Financial index system evaluation method and system based on digitization

Abstract

The invention discloses a financial index system evaluation method and system based on digitization in the technical field of financial science and technology. The method comprises the following steps: constructing a plurality of specific evaluation indexes based on four levels of coverage, use depth, digitization degree and financial risk control level; original data of specific evaluation indexes are collected from a banking business system; missing values and abnormal values in the original data of the specific evaluation indexes are cleaned, and noise reduction processing of the original data of the specific evaluation indexes is completed; a range standardization method is adopted to unify dimensions of specific evaluation indexes, and an analytic hierarchy process (AHP) and an entropy evaluation method are adopted to calculate a weight value of each specific evaluation index. According to the method, a plurality of specific evaluation indexes are constructed on the basis of four levels of coverage, use depth, digitization degree and financial risk control level, so that the digital service capability of a local financial institution can be comprehensively evaluated, and the digital financial service level of a local area can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital finance, and specifically, to a method and system for evaluating a financial index system based on digitization. Background Art

[0002] Digital inclusive finance refers to all actions that promote inclusive finance through digital financial services. Digital inclusive finance has reduced the threshold of financial services and improved service efficiency through information technology means, but there are still deficiencies in the quantitative evaluation of its development level.

[0003] Existing evaluation mechanisms mostly focus on the macro dimension, which includes the construction of a comprehensive index of geographical penetration and availability. Although the inclusive finance index proposed by Sarma and the global financial comprehensive index system proposed by Allen et al. can synthesize a comprehensive inclusive finance index to a certain extent.

[0004] However, the fine-grained evaluation system for local financial institutions at the county and township levels and below is still not perfect. In particular, there are gaps in terms of the comprehensiveness of covered services, the independence of indicators, and regional applicability. On the other hand, although the existing digital inclusive finance index is based on user transaction data, its framework cannot be improved according to the business characteristics of rural commercial banks and is difficult to reflect the digital service capabilities of local financial institutions at the county and township levels and below. In addition, most of the existing index systems use equal weights or simple statistical methods to assign weights, lacking consideration of business relevance and regional difference indicators. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for evaluating a financial index system based on digitization. By constructing multiple specific evaluation indicators based on four levels of coverage breadth, usage depth, digitization degree, and financial risk control level, it is possible to comprehensively evaluate the digital service capabilities of local financial institutions, which is beneficial to strengthening the digital financial business level in local areas.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for evaluating a digital-based financial indicator system, including constructing multiple specific evaluation indicators based on four levels of coverage breadth, usage depth, digitalization degree, and financial risk control level; collecting the original data of the specific evaluation indicators from the banking business system; cleaning the missing values and outliers in the original data of the specific evaluation indicators to complete the noise reduction process of the original data of the specific evaluation indicators; using the range standardization method to unify the dimensions of the specific evaluation indicators, and using the Analytic Hierarchy Process (AHP) and entropy method to calculate the weight values of each specific evaluation indicator; calculating the scores of each specific evaluation indicator and the scores of each level. Among them, the coverage breadth, usage depth, digitalization degree, and financial risk control level constitute the financial indicator system. Summing up the scores of each level to obtain the overall evaluation score of the financial indicator system, which can comprehensively reflect the performance of financial institutions in digital finance and provide directions for improvement and optimization for financial institutions.

[0008] On the other hand, according to the obtained evaluation score of the financial indicator system, it is possible to rank or classify the digital financial service levels in different regions, so as to provide a decision-making basis for investors and regulatory agencies. According to the evaluation results, it is possible to make targeted improvements to the weak links in the financial indicator system and improve the digital financial level.

[0009] As a further solution of the present invention: the specific evaluation indicators of the coverage breadth include one or several of the number of customers, the coverage rate in county and rural areas, and the proportion of mobile users; by constructing the specific evaluation indicators of the coverage breadth, the coverage range of financial services can be measured;

[0010] The specific evaluation indicators of the usage depth include one or several of deposit business, loan business, payment business, intermediate business, and e-banking business; by analyzing the numerical values of the specific evaluation indicators of the usage depth, the digital business penetration rate and user activity can be reflected;

[0011] The specific evaluation indicators of the digitalization degree include one or several of the proportion of mobile business, preferential rate, credit rate, and facilitation degree; by constructing the specific evaluation indicators of the digitalization degree, the digital transformation level of digital business can be reflected;

[0012] The preferential rate includes the average interest rate paid on behalf of small and micro enterprises, the average interest rate paid on behalf of large and medium-sized enterprises, the average online loan interest rate for individuals, and the average offline loan interest rate for individuals; the credit rate includes the proportion of online loans, the proportion of offline loans, and the proportion of credit cards, and the facilitation degree includes the convenience degree of code scanning payment and the convenience degree of agricultural comprehensive service stations;

[0013] The financial risk control level includes one or several of the anti-fraud transaction blocking rate and the accuracy rate of loan overdue rate monitoring; by obtaining the specific evaluation indicators of the financial risk control level, the intensity of the risk control management ability of digital business can be reflected.

[0014] As a further solution of the present invention: the deposit business includes personal deposit balance and corporate deposit balance; the loan business includes corporate business and personal business; the payment business includes unified payment business and Huipay business; the e-banking business includes mobile banking business, open banking business, Huisheng huo business, enterprise online shopping business and self-service machine business. The mobile banking business includes the number of active customers, the first number of transaction pens and the first transaction amount. The first number of transaction pens is the number of transaction pens of the mobile banking business, and the first transaction amount is the transaction amount of the mobile banking business; the open banking business, Huisheng huo business and enterprise online shopping business all include the number of customers, the second number of transaction pens and the second transaction amount. The second number of transaction pens is the sum of the number of transaction pens of the open banking business, Huisheng huo business and enterprise online shopping business, and the second transaction amount is the sum of the transaction amounts of the open banking business, Huisheng huo business and enterprise online shopping business.

[0015] As a further solution of the present invention: the corporate business and personal business respectively include the number of loan users with credit, the average number of loan pens and the average loan amount. The unified payment business and Huipay business both include the per capita number of payment pens, the per capita payment amount and the proportion of active users; the self-service machine business includes the number of machines, the third number of transaction pens and the third transaction amount. The third number of transaction pens is the number of transaction pens of the self-service machine, and the third transaction amount is the transaction amount of the self-service machine. The convenience degree of code scanning payment includes the proportion of the number of customer code scanning payment pens and the proportion of the customer code scanning payment amount; the convenience degree of the agricultural comprehensive service station includes the number of stations, the number of station transactions and the station transaction amount. The anti-fraud transaction blocking rate includes the number of blocked pens and the blocked transaction amount. The accuracy rate of loan overdue rate monitoring includes the number of loan overdue customers and the loan overdue amount.

[0016] As a further solution of the present invention: the method for cleaning the missing values and outliers in the original data of the specific evaluation indicators includes checking the original data of the specific evaluation indicators based on data processing software to identify the missing values; filling the missing values with the median; using the box plot statistical method to identify the outliers in the data; and correcting the obvious incorrect outliers. The data processing software is Excel.

[0017] As a further solution of the present invention: the method for unifying the dimensions of the specific evaluation indicators by using the range standardization method includes determining the maximum value and the minimum value of each specific evaluation indicator; calculating the range by using the range formula, where the range is equal to the maximum value of the specific evaluation indicator minus the minimum value of the specific evaluation indicator; after subtracting the minimum value from each observed value in the specific evaluation indicator, dividing by the range to obtain the standardized value, and the standardized value satisfies being greater than or equal to 0 and less than or equal to 1.

[0018] As a further solution of the present invention: the method of calculating the weight of each specific evaluation indicator using the analytic hierarchy process (AHP) and the entropy method includes constructing an importance matrix of specific evaluation indicators through expert scoring, and calculating the hierarchical single-ranking weights of the specific evaluation indicators; based on the entropy method, the discreteness of the hierarchical single-ranking weights is corrected to obtain the weight values ​​of the specific evaluation indicators, which can accurately reflect the actual role of each indicator in the evaluation system. The entropy method determines its weight according to the discreteness of the indicator data. The greater the discreteness of the data, the greater the role of the indicator in the evaluation system, and the higher its weight. By correcting the discreteness of the hierarchical single-ranking weights, the entropy method can further optimize the distribution of weights, making the evaluation system more scientific and reasonable. Combining the analytic hierarchy process with the entropy method can not only make full use of the experience and knowledge of experts, but also objectively reflect the characteristics of the data itself, thereby obtaining a more accurate and reliable weight distribution result.

[0019] As a further solution of the present invention: the method for calculating the score of each specific evaluation indicator and the score of each level includes respectively obtaining the value of each specific evaluation indicator and the level to which it belongs; multiplying the value of the specific evaluation indicator of each level by the weight value of the specific evaluation indicator in turn to obtain the weighted value of the specific evaluation indicator at each level, and setting the weighted value as the score of the specific evaluation indicator; adding and summing the weighted values ​​of the specific evaluation indicators of each level respectively, and obtaining the score of each level according to the added and summed value.

[0020] As a further solution of the present invention: the method also includes pre-setting evaluations and dynamic improvement suggestions corresponding to the scores at each level; updating the content of the dynamic improvement suggestions in real time; and regularly updating the evaluations corresponding to the scores. The pre-set evaluations can quickly give corresponding evaluation levels and evaluation descriptions based on the scores at each level, so that the evaluator can intuitively understand the current status of the financial indicator system. The dynamic improvement suggestions automatically recommend targeted improvement measures or development directions based on the scores, providing clear guidance for decision makers. The real-time updating of the content of the dynamic improvement suggestions can ensure the timeliness and pertinence of the suggestions. As the financial market changes, the improvement direction is adjusted in time. The regular updating of the evaluations corresponding to the scores is to track the development of the financial indicator system, evaluate the effectiveness of the improvement measures, and adjust the evaluation standards and weight distribution according to the new market environment or business needs to ensure the continued effectiveness and adaptability of the evaluation system.

[0021] Second aspect, the present invention also provides a system, which adopts the digital-based financial index system evaluation method as described in the above solution. The system includes an index construction module, a data collection module, a data processing module, a weight calculation module, and a score generation module; the index construction module is used to set a plurality of specific evaluation indexes included in four levels of coverage breadth, usage depth, digitalization degree, and financial risk control level; the data collection module is used to collect the original data of the specific evaluation indexes from the banking business system, and the input end of the data collection module is connected to the output end of the index construction module; the data processing module is used to complete the noise reduction processing of the original data of the specific evaluation indexes, and the input end of the data processing module is connected to the output end of the data collection module; the weight calculation module is used to calculate the weight value of each specific evaluation index by using the analytic hierarchy process (AHP) and the entropy method, and the input end of the weight calculation module is connected to the output end of the data processing module; the score generation module is used to calculate the score and rating of each specific evaluation index, and the input end of the score generation module is connected to the output end of the weight calculation module.

[0022] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0023] 1. By constructing a multi-dimensional index system covering four major fields of coverage breadth, usage depth, digitalization degree, and financial risk control level, and combining the business characteristics and data characteristics of local financial institutions, the present invention realizes the fine-grained quantitative evaluation of the digital inclusive finance development level of local banks, which can strengthen the comprehensiveness of the evaluation of the digital service capabilities of local financial institutions and is conducive to enhancing the digital financial business level of local areas.

[0024] 2. By aiming at the business characteristics of commercial banks in local areas such as county and township services and small and micro customer groups, the present invention constructs an evaluation system, screens indexes through correlation analysis and principal component analysis to ensure the independence between indexes, avoids repeated evaluation, and at the same time can maintain the evaluation system by combining the subjective evaluation of expert experience and the objective reality of data dispersion, thus improving the scientificity and adaptability of the evaluation results.

[0025] 3. Based on the entropy method, the present invention corrects the dispersion of the hierarchical single sorting weights to obtain the weight values of specific evaluation indexes, which can accurately reflect the actual role of each index in the evaluation system. By correcting the dispersion of the hierarchical single sorting weights, the entropy method can further optimize the weight allocation, making the evaluation system more scientific and reasonable. Combining the analytic hierarchy process with the entropy method can not only make full use of the experience and knowledge of experts, but also objectively reflect the characteristics of the data itself, thus obtaining a more accurate and reliable weight allocation result. Description of the Drawings

[0026] Figure 1 It is a method flow step diagram of the present invention;

[0027] Figure 2 System module diagram of the present invention;

[0028] Figure 3 Financial index system diagram of the present invention;

[0029] Figure 4 Structural diagram of specific evaluation indicators at the usage depth level of the present invention;

[0030] Figure 5 Structural diagram of specific evaluation indicators of the digitalization degree of the present invention;

[0031] Figure 6 Structural diagram of specific evaluation indicators of the financial risk control level of the present invention.

[0032] In the figure: 1. Index construction module; 2. Data collection module; 3. Data processing module; 4. Weight calculation module; 5. Weight calculation module; 6. Result analysis module; 7. User interaction interface. Specific implementation manners

[0033] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0034] Embodiment:

[0035] Please refer to Figure 1 、 Figure 3 - Figure 6 In the embodiments of the present invention, a financial index system evaluation method based on digitalization is provided, including the following steps:

[0036] S1: Construct multiple specific evaluation indicators based on four levels of coverage breadth, usage depth, digitalization degree, and financial risk control level;

[0037] S2: Collect the original data of specific evaluation indicators from the banking business system;

[0038] S3: Clean the missing values and outliers in the original data of specific evaluation indicators to complete the noise reduction processing of the original data of specific evaluation indicators;

[0039] S4: Use the range standardization method to unify the dimensions of specific evaluation indicators, and use the analytic hierarchy process (AHP) and entropy method to calculate the weight values of each specific evaluation indicator;

[0040] S5: Calculate the scores of each specific evaluation indicator and the scores of each level.

[0041] Among them, the coverage breadth, usage depth, digitalization level, and financial risk control level constitute a financial indicator system. By aggregating the scores at each level, an overall evaluation score of the financial indicator system is obtained. This score can comprehensively reflect the performance of financial institutions in digital finance and provide directions for improvement and optimization for financial institutions.

[0042] On the other hand, based on the obtained evaluation score of the financial indicator system, it is possible to rank or classify the digital financial service levels in different regions, so as to provide a decision-making basis for investors and regulatory agencies. According to the evaluation results, targeted improvements can be made to the weak links in the financial indicator system to enhance the digital finance level.

[0043] Preferably, the specific evaluation indicators for coverage breadth include the number of customers, the coverage rate in counties and townships, and the proportion of mobile users. By constructing the specific evaluation indicators for coverage breadth, the coverage scope of financial services can be measured.

[0044] The specific evaluation indicators for usage depth include deposit business, loan business, payment business, intermediate business, and e-banking business. By analyzing the values of the specific evaluation indicators for usage depth, the penetration rate of digital business and user activity can be reflected.

[0045] The specific evaluation indicators for digitalization level include the proportion of mobile business, preferential rate, credit rate, and facilitation level. By constructing the specific evaluation indicators for digitalization level, the digital transformation level of digital business can be reflected.

[0046] The preferential rate includes the average interest rate paid on behalf of small and micro enterprises, the average interest rate paid on behalf of large and medium-sized enterprises, the average online loan interest rate for individuals, and the average offline loan interest rate for individuals. The credit rate includes the proportion of online loans, the proportion of offline loans, and the proportion of credit cards. The facilitation level includes the convenience of QR code payment and the convenience of agricultural comprehensive service stations.

[0047] The financial risk control level includes the anti-fraud transaction blocking rate and the monitoring accuracy rate of loan overdue rates. By obtaining the specific evaluation indicators for the financial risk control level, the intensity of risk control management capabilities for digital business can be reflected.

[0048] Preferably, the deposit business includes personal deposit balance and corporate deposit balance; the loan business includes corporate business and personal business; the payment business includes unified payment business and Huipay business; the e-banking business includes mobile banking business, open banking business, Huisheng huo business, corporate online shopping business and self-service machine business. The mobile banking business includes the number of active customers, the first number of transaction records and the first transaction amount. The first number of transaction records is the number of transaction records of the mobile banking business, and the first transaction amount is the transaction amount of the mobile banking business. The open banking business, Huisheng huo business and corporate online shopping business all include the number of customers, the second number of transaction records and the second transaction amount. The second number of transaction records is the sum of the number of transaction records of the open banking business, Huisheng huo business and corporate online shopping business, and the second transaction amount is the sum of the transaction amounts of the open banking business, Huisheng huo business and corporate online shopping business.

[0049] Preferably, the corporate business and personal business respectively include the number of loan users with credit, the average number of loan records and the average loan amount. The unified payment business and Huipay business both include the average number of payment records per person, the average payment amount per person and the proportion of active users. The self-service machine business includes the number of machines, the third number of transaction records and the third transaction amount. The third number of transaction records is the number of transaction records of the self-service machine, and the third transaction amount is the transaction amount of the self-service machine. The convenience degree of code scanning payment includes the proportion of the number of customer code scanning payment records and the proportion of the customer code scanning payment amount. The convenience degree of the agricultural comprehensive service station includes the number of stations, the number of station transaction records and the station transaction amount. The anti-fraud transaction blocking rate includes the number of blocked records and the blocked transaction amount. The monitoring accuracy rate of loan overdue rate includes the number of loan overdue customers and the loan overdue amount.

[0050] Preferably, the method for cleaning the missing values and outliers in the original data of specific evaluation indicators includes checking the original data of specific evaluation indicators based on data processing software to identify the missing values; filling the missing values with the median; using the box plot statistical method to identify the outliers in the data; correcting the obviously wrong outliers or deleting them to ensure the accuracy and reliability of the data. In addition, other statistical methods such as mean filling, mode filling or interpolation method can also be used, and the most suitable missing value filling method can be selected according to the specific situation. In terms of outlier processing, in addition to direct correction or deletion, the outliers can also be processed through techniques such as data smoothing and data normalization to reduce their impact on the overall data. The data after cleaning will be more accurate, complete and reliable, providing strong support for subsequent analysis and evaluation.

[0051] Preferably, the data processing software is Excel.

[0052] Preferably, the method of unifying the dimensions of specific evaluation indicators by using the range normalization method includes determining the maximum and minimum values of each specific evaluation indicator; calculating the range using the range formula, where the range is equal to the maximum value of the specific evaluation indicator minus the minimum value of the specific evaluation indicator; after subtracting the minimum value from each observed value in the specific evaluation indicator, dividing by the range to obtain the standardized value, and the standardized value satisfies being greater than or equal to 0 and less than or equal to 1. This range normalization method can effectively eliminate the influence of different dimensions on the evaluation indicators, enabling horizontal comparison and comprehensive analysis among various indicators. The standardized value is between 0 and 1, which not only retains the relative magnitude and sorting relationship of the original data but also eliminates the dimension difference, allowing for fair comparison and evaluation among different indicators. It is simple and easy to understand and convenient to calculate.

[0053] Preferably, the method of calculating the weight of each specific evaluation indicator by using the Analytic Hierarchy Process (AHP) and the entropy method includes constructing an importance matrix of specific evaluation indicators through expert scoring and calculating the hierarchical single - sorting weights of specific evaluation indicators; based on the entropy method, correcting the dispersion of the hierarchical single - sorting weights to obtain the weight values of specific evaluation indicators, which can accurately reflect the actual role of each indicator in the evaluation system. The entropy method determines the weight according to the dispersion degree of the indicator data. The greater the dispersion degree of the data, the greater the role of the indicator in the evaluation system and the higher its weight. By correcting the dispersion of the hierarchical single - sorting weights, the entropy method can further optimize the weight distribution, making the evaluation system more scientific and reasonable. Combining the Analytic Hierarchy Process with the entropy method can not only make full use of the experience and knowledge of experts but also objectively reflect the characteristics of the data itself, thus obtaining a more accurate and reliable weight distribution result.

[0054] Preferably, invite 10 fintech experts to score the importance of the indicators and determine the final weight after correction combined with the entropy method.

[0055] Preferably, the method for calculating the scores of each specific evaluation index and the ratings of each level includes respectively obtaining the values of each specific evaluation index and their corresponding levels; successively multiplying the values of the specific evaluation indices of each level by the weight values of the specific evaluation indices to obtain the weighted values of the specific evaluation indices on each level, and setting the weighted values as the scores of the specific evaluation indices; adding up the weighted values of the specific evaluation indices of each level respectively, and obtaining the ratings of each level according to the added-up values. This process ensures that the contributions of each evaluation index are appropriately quantified and reflected. By calculating the scores of specific evaluation indices item by item, the performance of each financial index can be accurately captured. And by summing up the weighted values of the evaluation indices of each level, the comprehensive ratings of each level can be further obtained, which helps to comprehensively understand the overall performance of financial indices at different levels, is conducive to improving the accuracy of evaluation, enhancing the operability of evaluation, and can clearly observe the advantages and disadvantages of the financial index system at each level, providing a data basis for subsequent analysis and improvement.

[0056] Preferably, the method further includes presetting the evaluations and dynamic improvement suggestions corresponding to the ratings of each level; updating the content of the dynamic improvement suggestions in real time; and updating the evaluations corresponding to the ratings regularly. The preset evaluations can quickly give the corresponding evaluation grades and evaluation descriptions based on the ratings of each level, enabling the evaluators to intuitively understand the current situation of the financial index system. The dynamic improvement suggestions automatically recommend targeted improvement measures or development directions according to the rating situation, providing clear guidance for decision-makers. Updating the content of the dynamic improvement suggestions in real time can ensure the timeliness and pertinence of the suggestions, and adjust the improvement direction in a timely manner as the financial market changes. Regularly updating the evaluations corresponding to the ratings is to track the development of the financial index system, evaluate the effects of improvement measures, and adjust the evaluation criteria and weight distribution according to the new market environment or business requirements to ensure the continuous effectiveness and adaptability of the evaluation system.

[0057] Please refer to Figure 2, the present invention also provides a system that adopts the digital-based financial index system evaluation method as described above. The system includes an index construction module 1, a data collection module 2, a data processing module 3, a weight calculation module 4, and a score generation module 5. The index construction module 1 is used to set multiple specific evaluation indexes included in four aspects: coverage breadth, usage depth, digitalization degree, and financial risk control level. The data collection module 2 is used to collect the original data of specific evaluation indexes from the banking business system, and the input end of the data collection module 2 is connected to the output end of the index construction module 1. The data processing module 3 is used to complete the noise reduction processing of the original data of specific evaluation indexes, and the input end of the data processing module 3 is connected to the output end of the data collection module 2. The weight calculation module 4 is used to calculate the weight value of each specific evaluation index by using the analytic hierarchy process (AHP) and the entropy method, and the input end of the weight calculation module 4 is connected to the output end of the data processing module 3. The score generation module 5 is used to calculate the score and rating of each specific evaluation index, and the input end of the score generation module 5 is connected to the output end of the weight calculation module 4.

[0058] Preferably, the system further includes a result analysis module 6. The input end of the result analysis module 6 is connected to the output end of the score generation module 5. The result analysis module 6 is used to further analyze the score output by the score generation module 5 and generate an evaluation report. The evaluation report can intuitively display the performance of financial institutions on each evaluation index and the overall evaluation result.

[0059] Preferably, the system further includes a user interaction interface 7. The user interaction interface 7 is electrically connected to the result analysis module 6 and is used to display the evaluation report and provide a user operation interface to facilitate the user to perform operations such as index setting, data query, and evaluation result viewing.

[0060] The above is only the preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

Claims

1. A digital financial indicator system evaluation method, characterized in that: include: Construct multiple specific evaluation indicators based on four aspects: coverage breadth, usage depth, degree of digitization and financial risk control level; Collect original data of specific evaluation indicators from the banking business system; Clean the missing values ​​and outliers in the original data of the specific evaluation indicators, and complete the noise reduction processing of the original data of the specific evaluation indicators; The method of range standardization is used to unify the dimensions of specific evaluation indicators, and the analytic hierarchy process (AHP) and entropy method are used to calculate the weight value of each specific evaluation indicator; Calculate the score for each specific evaluation indicator and the score for each level.

2. The digital-based financial indicator system evaluation method according to claim 1 is characterized in that: The specific evaluation indicators of the coverage breadth include one or more of the number of customers, county and township coverage rate, and proportion of mobile users; The specific evaluation indicators of the usage depth include one or more of deposit business, loan business, payment business, intermediary business and electronic banking business; The specific evaluation indicators of the degree of digitalization include one or more of the proportion of mobile services, preferential rate, credit rate and convenience level; The preferential rates include the average agency payment interest rate for small and micro enterprises, the average agency payment interest rate for large and medium-sized enterprises, the average online loan interest rate for individuals, and the average offline loan interest rate for individuals; the credit rate includes the proportion of online loans, the proportion of offline loans, and the proportion of credit cards; the convenience level includes the convenience of scanning code payment and the convenience of agricultural comprehensive stations; The level of financial risk control includes one or more of the anti-fraud transaction blocking rate and the loan delinquency rate monitoring accuracy.

3. The digital-based financial indicator system evaluation method according to claim 2 is characterized in that: The deposit business includes personal deposit balance and corporate deposit balance; the loan business includes corporate business and personal business; Payment services include unified payment services and Huipay services; Electronic banking services include mobile banking services, open banking services, Huishenghuo services, corporate online shopping services and self-service machine services. Mobile banking services include the number of active customers, the number of first transactions and the first transaction amount. The number of first transactions refers to the number of transactions of mobile banking services, and the first transaction amount refers to the transaction amount of mobile banking services. Open banking business, Huisheng life business and enterprise online shopping business all include the number of customers, the number of second transactions and the second transaction amount. The number of second transactions is the sum of the number of transactions of open banking business, Huisheng life business and enterprise online shopping business, and the second transaction amount is the sum of the transaction amounts of open banking business, Huisheng life business and enterprise online shopping business.

4. The digital-based financial indicator system evaluation method according to claim 3 is characterized in that: The corporate business and personal business include the number of loan credit users, the average number of loans and the average loan amount respectively; the unified payment business and Huipay business include the number of payments per capita, the average payment amount per capita and the proportion of active users; Self-service machine business includes the number of machines, the number of third-party transactions and the amount of third-party transactions. The number of third-party transactions refers to the number of transactions at the self-service machines, and the amount of third-party transactions refers to the amount of transactions at the self-service machines. The convenience of scanning code payment includes the proportion of customer scanning code payment and the proportion of customer scanning code payment amount. The convenience of agricultural comprehensive stations includes the number of sites, the number of transactions at the sites and the transaction amount at the sites. The anti-fraud transaction blocking rate includes the number of blocked transactions and the amount of blocked transactions. The accuracy of loan delinquency rate monitoring includes the number of overdue loan customers and the overdue loan amount.

5. The digital-based financial indicator system evaluation method according to claim 4 is characterized in that: The method for cleaning missing values ​​and outliers in the original data of specific evaluation indicators includes: Check the raw data of specific evaluation indicators based on data processing software to identify missing values; The median was used to fill missing values; Use box plot statistics to identify outliers in the data; Correction was made for obviously erroneous outliers.

6. The method for evaluating a financial indicator system based on digitization according to claim 5 is characterized in that: The method of unifying the dimensions of specific evaluation indicators by using the range standardization method includes: Determine the minimum and maximum values ​​of each specific evaluation index; The range formula is used to calculate the range, which is equal to the maximum value of the specific evaluation index minus the minimum value of the specific evaluation index; Subtract the minimum value from each observation value in the specific evaluation index, and then divide it by the range to obtain the standardized value.

7. The digital-based financial indicator system evaluation method according to claim 6 is characterized in that: The method of using the analytic hierarchy process (AHP) and entropy method to calculate the weight of each specific evaluation index includes: The importance matrix of specific evaluation indicators is constructed through expert scoring, and the hierarchical single ranking weights of specific evaluation indicators are calculated; Based on the entropy method, the discreteness of the hierarchical single-ranking weights is corrected to obtain the weight values ​​of specific evaluation indicators.

8. The digital-based financial indicator system evaluation method according to claim 7 is characterized in that: The method for calculating the score of each specific evaluation indicator and the score of each level includes: Get the value of each specific evaluation indicator and the level to which it belongs respectively; The value of the specific evaluation indicator at each level is multiplied by the weight value of the specific evaluation indicator in turn to obtain the weighted value of the specific evaluation indicator at each level, and the weighted value is set as the score of the specific evaluation indicator; The weighted values ​​of the specific evaluation indicators at each level are added together and the scores at each level are obtained based on the added and summed values.

9. The digital-based financial indicator system evaluation method according to claim 8 is characterized in that: The method further comprises: Pre-set evaluations and dynamic improvement suggestions corresponding to scores at each level; Update the content of dynamic improvement suggestions in real time; Regularly update the reviews corresponding to the ratings.

10. A system, characterized in that: Using the digital-based financial indicator system evaluation method according to any one of claims 1 to 9, the system comprises: The indicator construction module is used to set multiple specific evaluation indicators in four aspects: coverage breadth, usage depth, degree of digitization and financial risk control level; A data collection module, which is used to collect raw data of specific evaluation indicators from the banking business system, and the input end of the data collection module is connected to the output end of the indicator construction module; A data processing module, which is used to complete the noise reduction processing of the original data of the specific evaluation index, and the input end of the data processing module is connected to the output end of the data acquisition module; A weight calculation module, which is used to calculate the weight value of each specific evaluation index by using the analytic hierarchy process (AHP) and the entropy method. The input end of the weight calculation module is connected to the output end of the data processing module. The scoring generation module is used to calculate the score and rating of each specific evaluation indicator. The input end of the scoring generation module is connected to the output end of the weight calculation module.

Images