A data processing method and apparatus

Abstract

The application provides a data processing method and device, applied to the field of data processing, and used for improving the accuracy of credit risk assessment of a financial institution. The method comprises the following steps: acquiring characteristic information of a first financial institution; determining one or more indexes according to the characteristic information of the first financial institution; determining and outputting one or more information according to the one or more indexes, wherein the one or more indexes and the one or more information are in one-to-one correspondence, and the information is used for indicating the credit risk size of the first financial institution.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular to a data processing method and apparatus. Background Technology

[0002] The non-performing loan (NPL) ratio of financial institutions (such as banks) is usually an important indicator of credit risk, and changes in the NPL ratio are caused by various factors.

[0003] Existing technologies use macroeconomic indicators to assess the non-performing loan ratios of various financial institutions, resulting in incomplete and inaccurate analysis results.

[0004] Therefore, improving the accuracy of credit risk assessment for financial institutions is an urgent problem to be solved. Summary of the Invention

[0005] This application provides a data processing method and apparatus for improving the accuracy of credit risk assessment for financial institutions.

[0006] In a first aspect, embodiments of this application provide a data processing method that can be applied to any electronic device with processing capabilities, including:

[0007] Obtain the characteristic information of the first financial institution; the characteristic information includes the industry in which the first financial institution's credit flows;

[0008] Identify at least one industry that is associated with the credit risk of the first financial institution based on the feature information;

[0009] At least one indicator is determined based on at least one industry; wherein each of the at least one industry corresponds to one or more of the at least one indicator.

[0010] At least one piece of information is determined and output based on at least one indicator, with each indicator corresponding to at least one piece of information, and the information is used to indicate the credit risk level of the first financial institution.

[0011] In this method, since the credit risk of the first financial institution is strongly correlated with the industry in which credit flows in, and the industry concentration of customers of different financial institutions is also different, at least one industry (i.e., industry) related to the credit risk of the first financial institution is screened from the industry in which credit flows in. Then, at least one indicator is determined based on at least one industry, which can be used to obtain the indicator related to the credit risk of the first financial institution. Subsequently, the credit risk of the first financial institution can be assessed based on this indicator, which can improve the accuracy of credit risk assessment.

[0012] Optionally, at least one indicator is determined based on at least one industry, including: obtaining all indicators for each industry in at least one industry; and selecting at least one indicator from all indicators, wherein the correlation between each indicator and the profit margin of the corresponding industry is greater than a threshold.

[0013] In this method, after identifying at least one industry related to the credit risk of the first financial institution, at least one indicator with a correlation greater than a threshold to the profit margin of the corresponding industry is further screened from all indicators of the at least one industry. That is, at least one indicator in each industry with a correlation greater than a threshold to the profit margin of that industry. Since credit risk is mainly related to the profit margin (i.e., returns) of an industry, indicators with low correlation to the industry profit margin can be excluded first, reducing the computational resource consumption of credit risk assessment and improving the efficiency and accuracy of credit risk assessment.

[0014] Optionally, the feature information may also include the region where the first financial institution is located; the method may also include: determining at least one of the following factors based on the region where the first financial institution is located: GDP, CPI, unemployment rate, money supply, fiscal deficit, public external debt, and trade balance; and determining and outputting at least one piece of information based on the at least one factor.

[0015] In this method, at least one indicator is determined based on the region where the first financial institution is located, so that the obtained indicator can more accurately reflect the economic situation of the region where the first financial institution is located, thereby improving the accuracy and reliability of subsequent risk assessment of the first financial institution.

[0016] Optionally, the feature information may also include the type of the first financial institution; the first financial institution is a bank; the method may also include: determining the bank's interest rate based on the bank's type; determining and outputting information based on the interest rate.

[0017] In this method, the interest rate of a bank is determined according to its type, and the bank's interest rate is used as one of its indicators. This allows the indicator to more accurately reflect the bank's own situation, thereby improving the accuracy and reliability of subsequent risk assessments of the bank.

[0018] Optionally, at least one industry includes the industrial sector, and at least one indicator is determined based on the at least one industry, including: at least one of the following: industrial producer purchase price index, industrial producer price index, production materials price index, product output, and inventory level.

[0019] Optionally, at least one industry includes the real estate industry, and at least one indicator is determined based on at least one industry, including: at least one of the following: the sales area of ​​commercial housing, the construction area of ​​real estate, the completed area of ​​real estate, and the actual investment in real estate development.

[0020] Optionally, the method further includes: dividing multiple financial institutions into one or more sets according to the characteristic information of the multiple financial institutions, each set including financial institutions with the same characteristic information, and the multiple financial institutions including a first financial institution; determining at least one indicator based on the characteristic information corresponding to each set, and the determined at least one indicator corresponding to each financial institution in each set.

[0021] In this method, multiple financial institutions are divided into one or more sets based on their characteristic information. The financial institutions in each set have the same characteristic information. At least one indicator is determined for each set, which facilitates credit risk assessment for each set. This can improve the efficiency of risk assessment and also make it easier to show the overall credit risk of financial institutions in the same region and / or of the same type.

[0022] Secondly, embodiments of this application provide a data processing apparatus, including:

[0023] The acquisition module is used to: acquire the characteristic information of the first financial institution; the characteristic information includes the industry in which the first financial institution's credit flows;

[0024] The processing module is used to: determine at least one industry that is related to the credit risk of the first financial institution based on feature information; determine at least one indicator based on the at least one industry; wherein each industry in the at least one industry corresponds to one or more indicators in the at least one indicator; and determine at least one piece of information based on the at least one indicator, wherein the at least one indicator corresponds one-to-one with the at least one piece of information, and the information is used to indicate the size of the credit risk of the first financial institution.

[0025] The output module is used to output at least one piece of information.

[0026] Optionally, when determining at least one indicator based on at least one industry, the processing module is used to: obtain all indicators for each industry in at least one industry; and filter at least one indicator from all indicators, wherein the correlation between each indicator and the profit margin of the corresponding industry is greater than a threshold.

[0027] Optionally, the feature information also includes the region where the first financial institution is located; the processing module is also used to: determine at least one of the following in the region where the first financial institution is located: GDP, CPI, unemployment rate, money supply, fiscal deficit, public external debt, and trade balance, and determine and output at least one piece of information based on the at least one.

[0028] Optionally, the feature information also includes the type of the first financial institution; the first financial institution is a bank; the processing module is also used to: determine the bank's interest rate based on the bank's type, and determine and output information based on the interest rate.

[0029] Optionally, at least one industry includes the industrial sector, and when the processing module determines at least one indicator based on at least one industry, it is used to: determine at least one of the following based on the industrial sector: the industrial producer purchase price index, the industrial producer price index, the production materials price index, product output, and inventory.

[0030] Optionally, at least one industry includes the real estate industry, and when the processing module determines at least one indicator based on at least one industry, it is used to: determine at least one of the following based on the real estate industry: the sales area of ​​commercial housing, the construction area of ​​real estate, the completed area of ​​real estate, and the actual investment in real estate development.

[0031] Optionally, the processing module is also used to: divide multiple financial institutions into one or more sets according to the characteristic information of the multiple financial institutions, each set including financial institutions with the same characteristic information, and the multiple financial institutions including the first financial institution; determine at least one indicator according to the characteristic information corresponding to each set, and the determined at least one indicator corresponds to each financial institution in each set.

[0032] Thirdly, embodiments of this application provide an electronic device including at least one processor, which, when executing a computer program stored in a memory, causes the method as described in the first aspect or any optional implementation of the first aspect to be implemented.

[0033] Fourthly, embodiments of this application provide a computer-readable storage medium for storing instructions that, when executed, cause the method as described in the first aspect or any optional implementation of the first aspect to be implemented.

[0034] Fifthly, embodiments of this application provide a computer program product, including computer program code, which, when executed on a computer, causes the method as described in the first aspect or any optional implementation of the first aspect to be implemented.

[0035] The technical effects or advantages of one or more technical solutions provided in the second, third, fourth and fifth aspects of this application can all be explained by the corresponding technical effects or advantages of one or more technical solutions provided in the first aspect. Attached Figure Description

[0036] Figure 1 A flowchart of a data processing method provided in an embodiment of this application;

[0037] Figure 2 A structural diagram of a data processing device provided in an embodiment of this application;

[0038] Figure 3 This is a structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0039] The data collection, dissemination, and use in this application all comply with relevant national laws and regulations.

[0040] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0041] The technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this application and the specific features in the embodiments are detailed descriptions of the technical solution of this application, rather than limitations on the technical solution of this application. In the absence of conflict, the embodiments of this application and the technical features in the embodiments can be combined with each other.

[0042] Introduction to technical terms:

[0043] 1. The non-performing loan ratio (i.e., the non-performing credit loan ratio) refers to the proportion of non-performing loans in the total loan balance of a financial institution. Non-performing loans refer to the five categories of credit classified according to risk basis when assessing credit quality: normal, special mention, substandard, doubtful, and loss. The latter three categories are collectively referred to as non-performing loans.

[0044] 2. Lag effect: This refers to the phenomenon where the dependent variable is affected by changes in itself or an explanatory variable, but the expected effect does not appear immediately, but only after a period of time.

[0045] 3. Price Index: An economic indicator that reflects the direction, trend and degree of change in the price level of a group of goods (services) in different periods. It is a type of economic index and is usually expressed as a relative number comparing the reporting period (i.e., the current period) and the base period.

[0046] 4. In the description of the embodiments of this application, "multiple" refers to two or more. "First," "second," etc., in the embodiments of this application are used to distinguish different objects, not to describe a specific order. The term "and / or" in the embodiments of this application is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, the term "comprising" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices. In the embodiments of this application, a module refers to a part of a software system that has independent functionality.

[0047] The assessment of credit risk (e.g., non-performing loan ratio of banks) of financial institutions typically employs static models, such as static panel data models, with the following formula:

[0048] Y it =x it β it +z i δ+λ t +c i +u it

[0049] Where, β it For regression parameters z at different time points (i.e., different periods) and for different cross-sectional individuals (i.e., parameters related to credit risk), i λ represents a variable that does not change over time. t c represents the time effect that does not change with individual cross-sections but changes with time. i u represents the individual effect that does not change over time but varies with the individual at the cross-section. it Let x represent the random disturbance term. it The indicators used typically include macroeconomic indicators such as Gross Domestic Product (GDP) and Consumer Price Index (CPI).

[0050] However, the aforementioned model fails to consider that the indicators affecting credit risk may differ across regions and types of financial institutions. Furthermore, the impact of different indicators on credit risk varies across different periods. It only analyzes the correlation between credit risk and some macroeconomic indicators, neglecting indicators specific to different regions and the industry concentration of customers for different types of financial institutions (such as banks). This leads to an incomplete analysis of credit risk and poor accuracy of the results. Customers in different industries involve different indicators, and the degree of impact of these indicators on the credit risk of financial institutions varies, resulting in different manifestations of credit risk for financial institutions across different industries.

[0051] In view of this, embodiments of this application provide a data processing method that determines at least one indicator of a first financial institution based on its characteristic information, including the region where the first financial institution is located, the type of the first financial institution, and the industry in which the credit flows into the first financial institution. This allows the obtained indicator to more accurately reflect the situation of the first financial institution. By evaluating the impact of each indicator on the credit risk of the first financial institution based on each of the at least one indicator, the risk assessment of the first financial institution can be made more accurate.

[0052] The data processing method provided in this application is applicable to credit risk assessment by financial institutions, including but not limited to the above-mentioned analysis of non-performing loan ratios of banks.

[0053] The data processing method provided in this application can be applied to any electronic device with processing capabilities, such as servers, mobile phones, tablets, computers, etc.

[0054] See Figure 1 This application provides a data processing method, taking credit risk analysis as an example. The method includes steps S101 to S103:

[0055] S101. Obtain the characteristic information of the first financial institution.

[0056] For example, the characteristic information of the first financial institution may include the industries in which the first financial institution's credit flows.

[0057] The industries into which the first financial institution's credit flows are such as industrial, agricultural, real estate, and aerospace technology industries, and the corresponding industries are obtained based on the first financial institution's actual credit records.

[0058] S102. Identify at least one industry that is related to the credit risk of the first financial institution based on the feature information.

[0059] For example, taking the first financial institution as a bank and credit risk represented by the non-performing loan ratio, since the proportion of corporate credit flowing into different industries varies greatly among different types of banks, it is necessary to determine whether the various industries into which the credit flows have an impact on the bank's credit risk.

[0060] From the industries receiving credit inflows from the primary financial institution, select at least one industry that is associated with the credit risk of the primary financial institution. Specifically, this may include:

[0061] Let x be the amount of credit flowing into a certain industry from a bank, and Y be the non-performing loan ratio. Establish a Granger model to test whether the amount of credit loans flowing into the industry from the bank is related to the bank's non-performing loan ratio.

[0062] The above method is used to verify whether each bank's credit fund flow into each industry affects the bank's non-performing loan ratio.

[0063] Specifically, the formula for the Granger model is:

[0064] Among them, y t This represents the value of the explained variable y at time t, x t c1 represents the value of the explanatory variable x over time t, and α is a constant term. i and β j It is a regression function, ε t This is the error term.

[0065] The basic idea of ​​the Granger causality test is: assuming that the change in variable x is the cause of the change in variable y, then the change in variable x should occur earlier than that in variable y, and variable x should have a significant effect in predicting variable y. That is, in the regression model that predicts y, introducing past observations of variable x as independent variables should statistically significantly increase the explanatory power of the model.

[0066] Therefore, the Granger model can be used to screen out x that have a causal effect on y, that is, the credit flow from banks to a certain industry will affect the non-performing loan ratio of that bank, thereby identifying the industries that need further analysis.

[0067] S103. Determine at least one indicator based on at least one industry.

[0068] Each of the at least one industry corresponds to one or more indicators in at least one indicator.

[0069] For example, based on the industries identified above that will affect the non-performing loan ratio of banks, all indicators for that industry are determined. Specific examples are given below:

[0070] Example 1: At least one industry includes the industrial sector, and at least one indicator is determined based on the at least one industry, including: at least one of the following: industrial producer purchase price index, industrial producer ex-factory price index, production materials price index, product output, and inventory level.

[0071] For the industrial sector, the main factors influencing industry prosperity include demand and supply. Therefore, indicators related to demand and supply can be selected as indicators for analyzing the industry.

[0072] Example 2: At least one industry includes the real estate industry, and at least one indicator is determined based on the at least one industry, including: at least one of the following: the sales area of ​​commercial housing, the construction area of ​​real estate, the completed area of ​​real estate, and the actual investment in real estate development.

[0073] For the real estate industry, the factors that have the greatest impact on the industry are mainly sales and investment. Therefore, indicators related to sales and investment can be selected as indicators for analyzing the industry.

[0074] It is understandable that the above are just two possible examples, and the actual situation is not limited to these.

[0075] In one possible embodiment, the number of indicators determined based on at least one industry in the above steps may be large, and there may be indicators that are not closely related to credit risk or industry economics. Using such indicators as indicators for analyzing credit risk is not very meaningful and consumes a lot of computing resources. Therefore, in order to improve the efficiency and accuracy of data processing, all the obtained indicators can be screened first.

[0076] Specifically, at least one indicator is determined based on at least one industry, including: obtaining the indicator corresponding to each industry in at least one industry; selecting at least one indicator from the indicators, wherein the correlation between each indicator and the profit margin of the corresponding industry is greater than a threshold.

[0077] It is understandable that, since credit risk is usually related to the economy of various industries, indicators that are strongly correlated with industry profit margins can be selected.

[0078] For example, based on monthly industry data from the National Bureau of Statistics website, with the profit rate of each industry as the dependent variable and the following indicators of each industry as independent variables, an XGBoost model is established to screen out variables that are strongly correlated with the industry profit rate as the objects of credit risk analysis.

[0079] It's understandable that the range of independent variables in the XGBoost model differs for each industry. Taking the industrial sector as an example, according to industry data from the National Bureau of Statistics, the independent variables for the industrial sector include factors closely related to supply and demand, such as the industrial producer purchase price index, the industrial producer ex-factory price index, and the production materials price index. In addition, the independent variables for the industrial sector also include product output, inventory, and various expenses.

[0080] The independent variables for each industry listed above can be filtered using the XGBoost model to obtain only indicators that are strongly correlated with the industry's profit margin.

[0081] S104. Determine and output at least one piece of information based on at least one indicator.

[0082] In this context, at least one indicator corresponds one-to-one with at least one piece of information, which is used to indicate the magnitude of credit risk of the first financial institution.

[0083] For example, by determining and outputting the credit risk level of the first financial institution corresponding to each indicator, the impact of each indicator on the credit risk of the first financial institution can be determined, which facilitates subsequent credit risk management.

[0084] The magnitude of credit risk can be reflected through various indicators, such as the non-performing loan ratio mentioned above, and can also include the lag effect.

[0085] It is understandable that the credit risk exposure of financial institutions (such as banks) has a lag effect on some risk factors (i.e., target indicators). This means that at least one indicator at present will not immediately affect credit risk (e.g., the non-performing loan ratio), but may have an impact on credit risk after a period of time. Therefore, studying the lag effect of risk factors (i.e., one or more indicators) is particularly important for early warning of financial risks.

[0086] For example, taking the first financial institution as a bank, and taking at least one piece of information including the non-performing loan ratio and / or the number of lags as an example, at least one piece of information can be determined based on at least one indicator in the following manner.

[0087] Obtain at least one of the indicators acquired in the above steps. Take the monthly data for each indicator, i.e., each indicator can yield a series of monthly time series data. Build a lag model for each indicator separately with the bank's current monthly non-performing loan ratio, and determine the lag period for each indicator.

[0088] Specifically, the formula example for the distributed lag model is as follows:

[0089] Y t =α+β0X t +β1X t-1 +β2Xt-2 +…+β k X t-k +u t

[0090] In the distributed lag model, each coefficient reflects the different degrees of influence of the various lagged values ​​of the explanatory variable x (i.e., the target indicator) on the explained variable y (i.e., the non-performing loan ratio), which is commonly referred to as the multiplier effect. Here, X... t The coefficients are called short-term multipliers or immediate multipliers, representing the average impact of a one-unit change in the independent variable x (i.e., the target indicator) on the dependent variable y (i.e., the current non-performing loan ratio). Establishing a distributed lag model allows us to determine the number of periods in which the independent variable lags the dependent variable. Calculating the weighted average of the coefficients of the independent variables for different periods in the model yields the proportion of contribution of the independent variable to the lag effect for each period.

[0091] In this embodiment of the application, both the explanatory variable x and the explained variable y are monthly data (i.e., data from each month). If the order of the explanatory variable x is first, it means that the lag period is one month; if the order of x is second, it means that the lag period is two months, and so on.

[0092] In this way, we can obtain the lag period of each indicator on the bank's non-performing loan ratio, as well as the degree of influence of the indicator on the current bank's non-performing loan ratio in each period.

[0093] The calculation principle of the distributed lag model:

[0094] First, the lag period can be determined by methods such as calculating the correlation coefficient, calculating the decision coefficient, the Schwarz criterion, and the Akaike criterion, to determine the optimal lag period.

[0095] For example, the optimal lag period is the number of lag periods of this indicator relative to the bank's non-performing loan ratio.

[0096] Then, model estimation was performed using methods such as empirical weighting and Almon polynomial method to obtain α, β0, and β. i The value;

[0097] Next, the obtained distributed lag model is validated and estimated using regression equations or regression coefficients;

[0098] Finally, the lag effect is analyzed.

[0099] For example, β0 is the short-term multiplier, which represents the effect of a one-unit change in the explanatory variable (i.e., the target indicator) on the explained variable (i.e., the non-performing loan ratio) in the same period, i.e., the short-term effect.

[0100] β i(i>0) represents the deferred multiplier or dynamic multiplier, which reflects the impact of one unit change in the explanatory variable (i.e., the target indicator) in each lag period on the explained variable (i.e., the non-performing loan ratio), i.e., the lagged effect.

[0101] The (n-period) medium-term multiplier reflects the cumulative n-period impact of a one-unit change in the explanatory variable (i.e., the target indicator) in each lag period on the explained variable (i.e., the non-performing loan ratio), where n is a positive integer.

[0102] As a long-term multiplier, it reflects the cumulative total impact of a one-unit change in the explanatory variable (i.e., the target index) on the explained variable (i.e., the non-performing loan ratio) in each lag period.

[0103] This means that the lag period and degree of impact of each indicator on the non-performing loan ratio can be determined based on the obtained parameters.

[0104] In this implementation method, since the credit risk of the first financial institution is strongly correlated with the industry in which credit flows in, and the industry concentration of customers of different financial institutions is also different, at least one industry (i.e., industry) related to the credit risk of the first financial institution is screened from the industry in which credit flows in. Then, at least one indicator is determined based on at least one industry, which can obtain the indicator related to the credit risk of the first financial institution. Subsequently, the credit risk of the first financial institution can be assessed based on this indicator, which can improve the accuracy of credit risk assessment.

[0105] In one possible design, the characteristic information of the first financial institution also includes the region where the first financial institution is located, and the method may also include:

[0106] Based on the characteristic information of the first financial institution, one or more indicators are determined, including: based on the region where the first financial institution is located, at least one of the following: GDP, CPI, unemployment rate, money supply, fiscal deficit, public external debt, and trade balance of the region where the first financial institution is located.

[0107] Determine and output at least one piece of information based on at least one of these criteria.

[0108] Specifically, the region where the first financial institution is located can be a country, such as China, South Korea, Russia, etc., or a specific province, such as Fujian Province or Guangdong Province in China. It can also be further refined to a specific city, county, or even district, such as Guangzhou City in Guangdong Province or Qingyang District in Chengdu City, Sichuan Province in China. It can be determined according to the specific circumstances of the financial institution to be analyzed. This application does not impose any restrictions on this.

[0109] It is understandable that if the same national macroeconomic indicators are used to assess the credit risk of each financial institution, the assessment results will not accurately reflect the specific credit risk of each financial institution. However, using the macroeconomic indicators of the region where each financial institution is located can better reflect the emergency situation in that region. This allows for the analysis of the relationship between the credit risk of each financial institution and the macroeconomic indicators of the region where the financial institution is located, making the credit risk assessment results more accurate and reliable.

[0110] Similarly, the method described in S104 above can be used to calculate at least one piece of information of the at least one item, which will not be repeated here.

[0111] In one possible design, the characteristic information of the first financial institution also includes the type of the first financial institution; the first financial institution is a bank; the method also includes:

[0112] The bank's interest rate is determined based on its type.

[0113] Output a message based on the interest rate.

[0114] For example, taking a bank as the primary financial institution, the types of primary financial institutions (i.e., banks) can include at least one of the following: central bank, policy bank, state-owned commercial bank, nationwide joint-stock commercial bank, city commercial bank, rural credit cooperative, rural commercial bank, village and township bank, cooperative bank, investment bank, World Bank, and foreign bank; or, each type can be further subdivided. For example, state-owned commercial banks include the Industrial and Commercial Bank of China, Agricultural Bank of China, Bank of China, China Construction Bank, Bank of Communications, and Postal Savings Bank of China, etc. Each type of state-owned commercial bank can be considered as one type. The above is only one possible example, and other classification methods can be used in practice.

[0115] It's understandable that if the primary financial institution is a bank, there's a strong correlation between the bank's interest rates and credit risk. Different types of banks have different interest rates, and the specific interest rate of a bank can be obtained based on its type. Therefore, using the bank's interest rate as an indicator allows the indicator to more accurately reflect the bank's situation, thereby improving the accuracy and reliability of subsequent risk assessments.

[0116] The above are merely possible examples. In practice, the characteristic information of the first financial institution can also be used as the indicator of the financial institution. This application does not limit this.

[0117] Similarly, the method described in S104 above can be used to calculate the information corresponding to the interest rate, which will not be repeated here.

[0118] In one possible design, embodiments of this application also provide a method for assessing the credit risk of multiple financial institutions, including:

[0119] Multiple financial institutions are divided into one or more sets according to their characteristic information. Each set includes financial institutions with the same characteristic information. The multiple financial institutions include the first financial institution. At least one indicator is determined based on the characteristic information corresponding to each set. The determined at least one indicator corresponds to each financial institution in each set.

[0120] For example, multiple financial institutions can be divided into different sets according to their different regions and types. Each set contains financial institutions of the same type in the same region. In each set, the steps S101 to S104 above are performed. Taking a set as a whole, one or more indicators of the entire set are determined. Based on one or more indicators of each set, one or more pieces of information reflecting the credit risk of the set are determined.

[0121] In this way, the financial institutions in each set have the same characteristic information, which facilitates credit risk assessment for each set, improves the efficiency of risk assessment, and makes it easier to show the overall credit risk of financial institutions in the same region and / or of the same type.

[0122] It is understood that the above-mentioned method of dividing the set is only one possible example. It can be divided based solely on the region where the financial institution is located, the type of financial institution, or the industry in which the financial institution's credit flows. Alternatively, it can freely combine the aforementioned characteristic information of the financial institution, or it can use other characteristic information such as the reputation of the financial institution, the number of branches, etc. The embodiments of this application do not impose any restrictions on this.

[0123] The methods provided in the embodiments of this application have been described above. The apparatus provided in the embodiments of this application will be described below.

[0124] Based on the same technical concept, embodiments of this application provide a data processing apparatus, which includes a module / unit / means for executing the method performed by the electronic device with processing capabilities described in the above method embodiments. This module / unit / means can be implemented in software, or in hardware, or implemented by hardware executing corresponding software.

[0125] For example, such as Figure 2 As shown, the device 200 may include:

[0126] The acquisition module 201 is used to: acquire the characteristic information of the first financial institution; the characteristic information includes the industry in which the credit flows into the first financial institution;

[0127] Processing module 202 is used to: determine at least one industry that is related to the credit risk of the first financial institution based on feature information; determine at least one indicator based on the at least one industry; wherein each industry in the at least one industry corresponds to one or more indicators in the at least one indicator; and determine at least one piece of information based on the at least one indicator, wherein the at least one indicator corresponds one-to-one with the at least one piece of information, and the information is used to indicate the size of the credit risk of the first financial institution.

[0128] Output module 203 is used to output at least one piece of information.

[0129] It should be understood that all relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0130] Based on the same technical concept, see [link / reference] Figure 3 This application also provides an electronic device 300, comprising:

[0131] At least one processor 301; and a communication interface 303 communicatively connected to the at least one processor 301; the at least one processor 301 causes the electronic device 300 to execute the method steps performed by the dashboard in the above method embodiment through the communication interface 303 by executing instructions stored in the memory 302.

[0132] Optionally, the memory 302 is located outside the electronic device 300.

[0133] Optionally, the electronic device 300 includes a memory 302 connected to the at least one processor 301, and the memory 302 contains instructions executable by the at least one processor 301. (See attached image) Figure 3 The dashed line indicates that the memory 302 is optional for the electronic device 300.

[0134] The at least one processor 301 and the memory 302 can be coupled through an interface circuit or integrated together, which is not limited here.

[0135] This application embodiment does not limit the specific connection medium between at least one processor 301, memory 302, and communication interface 303. This application embodiment... Figure 3 At least one processor 301, memory 302, and communication interface 303 are connected via a bus 304. Figure 3 The connections between other components are shown in bold and are for illustrative purposes only, not as limiting information. This bus section can be an address bus, data bus, control bus, etc. For ease of illustration, Figure 3 It is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0136] It should be understood that the processor mentioned in the embodiments of this application can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, integrated circuit, etc. When implemented in software, the processor can be a general-purpose processor, implemented by reading software code stored in memory.

[0137] For example, the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0138] It should be understood that the memory mentioned in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which acts as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate Synchronous DRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct RAM (DR RAM).

[0139] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, the memory (storage module) can be integrated into the processor.

[0140] It should be noted that the memories described herein are intended to include, but are not limited to, these and any other suitable types of memories.

[0141] Based on the same technical concept, embodiments of this application also provide a computer-readable storage medium for storing instructions that, when executed, cause a computer to perform the method steps performed by any of the devices in the above method embodiments.

[0142] Based on the same technical concept, this application also provides a computer program product, including computer program code, which, when the computer program code is run on a computer, causes the method steps executed by any device in the above method embodiments to be implemented.

[0143] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0144] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0145] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The function specified in one or more boxes.

[0146] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0147] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A data processing method, characterized by, include: Obtain the characteristic information of the first financial institution; The feature information includes the industries in which the first financial institution's credit flows. Based on the aforementioned feature information, at least one industry that is associated with the credit risk of the first financial institution is identified; At least one indicator is determined based on the at least one industry, wherein each of the at least one industry corresponds to one or more of the at least one indicators; At least one piece of information is determined and output based on the at least one indicator, wherein the at least one indicator corresponds one-to-one with the at least one piece of information, and the information is used to indicate the credit risk level of the first financial institution; The at least one piece of information includes the non-performing loan ratio and / or the number of lag periods; The step of determining at least one indicator based on the at least one industry includes: Obtain all indicators for each of the at least one industry; At least one indicator is selected from all the indicators, and each of the at least one indicator has a correlation greater than a threshold with the profit margin of the industry corresponding to each indicator.

2. The method of claim 1, wherein, The feature information also includes the region where the first financial institution is located; The method further includes: Based on the region where the first financial institution is located, determine at least one of the following: GDP, CPI, unemployment rate, money supply, fiscal deficit, public external debt, and trade balance of the region where the first financial institution is located. Determine and output at least one of the aforementioned pieces of information based on at least one of the aforementioned items.

3. The method as described in claim 1, characterized in that, The feature information includes the type of the first financial institution; the first financial institution is a bank. The method further includes: The interest rate of the bank is determined according to the type of the bank; The information is determined and output based on the interest rate.

4. The method as described in claim 1, characterized in that, The at least one industry includes the industrial sector, and the determination of at least one indicator based on the at least one industry includes: Based on the industrial sector, determine at least one of the following: the industrial producer purchase price index, the industrial producer ex-factory price index, the production materials price index, product output, and inventory level.

5. The method as described in claim 1, characterized in that, The at least one industry includes the real estate industry, and the determination of at least one indicator based on the at least one industry includes: Based on the real estate industry, determine at least one of the following: the sales area of ​​commercial housing, the construction area of ​​real estate, the completed area of ​​real estate, and the actual amount of real estate development investment in the real estate industry.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: Multiple financial institutions are divided into one or more sets according to their characteristic information. Each set includes financial institutions with the same characteristic information. The multiple financial institutions include the first financial institution. At least one indicator is determined based on the feature information corresponding to each set, and the determined at least one indicator corresponds to each financial institution in each set.

7. A data processing apparatus, characterized in that, include: The acquisition module is used to: acquire the feature information of the first financial institution; The feature information includes the industries in which the first financial institution's credit flows. The processing module is configured to: determine at least one industry that is related to the credit risk of the first financial institution based on the feature information; determine at least one indicator based on the at least one industry, wherein each industry in the at least one industry corresponds to one or more indicators in the at least one indicator; and determine at least one piece of information based on the at least one indicator, wherein the at least one indicator corresponds one-to-one with the at least one indicator, and the information is used to indicate the credit risk level of the first financial institution. An output module is used to output the at least one piece of information; the at least one piece of information includes the non-performing loan ratio and / or the number of lag periods; Specifically, when the processing module determines at least one indicator based on the at least one industry, it is used to: obtain all indicators of each industry in the at least one industry; and select at least one indicator from all the indicators, wherein the correlation between each of the at least one indicator and the profit margin of the industry corresponding to each indicator is greater than a threshold.

8. An electronic device, characterized in that, include: Memory, used to store program instructions; A processor is configured to invoke program instructions stored in the memory and execute the steps included in the method as described in any one of claims 1-6 according to the obtained program instructions.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a computer, cause the method as described in any one of claims 1-6 to be implemented.

10. A computer program product, characterized in that, The computer program product includes: computer program code, which, when run on a computer, causes the computer to perform the method described in any one of claims 1-6.

Images