity risk.

[0076] S320, deriving features according to the plurality of term mismatch indicators and the plurality of non-term mismatch indicators to obtain a plurality of derived indicators.

[0077] The plurality of term mismatch indicators and the plurality of non-term mismatch indicators can be derived multiple times to obtain a plurality of derived indicators.

[0078] As an example, the term mismatch indicators and the non-term mismatch indicators include indicators of a plurality of time windows, and S320 can specifically include:

[0079] For each time window in the plurality of time windows, the following steps are performed to obtain a plurality of derived indicators:

[0080] The term mismatch indicators of the target time window are combined according to a preset algorithm to obtain a first derived indicator of the target time window, wherein the target time window is any time window in the plurality of time windows;

[0081] The statistical indicators corresponding to the term mismatch indicators, the non-term mismatch indicators, and the first derived indicator of the target time window are determined as a second derived indicator;

[0082] The first derived indicator and the second derived indicator are determined as derived indicators.

[0083] The plurality of time windows can include different time windows of years, half years, quarters, months, and weeks, and the preset algorithm can be, for example, subtracting the sum of long-term funding indicators from the sum of long-term funding sources indicators, and then subtracting the result from short-term funding sources indicators to obtain the first derived indicator of the target window.

[0084] In addition, the statistical indicators can include, for example, mean value, standard deviation, coefficient of variation, maximum value, minimum value, upper limit value and lower limit value of a confidence interval at a 95% confidence level, kurtosis value and skewness value of a proportion of medium and long-term loans in a year calculated on a monthly basis, and each term mismatch indicator, each non-term mismatch indicator, and each first derivative indicator can be determined as a second derivative indicator.

[0085] S330, the plurality of term mismatch indicators, the plurality of non-term mismatch indicators, and the plurality of derivative indicators are determined as a plurality of business indicators.

[0086] Here, the plurality of term mismatch indicators, the plurality of non-term mismatch indicators, and the plurality of derivative indicators can be determined as a plurality of business indicators.

[0087] Therefore, by obtaining the plurality of term mismatch indicators and the plurality of non-term mismatch indicators, and deriving a plurality of derivative indicators, the alternative indicators for evaluating the term mismatch risk are enriched, and the related indicators that affect the term mismatch risk are fully considered, so that the indicators for representing the term mismatch risk can be more accurately screened, and the accuracy of the term mismatch risk evaluation is improved.

[0088] It should be noted that the application scenarios described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems as new application scenarios appear.

[0089] Based on the same inventive concept, the present application also provides a term mismatch risk evaluation device. The specific embodiments are described in detail in combination with Figure 4 .

[0090] Figure 4 is a structural schematic diagram of a term mismatch risk evaluation device provided by the embodiments of the present application.

[0091] As Figure 4 shown, the term mismatch risk evaluation device 400 can include:

[0092] The first obtaining module 401 is configured to obtain, for each business indicator in a plurality of business indicators, business data corresponding to each business indicator of a plurality of enterprises, respectively, wherein the business indicator is an alternative indicator for evaluating the term mismatch risk of the enterprise.

[0093] The calculation module 402 is configured to calculate an IV value corresponding to each business indicator according to the business data corresponding to each business indicator of the plurality of enterprises, respectively.

[0094] The first determining module 403 is configured to obtain, from the plurality of business indexes, a business index with an IV value greater than a preset threshold, to obtain a first business index.

[0095] The constructing module 404 is configured to construct a logistic regression model according to the business data of the plurality of enterprises corresponding to the first business index, to obtain a plurality of second business indexes.

[0096] The evaluating module 405 is configured to evaluate the term mismatch risk of the target enterprise based on the plurality of second business indexes.

[0097] The term mismatch risk evaluation device 400 is described in detail as follows.

[0098] In some embodiments, the term mismatch risk evaluation device 400 can specifically include:

[0099] The second obtaining module is configured to, before obtaining the business data of the plurality of enterprises corresponding to each of the plurality of business indexes, obtain a plurality of term mismatch indexes and a plurality of non-term mismatch indexes.

[0100] The feature derivation module is configured to derive features according to the plurality of term mismatch indexes and the plurality of non-term mismatch indexes, to obtain a plurality of derived indexes.

[0101] The second determining module is configured to take the plurality of term mismatch indexes, the plurality of non-term mismatch indexes, and the plurality of derived indexes as the plurality of business indexes.

[0102] In some embodiments, the term mismatch indexes and the non-term mismatch indexes include indexes of a plurality of time windows, and the feature derivation module can specifically include:

[0103] For the indexes of each of the plurality of time windows, the following steps are performed to obtain the plurality of derived indexes:

[0104] The combining sub-module is configured to combine the term mismatch indexes of a target time window according to a preset algorithm, to obtain a first derived index of the target time window, wherein the target time window is any of the plurality of time windows.

[0105] The first determining sub-module is configured to determine, as a second derived index, a statistical index corresponding to the term mismatch indexes, the non-term mismatch indexes, and the first derived index of the target time window.

[0106] The second determining sub-module is configured to determine the first derived index and the second derived index as the derived index.

[0107] In some embodiments, the constructing module 404 can specifically include:

[0108] The correlation coefficient determination submodule determines a correlation coefficient between any two of the first business indicators according to the business data corresponding to the plurality of enterprises under the first business indicators.

[0109] The removal submodule removes a first business indicator with a smaller IV value among the at least two first business indicators when the correlation coefficient between the at least two first business indicators is greater than a preset threshold value, to obtain third business indicators.

[0110] The construction submodule constructs a logistic regression model according to the business data corresponding to the plurality of enterprises under the third business indicators, to obtain a plurality of second business indicators.

[0111] In some embodiments, the plurality of enterprises include good enterprises and bad enterprises, and the evaluation module 405 can specifically include:

[0112] The scoring submodule converts parameters of the logistic regression model into a standard scorecard to score the plurality of enterprises, to obtain scores corresponding to the plurality of enterprises respectively.

[0113] The division submodule sequentially arranges the plurality of enterprises according to the scores, and equally divides the plurality of enterprises according to the scores, to obtain a plurality of equal interval ranges.

[0114] The third determination submodule determines an enterprise recall rate and an enterprise false negative rate corresponding to a threshold line of the plurality of equal interval ranges according to a number of good enterprises and a number of bad enterprises in the plurality of equal interval ranges, the threshold line being a judgment standard boundary line between the good enterprises and the bad enterprises.

[0115] The fourth determination submodule determines a target threshold line from the threshold line of the plurality of equal interval ranges, the enterprise recall rate and the enterprise false negative rate of the target threshold line meeting a preset risk control condition.

[0116] The fifth determination submodule determines a number of good enterprises and a number of bad enterprises above and below the target threshold line among the plurality of enterprises according to the target threshold line.

[0117] The sixth determination submodule determines a warning line corresponding to the second business indicators according to the number of good enterprises and the number of bad enterprises above and below the target threshold line.

[0118] The evaluation submodule evaluates a term mismatch risk of a target enterprise based on the warning line corresponding to the plurality of second business indicators respectively.

[0119] In some embodiments, the sixth determination submodule can specifically include:

[0120] The acquisition unit is used to acquire multiple business data corresponding to multiple enterprises under the target business indicator, wherein the target business indicator is any one of multiple second business indicators;

[0121] The first determining unit is used to determine the number of good companies and the number of bad companies among the multiple companies corresponding to multiple business data.

[0122] The second determining unit is used to determine the target segment number that is closest to the number of good enterprises and the number of bad enterprises above and below the target threshold from the number of good enterprises and the number of bad enterprises among multiple enterprises;

[0123] The early warning line determination unit is used to divide the target into several business data points and use them as early warning lines for the target business indicators.

[0124] Therefore, by acquiring business data for each of multiple business indicators under each indicator, and then calculating the IV value corresponding to each business indicator based on the business data of each enterprise, the first business indicator is obtained by selecting business indicators with IV values ​​greater than a preset threshold. Based on the business data of each enterprise under the first business indicator, a logistic regression model is constructed to obtain multiple second business indicators. Thus, this application assesses the maturity mismatch risk of a target enterprise based on multiple second business indicators obtained from multiple alternative indicators for assessing the enterprise's maturity mismatch risk. Compared with existing technologies that use only a single indicator to assess the maturity mismatch risk of an enterprise, this improves the accuracy of maturity mismatch risk assessment.

[0125] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0126] The electronic device 500 may include a processor 501 and a memory 502 storing computer program instructions.

[0127] Specifically, the processor 501 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0128] The memory 502 can include mass storage for data or instructions. As an example and not by way of limitation, the memory 502 can include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disc (e.g., a compact disc (CD) or a digital versatile disc (DVD)), a solid-state drive (SSD), a USB drive, or a combination of two or more of these. Where appropriate, the memory 502 can include removable or non-removable (or fixed) media. Where appropriate, the memory 502 can be internal or external to the integrated gateway disaster recovery device. In particular embodiments, the memory 502 is non-volatile, solid-state memory.

[0129] In particular embodiments, the memory can include read-only memory (ROM), random access memory (RAM), magnetic disk storage mediums, optical storage mediums, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software that, when executed (by one or more processors), is operable to

[0130] The processor 501 implements the time mismatch risk assessment method of any of the above embodiments by reading and executing computer program instructions stored in the memory 502.

[0131] In some examples, the electronic device 500 can also include a communication interface 503 and a bus 510. As shown, the processor 501, the memory 502, and the communication interface 503 are connected by the bus 510 and complete communication among each other. Figure 5

[0132] The communication interface 503 is mainly used to realize the communication between the modules, devices, units and / or equipment in the embodiments of the present application.

[0133] ​Bus 510 includes hardware, software, or both, to couple components of the online data traffic metering device to each other and to couple components to other components within the online data traffic metering device. While bus 510 is shown for the sake of clarity as a single bus, bus 510 can include one or more buses operating together to form a bus system. Bus 510 can include a system bus, a Peripheral Component Interconnect (PCI) bus, a HyperTransport (HTX) bus, Industry Standard Architecture (ISA) bus, a low pin count (LPC) bus, a memory bus, a video bus, or the like. Bus 510 can include one or more buses according to any of the aforementioned bus types and / or a combination of any of the aforementioned bus types. Where appropriate, bus 510 can include an appropriate bus architecture, such as a bus architecture having a bus controller, a bus driver, an address bus, a data bus, a control bus, or the like. Although this disclosure describes and shows a particular bus, this disclosure contemplates any suitable bus or bus system.

[0134] In example embodiments, electronic device 500 can be a mobile phone, a tablet computer, a notebook computer, a handheld computer, a vehicle-mounted electronic device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), or the like.

[0135] Electronic device 500 can perform the term mismatch risk assessment method in the embodiments of the present disclosure, thereby realizing the term mismatch risk assessment method and device described in combination Figure 1 and Figure 4 with the above embodiments.

[0136] In addition, in combination with the term mismatch risk assessment method in the above embodiments, the embodiments of the present disclosure can provide a computer-readable storage medium to implement. The computer-readable storage medium has computer program instructions stored thereon; the computer program instructions are executed by a processor to implement any one of the term mismatch risk assessment methods in the above embodiments. Examples of the computer-readable storage medium include non-transitory computer-readable storage media, such as a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, etc.

[0137] It is to be understood that the application is not limited to particular configurations and processes described herein and shown in the drawings. The detailed description is not to be taken in a limiting sense, and the scope of the present application is defined by the appended claims. In the above embodiments, several specific steps are described and illustrated in order to provide a thorough understanding of the present application. However, the process of the present application can be carried out in some orders of the steps, under some conditions, and using some alternatives, all without departing from the spirit and scope of the application.

[0138] The functions of the various elements shown in the figures can be provided through the use of dedicated hardware as well as hardware capable of executing software. When provided by a processor, the functions can be provided by a software program tangibly embodied on a machine-readable medium (for example, a non-transitory machine-readable medium). The software program can be run by a processor to perform the functions of the application. A machine-readable medium includes any mechanism for storing or transmitting information in a form readable by a machine (e.g., a computer). For example, a machine-readable medium includes a machine-readable storage medium (for example, ROM, RAM, a magnetic or optical disk, a flash memory, etc.) and a machine-readable transmission medium (for example, a magnetic or optical carrier wave). The software program can be implemented in a high level procedural or object-oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. The software program can be transmitted to a computer using a data transmission medium (for example, a carrier wave on a bus or network) or can be loaded from a machine-readable medium.

[0139] It is also to be understood that the application is not limited to the particular implementations described herein, as variations of these embodiments can be made and still fall within the scope of the present application. For example, the steps recited in the claims can be performed in a different order than the order recited in the claims. Also, some of the steps can be performed simultaneously, rather than sequentially. Additionally, some of the steps can be performed by different components of the system, rather than by a single component.

[0140] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. Alternatively, computer program implemented steps can be implemented by a special purpose computer, a special purpose computer with associated hardware, or by a combination of computer and associated hardware.

[0141] The above merely describes a specific implementation of the present application. Those skilled in the art can clearly understand the specific working processes of the system, modules and units described above for the convenience and brevity of description, and the corresponding processes in the foregoing method embodiments can be referred to, which will not be described herein again. It should be understood that the protection scope of the present application is not limited in this way, and any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed in the present application, and these modifications or replacements should be covered in the protection scope of the present application.

Claims

1. A method for assessing maturity mismatch risk, characterized in that, include: For each of the multiple business indicators, obtain the business data corresponding to each business indicator for multiple enterprises, wherein the business indicators are alternative indicators used to assess the maturity mismatch risk of enterprises. Based on the business data of the multiple enterprises under each business indicator, calculate the information value (IV) value corresponding to each business indicator. From the plurality of business metrics, the business metrics with an IV value greater than a preset threshold are obtained to obtain the first business metric; Based on the business data of the multiple enterprises under the first business indicator, a logistic regression model is constructed to obtain multiple second business indicators. Based on the aforementioned multiple secondary business indicators, assess the maturity mismatch risk of the target company; The step involves constructing a logistic regression model based on the business data corresponding to the multiple enterprises under the first business indicator, to obtain multiple second business indicators, including: Based on the business data corresponding to the multiple enterprises under the first business indicator, determine the correlation coefficient between any at least two first business indicators among the multiple first business indicators; If the correlation coefficient between the at least two first business indicators is greater than a preset threshold, the first business indicator with the smaller IV value among the at least two first business indicators is removed to obtain the third business indicator. Based on the business data corresponding to the third business indicator for each of the multiple enterprises, a logistic regression model is constructed to obtain the multiple second business indicators.

2. The method according to claim 1, characterized in that, Before acquiring the business data corresponding to each of the multiple business metrics for each enterprise under the stated business metric, the method further includes: Obtain multiple maturity mismatch indicators and multiple non-maturity mismatch indicators; Based on the multiple maturity mismatch indicators and the multiple non-maturity mismatch indicators, feature derivation is performed to obtain multiple derived indicators; The plurality of maturity mismatch indicators, the plurality of non-maturity mismatch indicators, and the plurality of derived indicators are used as the plurality of business indicators.

3. The method according to claim 2, characterized in that, The maturity mismatch indicator and the non-maturity mismatch indicator include indicators with multiple time windows; The feature derivation based on the plurality of maturity mismatch indicators and the plurality of non-maturity mismatch indicators yields a plurality of derived indicators, including: For each time window's metrics within the multiple time windows, the following steps are performed to obtain the multiple derived metrics: The maturity mismatch indicators of the target time window are combined according to a preset algorithm to obtain the first derived indicator of the target time window, wherein the target time window is any one of the multiple time windows; The statistical indicators corresponding to the maturity mismatch indicator, the non-maturity mismatch indicator, and the first derived indicator in the target time window are determined as the second derived indicator; The first derived index and the second derived index are determined as the derived index.

4. The method according to claim 1, characterized in that, The plurality of enterprises includes both good and bad enterprises. The assessment of the maturity mismatch risk of the target enterprise based on the plurality of second business indicators includes: The parameters corresponding to the logistic regression model are converted into a standard scoring card, and the multiple enterprises are scored to obtain scores corresponding to each of the multiple enterprises. The multiple enterprises are arranged in order according to their scores, and then divided into multiple equally spaced intervals according to their scores. Based on the number of good companies and bad companies in the multiple equidistant intervals, determine the company recall rate and false positive rate corresponding to the threshold lines of the multiple equidistant intervals. The threshold lines are the dividing lines of the evaluation criteria between good companies and bad companies. From the threshold lines of the multiple equidistant intervals, the threshold line that meets the preset risk control conditions for the enterprise recall rate and the enterprise false positive rate is determined as the target threshold line; Based on the target threshold line, determine the number of good companies and the number of bad companies among the plurality of companies that are above and below the target threshold line; Based on the number of good and bad companies above and below the target threshold, determine the warning line corresponding to the second business indicator; Based on the warning lines corresponding to the various second business indicators, the maturity mismatch risk of the target company is assessed.

5. The method according to claim 4, characterized in that, The step of determining the warning line corresponding to the second business indicator based on the number of good and bad enterprises above and below the target threshold includes: Obtain multiple business data corresponding to the multiple enterprises under the target business indicator, wherein the target business indicator is any one of the multiple second business indicators; Determine the number of good companies and the number of bad companies among the multiple enterprises corresponding to the multiple business data; From the number of good companies and the number of bad companies among the multiple companies, determine the target segment number that is closest to the number of good companies and the number of bad companies above and below the target threshold. The business data corresponding to the number of divisions of the target will be used as the early warning line for the target business indicator.

6. A device for assessing maturity mismatch risk, characterized in that, The device includes: The first acquisition module is used to acquire business data corresponding to each business indicator for multiple enterprises under each business indicator, wherein the business indicators are alternative indicators used to assess the maturity mismatch risk of enterprises. The calculation module is used to calculate the information value (IV) corresponding to each business indicator based on the business data corresponding to each business indicator for the multiple enterprises. The first determining module is used to obtain the business indicators whose IV value is greater than a preset threshold from the plurality of business indicators, and obtain the first business indicator; The construction module is used to construct a logistic regression model based on the business data corresponding to the multiple enterprises under the first business indicator, and obtain multiple second business indicators. The assessment module is used to assess the maturity mismatch risk of the target company based on the multiple second business indicators. The building module is specifically used for: Based on the business data corresponding to the multiple enterprises under the first business indicator, determine the correlation coefficient between any at least two first business indicators among the multiple first business indicators; If the correlation coefficient between the at least two first business indicators is greater than a preset threshold, the first business indicator with the smaller IV value among the at least two first business indicators is removed to obtain the third business indicator. Based on the business data corresponding to the third business indicator for each of the multiple enterprises, a logistic regression model is constructed to obtain the multiple second business indicators.

7. An electronic device, characterized in that, The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the steps of the maturity mismatch risk assessment method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, implement the steps of the maturity mismatch risk assessment method as described in any one of claims 1-5.

9. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device performs the steps of the maturity mismatch risk assessment method as described in any one of claims 1-5.

Images