A risk assessment system for financial institutions based on big data analysis
By collecting and analyzing a variety of risk data in the financial institution risk assessment system, the problem of insufficient comprehensive data collection in the existing technology is solved, the accuracy and real-timeness of the analysis results are improved, and a comprehensive assessment of the risks of financial institutions is achieved. Timely warning.
Patent Information
- Application Number
- CN202411255824.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-09
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-09-09
Smart Images

Figure CN118761838B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of financial risk assessment, and more specifically, to a financial institution risk assessment system based on big data analysis. Background Art
[0002] With the rise of big data technology, new solutions have been provided for risk assessment of financial institutions. By using big data technology, valuable information can be extracted from massive data, helping financial institutions to identify potential risk points, thereby improving the accuracy and timeliness of risk assessment.
[0003] The existing big data financial institution risk assessment system mainly includes data collection module, data analysis module, data processing module and human-computer interaction module; the data collection module collects market data including stock prices, exchange rates, interest rates, macroeconomic indicators, as well as internal data such as customer transaction records, investment portfolio information, loan records, etc. within the financial institution; the data analysis and processing module cleans, converts and integrates the collected data from different sources to obtain valuable information and discover problems in a timely manner through the human-computer interaction module, thereby reducing risks and losses and improving the competitiveness and profitability of financial institutions.
[0004] However, the above system still has shortcomings. For example, when collecting data, only some market data and internal data are collected. This leads to the singleness of the collected data, which affects the reliability of the data source, and then leads to the singleness of the results of data analysis, which reduces the accuracy of the analysis results and is not conducive to the healthy development of financial institutions.
[0005] Therefore, there is an urgent need to provide a financial institution risk assessment system based on big data analysis to solve the problems of insufficient data collection and inaccurate data analysis results in existing financial institution risk assessment systems. Summary of the invention
[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a financial institution risk assessment system based on big data analysis, which solves the problems raised in the above-mentioned background technology through the following scheme.
[0007] To achieve the above purpose, the present invention provides the following technical solution: a financial institution risk assessment system based on big data analysis, comprising:
[0008] Data area division module: determine the data to be collected as target data, divide the target data into various collection times according to the equal time division method, and mark them as 1, 2, ..., n;
[0009] Financial institution data collection module: includes an internal risk data collection unit and an external risk data collection unit, and transmits the collected data to the financial institution risk data analysis module; the internal risk data collection unit is used to collect leverage risk data, operational risk data and liquidity risk data; the external risk data collection unit is used to collect market risk data, customer risk data and credit risk data;
[0010] Financial institution risk data analysis module: includes an internal risk data analysis unit and an external risk data analysis unit, and transmits the analysis results to the comprehensive risk assessment module; the internal risk data analysis unit includes a leverage risk data analysis node, an operational risk data analysis node, and a liquidity risk data analysis node; the external risk data analysis unit includes a market risk data analysis node, a customer risk data analysis node, and a credit risk data analysis node;
[0011] Comprehensive risk assessment module: including comprehensive risk analysis unit, which conducts comprehensive analysis on the data transmitted by the financial institution data analysis module and transmits the analysis results to the real-time warning module;
[0012] Real-time warning module: used to establish preset values for the comprehensive risk index of financial institutions, judge the comprehensive risk index value of financial institutions based on the preset values, and save the data in the database based on the judgment results.
[0013] Preferably, the leverage risk data include capital adequacy ratio Ca, total leverage ratio Tl and capital buffer ratio Cb; the operational risk data include fraud detection algorithm detection success rate Ds, number of operational risk loss events En and number of internal control deficiencies Cn; the liquidity risk data include net stable funding ratio Fr, funding gap time Ft and short-term debt coverage ratio Dc.
[0014] Preferably, the market risk data include the VIX index Vi, the VaR value Vv and the beta value Bv of the ETF; the customer risk data include the customer concentration ratio Cr, the credit limit utilization rate Cu and the number of business complaints Bn; the credit risk data include the fund default rate Fd, the bad debt rate Bd and the loan loss reserve ratio Lr.
[0015] Preferably, the leverage risk data analysis node is used to establish a leverage risk data calculation model, import the leverage risk data transmitted by the financial institution data acquisition module into the leverage risk data calculation model, and obtain the leverage risk data risk index value; the leverage risk data calculation model is specifically expressed as: ,in represents the risk index value of leverage risk data, 0.4 represents the weight value of capital buffer ratio and total leverage ratio, and 0.2 represents the weight value of capital buffer ratio; represents the current capital adequacy ratio, Indicates the highest acceptable level of capital adequacy ratio, It indicates the minimum acceptable level of capital adequacy ratio; Indicates the current total leverage ratio, Indicates the lowest acceptable level of total leverage ratio. Indicates the maximum acceptable level of total leverage ratio; represents the current capital buffer ratio, Indicates the maximum acceptable level of capital buffer.
[0016] Preferably, the operational risk data analysis node is used to establish an operational risk data calculation model, import the operational risk data transmitted by the financial institution data acquisition module into the operational risk data calculation model, and obtain the operational risk data risk index value; the operational risk data calculation model is specifically expressed as: ,in It represents the risk index value of operational risk data, 0.5 represents the weight value of the detection success rate of the fraud detection algorithm, 0.3 represents the weight value of the number of operational risk loss events, 0.2 represents the weight value of the number of internal control deficiencies, Ds represents the detection success rate of the fraud detection algorithm, En represents the number of operational risk loss events, and Cn represents the number of internal control deficiencies.
[0017] Preferably, the liquidity risk data analysis node is used to establish a liquidity risk data calculation model, import the liquidity risk data transmitted by the financial institution data acquisition module into the liquidity risk data calculation model, and obtain the liquidity data risk index value. The liquidity risk data calculation model is specifically expressed as: in It represents the liquidity data risk index value, 0.2 represents the net stable funding ratio weight value, 0.4 represents the funding gap time and the previous short-term debt coverage ratio weight value, represents the current net stable funding ratio, Indicates the minimum value of the net stable funding ratio, Indicates the minimum and maximum values of the net stable funding ratio; Indicates the current funding gap time, Indicates the minimum time of funding gap, Indicates the maximum time of the funding gap; represents the current short-term debt coverage ratio, represents the minimum short-term debt coverage ratio, Indicates the maximum value of short-term debt coverage ratio.
[0018] Preferably, the market risk data analysis node is used to establish a market risk data calculation model, import the market risk data transmitted by the financial institution data acquisition module into the market risk data calculation model, and obtain the market data risk index value. The market risk data calculation model is specifically expressed as: ,in Indicates the market data risk index value. Represents the current VIX index, represents the current VaR value, represents the value of VaR at the i-1th time; Indicates the current beta value of the ETF.
[0019] Preferably, the customer risk data analysis node is used to establish a customer risk data calculation model, import the customer risk data transmitted by the financial institution data collection module into the customer risk data calculation model, and obtain the customer data risk index value. The customer risk data calculation model is specifically expressed as: ,in Indicates the customer data risk index value, Indicates the current customer concentration ratio, Indicates the current credit limit utilization rate, Indicates the number of current business complaints. Indicates the number of business complaints i-1 times.
[0020] Preferably, the credit risk data analysis node is used to establish a credit risk data calculation model, import the credit risk data transmitted by the financial institution data acquisition module into the credit risk data calculation model, and obtain the credit data risk index value. The credit risk data calculation model is specifically expressed as: ,in represents the default rate of funds, Bd represents the bad debt rate, and Lr represents the loan loss reserve ratio.
[0021] Preferably, the comprehensive risk risk analysis unit is used to establish a comprehensive risk risk calculation model, and import the leverage risk data risk index value, operational risk data risk index value, liquidity data risk index value, market data risk index value, customer data risk index value and credit data risk index value transmitted by the financial institution risk data analysis module into the comprehensive risk risk calculation model to obtain the comprehensive risk risk index value of the financial institution; the comprehensive risk risk calculation model is specifically expressed as: , where D represents the comprehensive risk index value of financial institutions, 0.1 represents the weight value of the leverage risk data risk index value, the operational risk data risk index value and the customer data risk index value; 0.25 represents the weight value of the liquidity data risk index value and the market data risk index value; 0.2 represents the weight value of the credit data risk index value.
[0022] Technical effects and advantages of the present invention:
[0023] 1. The present invention divides the required collected data into different collection times according to certain collection requirements through the data area division module, thereby improving the real-time and flexibility of data collection; the financial institution risk data collection module collects leverage risk data, operational risk data, liquidity risk data, market risk data, customer risk data and credit risk data, collects data from multiple angles, reduces the singleness of the data, and provides strong support for subsequent data analysis;
[0024] 2. Through the financial institution risk data analysis module, the collected data is analyzed in detail to obtain the risk index values of leverage risk data, operational risk data, liquidity data, market data, customer data and credit data, which directly reflect the potential risk issues;
[0025] 3. The comprehensive risk assessment module integrates and evaluates the data analyzed by the financial institution risk data analysis module, further improving the accuracy of the analysis results; the real-time early warning module provides real-time feedback on the analysis results, making it easier for relevant technical personnel to manage. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] Figure 1 It is a schematic diagram of the overall structure of the present invention. DETAILED DESCRIPTION
[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0028] As attached Figure 1 A financial institution risk assessment system based on big data analysis is shown, including a data area division module, a financial institution risk data collection module, a financial institution risk data analysis module, a comprehensive risk assessment module, and a real-time warning module.
[0029] In this embodiment, it is specifically necessary to explain that the output end of the data area division module is telecommunication connected to the input and output ends of the financial institution risk data collection module; the output end of the financial institution risk data collection module is telecommunication connected to the input end of the financial institution risk data analysis module; the output end of the financial institution risk data analysis module is telecommunication connected to the input end of the comprehensive risk assessment module; the output end of the comprehensive risk assessment module is telecommunication connected to the input end of the real-time warning module.
[0030] The data area division module determines the data to be collected as target data, divides the target data into various collection times in an equal time division manner, and marks them as 1, 2, ..., n.
[0031] What needs to be specifically explained in this embodiment is that the equal time division method is used to divide each target data according to its characteristics through the background information management system, and each target data is divided into different collection times according to its real-time requirements, and a system database is established to store it.
[0032] The financial institution data collection module includes an internal risk data collection unit and an external risk data collection unit, and transmits the collected data to the financial institution risk data analysis module.
[0033] In this embodiment, it should be specifically explained that the internal risk data collection unit is used to collect leverage risk data, operational risk data and liquidity risk data; the external risk data collection unit is used to collect market risk data, customer risk data and credit risk data.
[0034] In this embodiment, it should be specifically explained that the leverage risk data includes the capital adequacy ratio Ca, the total leverage ratio Tl and the capital buffer ratio Cb; the operational risk data includes the fraud detection algorithm detection success rate Ds, the number of operational risk loss events En and the number of internal control deficiencies Cn; the liquidity risk data includes the net stable funding ratio Fr, the funding gap time Ft and the short-term debt coverage ratio Dc.
[0035] The capital adequacy ratio is obtained by directly exporting data from the internal system, filling in reports required by regulators, and automatically capturing and collecting data through API interfaces; the total leverage ratio is calculated through the total assets, total liabilities and owner's financial data provided by the financial statements and balance sheets; the capital buffer ratio is calculated by querying the financial database; the fraud detection is obtained by training the fraud detection model, and different machine learning or deep learning algorithms can be selected to collect data; the number of operational risk loss events is obtained by compiling a statistical report on operational risk loss events through the background management system; the number of internal control deficiencies is obtained through the analysis and summary of internal control self-assessment reports, audit reports and internal control deficiency disclosure documents; the net stable funding ratio is obtained by dividing the total available stable funding calculated by the financial statement data, including the balance sheet and liquidity coverage ratio report, by the total required stable funding; the funding gap time is calculated by collecting financial statements, cash flow statements, and budget plan data; the short-term debt coverage ratio is calculated through the balance sheet, income statement and cash flow statement.
[0036] In this embodiment, it should be specifically explained that the market risk data includes the VIX index Vi, the VaR value Vv and the beta value Bv of the ETF; the customer risk data includes the customer concentration ratio Cr, the credit limit utilization rate Cu and the number of business complaints Bn; the credit risk data includes the fund default rate Fd, the bad debt rate Bd and the loan loss reserve ratio Lr.
[0037] The VIX index is automatically collected through the financial data crawler library; the VaR value is estimated by applying the Monte Carlo simulation statistical model through historical data and the selected confidence level; the beta value of the ETF is obtained by calculating the covariance between the ETF's return rate and the market benchmark index return rate and the variance of the market benchmark index return rate using historical data; the customer concentration ratio is analyzed through internal financial statements and customer management systems, and customers are ranked according to sales, and the sales ratio of the top few major customers to the total sales is calculated; the credit limit utilization rate is collected through an automated credit management system; the number of business complaints is obtained through information technology means, The data is collected by establishing a customer complaint database; the fund default rate is obtained by using a prediction model through a data collection and management system to evaluate and predict the loan default risk based on the customer's personal information, financial status, and credit history factors; the bad debt rate is obtained by collecting loan amounts, repayment status, overdue days, and customer credit information through an internal credit system and a customer management system, and then determined based on the internal policies and accounting standards of the financial institution; the loan loss reserve ratio is obtained by classifying loans, distinguishing them according to their risk levels, using different provision ratios for different types of loans, and then calculating the balance of the loan loss reserve based on the loan balance and the corresponding provision ratio.
[0038] The financial institution risk data analysis module includes an internal risk data analysis unit and an external risk data analysis unit, and transmits the analysis results to the comprehensive risk assessment module.
[0039] In this embodiment, it should be specifically explained that the internal risk data analysis unit includes a leverage risk data analysis node, an operational risk data analysis node, and a liquidity risk data analysis node; the external risk data analysis unit includes a market risk data analysis node, a customer risk data analysis node, and a credit risk data analysis node.
[0040] In this embodiment, it should be specifically explained that the leverage risk data analysis node is used to establish a leverage risk data calculation model, import the leverage risk data transmitted by the financial institution data acquisition module into the leverage risk data calculation model, and obtain the leverage risk data risk index value; the leverage risk data calculation model is specifically expressed as: ,in represents the risk index value of leverage risk data, 0.4 represents the weight value of capital buffer ratio and total leverage ratio, and 0.2 represents the weight value of capital buffer ratio; represents the current capital adequacy ratio, Indicates the highest acceptable level of capital adequacy ratio, It indicates the minimum acceptable level of capital adequacy ratio; Indicates the current total leverage ratio, Indicates the lowest acceptable level of total leverage ratio. Indicates the maximum acceptable level of total leverage ratio; represents the current capital buffer ratio, Indicates the maximum acceptable level of capital buffer.
[0041] In this embodiment, it is specifically required to explain that the operational risk data analysis node is used to establish an operational risk data calculation model, import the operational risk data transmitted by the financial institution data acquisition module into the operational risk data calculation model, and obtain the operational risk data risk index value; the operational risk data calculation model is specifically expressed as: ,in It represents the risk index value of operational risk data, 0.5 represents the weight value of the detection success rate of the fraud detection algorithm, 0.3 represents the weight value of the number of operational risk loss events, 0.2 represents the weight value of the number of internal control deficiencies, Ds represents the detection success rate of the fraud detection algorithm, En represents the number of operational risk loss events, and Cn represents the number of internal control deficiencies.
[0042] In this embodiment, it should be specifically explained that the liquidity risk data analysis node is used to establish a liquidity risk data calculation model, import the liquidity risk data transmitted by the financial institution data acquisition module into the liquidity risk data calculation model, and obtain the liquidity data risk index value. The liquidity risk data calculation model is specifically expressed as: in It represents the liquidity data risk index value, 0.2 represents the net stable funding ratio weight value, 0.4 represents the funding gap time and the previous short-term debt coverage ratio weight value, represents the current net stable funding ratio, Indicates the minimum value of the net stable funding ratio, Indicates the minimum and maximum values of the net stable funding ratio; Indicates the current funding gap time, Indicates the minimum time of funding gap, Indicates the maximum time of the funding gap; represents the current short-term debt coverage ratio, represents the minimum short-term debt coverage ratio, Indicates the maximum value of short-term debt coverage ratio.
[0043] In this embodiment, it should be specifically explained that the market risk data analysis node is used to establish a market risk data calculation model, import the market risk data transmitted by the financial institution data acquisition module into the market risk data calculation model, and obtain the market data risk index value. The market risk data calculation model is specifically expressed as: ,in Indicates the market data risk index value. Represents the current VIX index, represents the current VaR value, represents the value of VaR at the i-1th time; Indicates the current beta value of the ETF.
[0044] In this embodiment, it should be specifically explained that the customer risk data analysis node is used to establish a customer risk data calculation model, import the customer risk data transmitted by the financial institution data collection module into the customer risk data calculation model, and obtain the customer data risk index value. The customer risk data calculation model is specifically expressed as: ,in Indicates the customer data risk index value, Indicates the current customer concentration ratio, Indicates the current credit limit utilization rate, Indicates the number of current business complaints. Indicates the number of business complaints i-1 times.
[0045] In this embodiment, it should be specifically explained that the credit risk data analysis node is used to establish a credit risk data calculation model, import the credit risk data transmitted by the financial institution data acquisition module into the credit risk data calculation model, and obtain the credit data risk index value. The credit risk data calculation model is specifically expressed as: ,in represents the default rate of funds, Bd represents the bad debt rate, and Lr represents the loan loss reserve ratio.
[0046] The comprehensive risk assessment module includes a comprehensive risk analysis unit, which comprehensively analyzes the data transmitted by the financial institution data analysis module and transmits the analysis results to the real-time warning module.
[0047] In this embodiment, it should be specifically explained that the comprehensive risk risk analysis unit is used to establish a comprehensive risk risk calculation model, and the leverage risk data risk index value, operational risk data risk index value, liquidity data risk index value, market data risk index value, customer data risk index value and credit data risk index value transmitted by the financial institution risk data analysis module are imported into the comprehensive risk risk calculation model to obtain the comprehensive risk risk index value of the financial institution; the comprehensive risk risk calculation model is specifically expressed as: , where D represents the comprehensive risk index value of financial institutions, 0.1 represents the weight value of the leverage risk data risk index value, the operational risk data risk index value and the customer data risk index value; 0.25 represents the weight value of the liquidity data risk index value and the market data risk index value; 0.2 represents the weight value of the credit data risk index value.
[0048] The real-time warning module is used to establish a preset value of the comprehensive risk index of a financial institution, judge the value of the comprehensive risk index of the financial institution according to the preset value of the comprehensive risk index of the financial institution, and save the data into a database according to the judgment result.
[0049] In this embodiment, it should be specifically noted that the preset value of the comprehensive risk index of the financial institution is marked as , when D< When D When , it means that the comprehensive risk index value of the financial institution is greater than or equal to the preset value of the comprehensive risk index of the financial institution, indicating that the comprehensive risk of the financial institution is high, a warning signal will be issued to relevant technical personnel, and the comprehensive risk index value of the financial institution will be recorded.
[0050] The present invention divides the required collected data into different collection times according to certain collection requirements through the data area division module, thereby improving the real-time and flexibility of data collection; collects leverage risk data, operational risk data, liquidity risk data, market risk data, customer risk data and credit risk data through the financial institution risk data collection module, collects data from multiple angles, reduces the singleness of the data, and provides strong support for subsequent data analysis; analyzes the collected data in detail through the financial institution risk data analysis module to obtain the leverage risk data risk index value, operational risk data risk index value, liquidity data risk index value, market data risk index value, customer data risk index value and credit data risk index value, which intuitively reflects the potential risk problems; integrates and evaluates the data analyzed by the financial institution risk data analysis module through the comprehensive risk assessment module, thereby further improving the accuracy of the analysis results; and provides real-time feedback on the analysis results through the real-time early warning module, which is convenient for relevant technical personnel to manage.
[0051] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;
[0052] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A financial institution risk assessment system based on big data analysis, characterized in that: include: Data area division module: the data to be collected is determined as the target data, and the target data is divided into various collection times in an equal time division manner, and marked as 1, 2, ..., n in sequence; Financial institution data collection module: includes internal risk data collection unit and external risk data collection unit, and transmits the collected data to the financial institution risk data analysis module; The internal risk data collection unit is used to collect leverage risk data, operational risk data and liquidity risk data; The external risk data collection unit is used to collect market risk data, customer risk data and credit risk data; The leverage risk data include capital adequacy ratio Ca, total leverage ratio Tl and capital buffer ratio Cb; The operational risk data include the fraud detection algorithm detection success rate Ds, the number of operational risk loss events En, and the number of internal control deficiencies Cn; the liquidity risk data include the net stable funding ratio Fr, the funding gap time Ft, and the short-term debt coverage ratio Dc; The market risk data includes the VIX index Vi, the VaR value Vv and the beta value Bv of the ETF; the customer risk data includes the customer concentration ratio Cr, the credit limit utilization ratio Cu and the number of business complaints Bn; the credit risk data includes the fund default rate Fd, the bad debt rate Bd and the loan loss reserve ratio Lr; Financial institution risk data analysis module: includes internal risk data analysis unit and external risk data analysis unit, and transmits the analysis results to the comprehensive risk assessment module; The internal risk data analysis unit includes a leverage risk data analysis node, an operational risk data analysis node, and a liquidity risk data analysis node; The external risk data analysis unit includes a market risk data analysis node, a customer risk data analysis node and a credit risk data analysis node; The leverage risk data analysis node is used to establish a leverage risk data calculation model, import the leverage risk data transmitted by the financial institution data acquisition module into the leverage risk data calculation model, and obtain the leverage risk data risk index value; the leverage risk data calculation model is specifically expressed as: ,in represents the risk index value of leverage risk data, 0.4 represents the weight value of capital buffer ratio and total leverage ratio, and 0.2 represents the weight value of capital buffer ratio; represents the current capital adequacy ratio, Indicates the highest acceptable level of capital adequacy ratio, It indicates the minimum acceptable level of capital adequacy ratio; Indicates the current total leverage ratio, Indicates the lowest acceptable level of total leverage ratio. Indicates the maximum acceptable level of total leverage ratio; represents the current capital buffer ratio, Indicates the maximum acceptable level of capital buffer; The operational risk data analysis node is used to establish an operational risk data calculation model, import the operational risk data transmitted by the financial institution data acquisition module into the operational risk data calculation model, and obtain the operational risk data risk index value; the operational risk data calculation model is specifically expressed as: ,in represents the risk index value of operational risk data, 0.5 represents the weight value of the detection success rate of the fraud detection algorithm, 0.3 represents the weight value of the number of operational risk loss events, 0.2 represents the weight value of the number of internal control deficiencies, Ds represents the detection success rate of the fraud detection algorithm, En represents the number of operational risk loss events, and Cn represents the number of internal control deficiencies; The liquidity risk data analysis node is used to establish a liquidity risk data calculation model, import the liquidity risk data transmitted by the financial institution data acquisition module into the liquidity risk data calculation model, and obtain the liquidity data risk index value. The liquidity risk data calculation model is specifically expressed as: in It represents the liquidity data risk index value, 0.2 represents the net stable funding ratio weight value, 0.4 represents the funding gap time and the previous short-term debt coverage ratio weight value, represents the current net stable funding ratio, Indicates the minimum value of the net stable funding ratio, Indicates the maximum value of the net stable funding ratio; Indicates the current funding gap time, Indicates the minimum time of funding gap, Indicates the maximum time of the funding gap; represents the current short-term debt coverage ratio, represents the minimum short-term debt coverage ratio, Indicates the maximum value of short-term debt coverage ratio; The market risk data analysis node is used to establish a market risk data calculation model, import the market risk data transmitted by the financial institution data acquisition module into the market risk data calculation model, and obtain the market data risk index value. The market risk data calculation model is specifically expressed as: ,in Indicates the market data risk index value. represents the current VIX index, represents the current VaR value, represents the value of VaR at the i-1th time; Indicates the current beta value of the ETF; The customer risk data analysis node is used to establish a customer risk data calculation model, import the customer risk data transmitted by the financial institution data acquisition module into the customer risk data calculation model, and obtain the customer data risk index value. The customer risk data calculation model is specifically expressed as: ,in Indicates the customer data risk index value, Indicates the current customer concentration ratio, Indicates the current credit limit utilization rate, Indicates the number of current business complaints. Indicates the number of business complaints i-1 times; The credit risk data analysis node is used to establish a credit risk data calculation model, import the credit risk data transmitted by the financial institution data acquisition module into the credit risk data calculation model, and obtain the credit data risk index value. The credit risk data calculation model is specifically expressed as: ,in represents the default rate of funds, Bd represents the bad debt rate, and Lr represents the loan loss reserve ratio; Comprehensive risk assessment module: including comprehensive risk analysis unit, which conducts comprehensive analysis on the data transmitted by the financial institution data analysis module and transmits the analysis results to the real-time warning module; The comprehensive risk analysis unit is used to establish a comprehensive risk calculation model, import the leverage risk data risk index value, operational risk data risk index value, liquidity data risk index value, market data risk index value, customer data risk index value and credit data risk index value transmitted by the financial institution risk data analysis module into the comprehensive risk calculation model, and obtain the comprehensive risk index value of the financial institution; the comprehensive risk calculation model is specifically expressed as: , where D represents the comprehensive risk index value of financial institutions, and 0.1 represents the weight value of the leverage risk data risk index value, the operational risk data risk index value, and the customer data risk index value; 0.25 represents the weight value of the liquidity data risk index value and the market data risk index value; 0.2 represents the weight value of the credit data risk index value; Real-time warning module: used to establish preset values for the comprehensive risk index of financial institutions, judge the comprehensive risk index value of financial institutions based on the preset values, and save the data in the database based on the judgment results.
Citation Information
Patent Citations
Bank credit asset risk analysis method and system based on AI technology
CN118134633A
Enterprise credit risk assessment method and system based on big data technology
CN118411244A
