CN117875770A - Credit rating method and device for object, storage medium and electronic device - Google Patents
Credit rating method and device for object, storage medium and electronic device Download PDFInfo
- Publication number
- CN117875770A CN117875770A CN202410009648.9A CN202410009648A CN117875770A CN 117875770 A CN117875770 A CN 117875770A CN 202410009648 A CN202410009648 A CN 202410009648A CN 117875770 A CN117875770 A CN 117875770A
- Authority
- CN
- China
- Prior art keywords
- target
- financial
- sample
- predicted
- indexes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 238000012417 linear regression Methods 0.000 claims abstract description 77
- 238000004364 calculation method Methods 0.000 claims description 37
- 238000012545 processing Methods 0.000 claims description 28
- 230000006399 behavior Effects 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 8
- 238000004519 manufacturing process Methods 0.000 abstract description 11
- 238000012360 testing method Methods 0.000 description 25
- 238000011002 quantification Methods 0.000 description 8
- 230000007306 turnover Effects 0.000 description 8
- 238000007726 management method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 238000010998 test method Methods 0.000 description 4
- 230000002411 adverse Effects 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004904 shortening Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/12—Accounting
- G06Q40/125—Finance or payroll
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Technology Law (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides a credit rating method and device of an object, a storage medium and electronic equipment, wherein the method comprises the following steps: obtaining a target macro economic factor for representing a macro variation trend predicted for financial data in a future period, inputting the target macro economic factor into a pre-trained target linear regression model to obtain a set of predicted financial indexes, wherein the predicted financial indexes represent the predicted financial data in the future period, inputting the set of predicted financial indexes into a target industry rating model determined based on a rule engine to obtain target credit ratings of target objects, and the rule engine is used for recording industry rating models of different industries to generate the credit ratings of the objects in different industries in batches. By the method and the device, the technical problem that the production efficiency of the credit rating is low due to the fact that the production time of the credit rating is long is solved.
Description
Technical Field
The embodiment of the application relates to the field of computers, in particular to a credit rating method and device for an object, a storage medium and an electronic device.
Background
Currently, in the case of performing credit rating on a large number of objects, the credit rating of the objects is sequentially produced by directly using the existing credit rating model in the related art, and the credit rating of a plurality of objects cannot be obtained at one time due to the excessive number of objects, that is, only one credit rating of an object can be obtained by using the credit rating model at a time, and in the process of performing credit rating on a large number of objects, there is a problem that the production time of credit rating is long, resulting in lower production efficiency of credit rating.
In view of the above problems, no effective solution has been proposed at present.
Disclosure of Invention
The embodiment of the application provides a credit rating method and device for an object, a storage medium and an electronic device, which are used for at least solving the problem that the production efficiency of credit rating is low due to long production time of the credit rating.
According to one aspect of the present application, there is provided a credit rating method of an object, including: obtaining a target macro-economic factor, wherein the target macro-economic factor represents a macro-variation trend predicted for financial data in a future period; inputting the target macro economic factors into a pre-trained target linear regression model to obtain a group of predicted financial indexes, wherein the target linear regression model is a model obtained by training an initial linear regression model by adopting sample macro economic factors and sample financial indexes, the sample macro economic factors and the sample financial indexes are financial data generated in a historical period, and the predicted financial indexes represent the predicted financial data in the future period; and inputting the set of predicted financial indexes into a target industry rating model determined based on a rule engine to obtain target credit rating of the target object, wherein the rule engine is used for recording the industry rating models of different industries so as to generate the credit rating of the objects in different industries in batches.
According to another aspect of the present application, there is provided a credit rating apparatus of an object, including: the acquisition module is used for acquiring a target macro economic factor, wherein the target macro economic factor represents a macro change trend predicted for financial data in a future period; the prediction module is used for inputting the target macro economic factors into a pre-trained target linear regression model to obtain a group of predicted financial indexes, wherein the target linear regression model is a model obtained by training an initial linear regression model by adopting sample macro economic factors and sample financial indexes, the sample macro economic factors and the sample financial indexes are financial data generated in a historical period, and the predicted financial indexes represent the predicted financial data in the future period; and the rating module is used for inputting the group of predictive financial indexes into a target industry rating model determined based on a rule engine to obtain target credit rating of the target object, wherein the rule engine is used for recording the industry rating models of different industries so as to generate the credit rating of the objects in different industries in batches.
Optionally, the apparatus is configured to input the set of predictive financial indicators into a target industry rating model determined based on a rules engine to obtain a target credit rating of the target object by: obtaining a target configuration file from the rule engine; analyzing the target configuration file to obtain target calculation logic; processing the set of predicted financial indexes according to the target calculation logic to obtain a set of modeling indexes; determining a target default probability of the target object according to the set of modeling indexes; and determining the target credit rating on a preset scale according to the target default probability.
Optionally, the apparatus is configured to determine the target breach probability of the target object according to the set of modeling metrics by: determining qualitative and quantitative default probabilities of the target object according to the set of modeling indexes; and determining the target default probability according to the qualitative default probability and the qualitative default probability.
Optionally, the apparatus is configured to determine the target breach probability according to the qualitative breach probability and the qualitative breach probability by: acquiring behavior data of the target object; and determining the target default probability according to the behavior data, the qualitative default probability and the qualitative default probability.
Optionally, the device is configured to process the set of predicted financial indicators according to the target calculation logic to obtain a set of modeling indicators by: obtaining a first predicted financial index and a second predicted financial index, wherein the set of predicted financial indexes includes the first predicted financial index and the second predicted financial index; and calculating the first predicted financial index and the second predicted financial index according to the target calculation logic to determine the target modeling index, wherein the group of modeling indexes comprises the target modeling index, and the target calculation logic comprises a calculation mode used by the target industry rating model for the target modeling index.
Optionally, the device is further configured to: inputting the target macro economic factors into a pre-trained target linear regression model, and acquiring the sample macro economic factors and the sample financial indexes before obtaining a group of predicted financial indexes, wherein the sample financial indexes are used for marking the sample macro economic factors; inputting the sample macro economic factors into an initial linear regression model to obtain sample predictive financial indexes; training the initial linear regression model according to the sample prediction financial index and the sample financial index to obtain the target linear regression model, wherein the target linear regression model is matched with the index type of the sample financial index, and different index types correspond to different target linear regression models.
Optionally, the device is configured to input the sample macro economic factor into an initial linear regression model to obtain a sample predicted financial index by: acquiring the type number of the sample macro economic factors, and initializing a corresponding number of target coefficients based on the type number; and weighting the corresponding sample macro economic factors by using each target coefficient, and summing with a target white noise variable to obtain the sample prediction financial index.
According to a further embodiment of the present application, there is also provided a computer readable storage medium having stored therein a computer program, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.
According to a further embodiment of the present application, there is also provided an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.
In the embodiment of the application, the target macro-economic factor is obtained, wherein the target macro-economic factor represents the macro-variation trend predicted for the financial data in a future period; inputting a target macro economic factor into a pre-trained target linear regression model to obtain a group of predicted financial indexes, wherein the target linear regression model is a model obtained by training an initial linear regression model by adopting a sample macro economic factor and a sample financial index, the sample macro economic factor and the sample financial index are financial data generated in a historical period, and the predicted financial index represents predicted financial data in a future period; inputting a group of prediction financial indexes into a target industry rating model determined based on a rule engine to obtain target credit rating of a target object, wherein the rule engine is used for recording industry rating models of different industries to generate the credit rating of the objects in different industries in batches, so that the aim of shortening the time-consuming time of carrying out credit rating on the objects is fulfilled, the technical effects of producing the credit rating in batches and saving computing resources are realized, and further, the technical problem that the production efficiency of the credit rating is lower due to longer production time of the credit rating is solved.
Drawings
FIG. 1 is a block diagram of a hardware architecture of a mobile terminal for a credit rating method for an object according to an embodiment of the present application;
FIG. 2 is a flow chart of a credit rating method for an object according to an embodiment of the present application;
FIG. 3 is a flow chart of a credit rating method for an object according to an embodiment of the present application;
FIG. 4 is a flow chart of a credit rating method for yet another object according to an embodiment of the present application;
FIG. 5 is a flow chart of a credit rating method for yet another object according to an embodiment of the present application;
FIG. 6 is a block diagram of a credit rating device for an object according to an embodiment of the application.
Detailed Description
Embodiments of the present application will be described in detail below with reference to the accompanying drawings in conjunction with the embodiments.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order.
First, partial terms or terminology appearing in describing embodiments of the present application are applicable to the following explanation:
and (3) pressure test: a risk management and analysis tool is used for analyzing the impact degree of assumed, extreme but possibly occurring adverse scenes on the whole bank or the asset combination, evaluating the negative influence of the adverse scenes on the quality, the profitability, the capital level and the liquidity of the bank asset combination, evaluating and judging the vulnerability of a single asset combination, a single institution or a bank group, taking necessary measures, and performing pressure test to analyze the influence of various risk factors on the quality, the profitability, the capital level and the liquidity of the bank asset, identify and locate weak links faced by banking business in the extreme scenes, improve the resistance of the bank to the extreme risk events and guarantee the safe and stable operation of the bank.
Barsel rating model: according to the requirements of the Basel regulatory committee and the domestic capital management method, the credit risk of the client is evaluated according to factors such as credit history, financial condition and transaction behavior of the client, so that the process of determining the credit level of the client can help financial institutions to formulate reasonable risk management strategies, reduce risk loss and improve client satisfaction and profitability of the financial institutions.
Two-step barcel PD mapping model: the two-step barcel PD mapping model is a stress test method combined with the current barcel rating results. The financial index related to the Basel rating model is utilized to build a linear model with the macro economic factors, so that the pressure scene of the macro economic factors is conducted to PD (probability of default ), and the method can be used for measuring the influence of a plurality of risk factors on bank risk exposure and bank risk bearing capacity caused by certain extreme adverse events under the assumption that the risk factors change simultaneously.
Rule engine: an automated rule-based tool for identifying, reasoning, classifying, and predicting tasks. It can automatically extract rules from data and perform corresponding operations according to the priority and condition of the rules, and is commonly used in the fields of machine learning, data mining, natural language processing, finance, medical, retail, etc. The rule engine can automatically generate rules, expand rules, modify rules, monitor rules, etc., thereby improving the efficiency and accuracy of the system. In the barsel rating model implementation, a rules engine is typically used to implement the rating of the customer.
Batch processing: without human intervention, a computer program performs a processing mode of a series of tasks based on a batch of inputs, so that a large amount of data can be rapidly acquired and processed, and the data processing efficiency and accuracy are improved.
And (3) online treatment: the real-time processing service indicates that the receiving and processing of the request are real-time, and the processing result is transmitted to the user in real time once the processing is finished, so that the complex data processing task can be completed, and the accurate and reliable result can be obtained in real time.
MPP: massively Parallel Processing, namely a massive parallel processing technology, in the application refers to a database management system capable of processing large-scale data sets, is an important database tool for data processing and analysis, can improve the consistency, reliability and performance of data, and is suitable for various different business requirements.
The method embodiments provided in the embodiments of the present application may be performed in a mobile terminal, a computer terminal or similar computing device. Taking the operation on a mobile terminal as an example, fig. 1 is a block diagram of a hardware structure of a mobile terminal of a credit rating method of an object according to an embodiment of the present application. As shown in fig. 1, a mobile terminal may include one or more (only one is shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 for communication functions and a terminal device 108. It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely illustrative and not limiting of the structure of the mobile terminal described above. For example, the mobile terminal may also include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1.
The memory 104 may be used to store computer programs, such as software programs of application software and modules, such as computer programs corresponding to the credit rating method of the object in the embodiment of the application, and the processor 102 executes the computer programs stored in the memory 104 to perform various functional applications and data processing, that is, implement the above-mentioned method. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission means 106 is arranged to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used to communicate with the internet wirelessly.
Alternatively, in the present embodiment, the credit rating method of the above object may also be implemented by a server, or implemented by a terminal device and a server together.
The above is merely an example, and the present embodiment is not particularly limited.
Optionally, as an optional implementation manner, fig. 2 is a flowchart of a credit rating method of an object according to an embodiment of the present application, and as shown in fig. 2, the credit rating method of the object includes:
s202, acquiring a target macro economic factor, wherein the target macro economic factor represents a macro change trend predicted for financial data in a future period;
alternatively, in embodiments of the present application, the target macro economic factors may include, but are not limited to, an overall economic growth rate, a currency expansion rate, a interest rate, a exchange rate, etc., and the financial data may be analyzed to determine a trend of change in the financial data under different economic pressure scenarios by analyzing the influence of the target macro economic factors, and the financial data may include, but is not limited to, asset liability sheet data, such as asset total, liability total, owner equity, liquidity asset ratio, liability ratio, etc., profit sheet data, such as business income, net profit, gross profit, net profit, business profit, etc., cash flow, investment activity cash flow, financing activity cash flow, free cash flow, etc., business data, such as asset turnover, accounts receivable turnover, inventory turnover, fixed asset turnover, etc., growth data, such as business income growth rate, net profit growth rate, per share growth rate, asset growth rate, etc.
In particular, the target macroeconomic factor may be used to represent a macroeconomic trend in a future period, for example, the target macroeconomic factor may represent a slow down of economic growth, an upgrade of trade war, fluctuation of financial market, etc. in this case, since the macroeconomic change occurs, the financial data is also affected by the target macroeconomic factor, and the change occurs, for example, the slow down of economic growth represents a slow down of income growth of the object, a slow down of return rate of investment, and a slow down of financial growth speed, in which the financial data includes the total assets of the object, which are also affected to be reduced.
S204, inputting a target macro economic factor into a pre-trained target linear regression model to obtain a group of predicted financial indexes, wherein the target linear regression model is a model obtained by training an initial linear regression model by adopting a sample macro economic factor and a sample financial index, the sample macro economic factor and the sample financial index are financial data generated in a historical period, and the predicted financial index represents the predicted financial data in a future period;
illustratively, the set of predicted financial indicators for the future time period is obtained by inputting a target macroeconomic factor into the target linear regression model trained from the initial linear regression model, which is a statistical model for establishing a linear relationship between continuous variables, and describing the relationship between the independent and dependent variables by finding a best fit straight line. The linear regression model assumes that there is a linear relationship between the independent and dependent variables, i.e., the dependent variable may be predicted by a linear combination of independent variables, and the set of predicted financial indicators may be understood as a set of predicted financial indicators that are output via the target linear regression model during a future time period under the influence of a target macro-economic factor, which may include, but is not limited to, total assets, revenue, total liabilities, owner equity, liquidity ratio, liability ratio, etc.
Alternatively, in the embodiment of the present application, the sample macroeconomic factor may be understood as a macroeconomic factor existing in the history period, in other words, a macroeconomic change trend of the history period may be known by the sample macroeconomic factor, and the sample financial index may be understood as a financial index having a correlation with the sample macroeconomic factor in the history period, that is, the sample financial index is affected by the sample macroeconomic factor.
Further, the initial linear regression model is trained using the sample macro economic factors and the sample financial indicators to obtain a best fit straight line for the initial linear regression model, which may be expressed, for example, as:
Y＝β 0 +β 1 X 1 +β 2 X 2 +...+β n X n +ε
wherein Y represents a predicted financial index, X 1 ,X 2 ,...,X n Multiple values representing sample macroeconomic factors, e.g., overall economic growth rate, draft rate, interest rate, exchange rate, etc., beta 0 ,β 1 ,β 2 ,...,β n Representing model parameters, ε represents an error term, and a best fit line can be found by minimizing the error term, thereby yielding a set of predicted financial indicators.
S206, inputting a group of prediction financial indexes into a target industry rating model determined based on a rule engine to obtain target credit rating of a target object, wherein the rule engine is used for recording industry rating models of different industries so as to generate the credit rating of the objects in different industries in batches.
Optionally, in an embodiment of the present application, the rule engine may include, but is not limited to, an XML configuration file, where the rule engine may include, but is not limited to, parameters including a loan amount, a loan term, an interest rate, and some calculation rules, such as an interest rate calculation formula, a repayment manner, and so on, for example, after the XML configuration file used to represent the rule engine is parsed by the parser, a specific loan interest rate calculation logic may be generated according to the parameters and the calculation formulas recorded in the XML configuration file, to calculate information such as a loan interest rate, a repayment plan, and further determine the credit rating of the object according to the loan interest rate and the repayment plan.
It should be noted that, the rating models corresponding to different industries may be different, and the rule engine may include, but is not limited to, a plurality of rating models corresponding to different industries, that is, one industry may correspond to one rating model, when the credit rating of the object is generated according to each rating model, the processing manner of the financial data of the object may be different, and besides using a set of predicted financial indexes corresponding to the object, the credit rating of the object may be performed in combination with a part of the financial indexes obtained from a financial report or the like.
Illustratively, fig. 3 is a flow chart of a credit rating method of an object according to an embodiment of the present application, as shown in fig. 3, the rating data 302 may include, but is not limited to, financial data and a target macro economic factor, a set of predicted financial indexes corresponding to the target object is predicted by the target linear regression model, and the set of predicted financial indexes is input into the target industry rating model determined in the rule engine 304 to generate a target credit rating 306 of the target object, where the target credit rating may be understood that, by rating the credit quality of the target object, a risk that the target object may appear in a future period is obtained, for example, a higher target credit rating of the target object may indicate that the target object has a smaller probability of occurrence of a breach in the future period, and a lower risk, whereas a lower target credit rating of the target object may indicate that the target object has a larger probability of occurrence of breach in the future period and a higher risk.
Further, when credit ratings of a large number of objects are obtained, financial data of the large number of objects may be stored in a distributed database, rating models corresponding to the objects are determined from the rule engines respectively, and the credit ratings of the objects are simultaneously produced by using the corresponding rating models.
In an exemplary embodiment, fig. 4 is a flowchart of a credit rating method of an object according to an embodiment of the present application, where the credit rating method of an object may be applied to a stress test application scenario in which a banking system performs a credit rating of a customer in batches, as shown in fig. 4:
s402, defining pressure test targets for carrying out credit rating on customers in batches by banks, determining risk factors, and designing pressure scenes, namely setting target macro economic factors;
s404, collecting financial data of the bank batch customers and interaction data generated by customer accounts, determining a testing method, and performing pressure testing of credit ratings of the batch customers to obtain credit rating results of the batch customers;
and S406, determining potential risks and fragile links existing in the system according to credit rating results of the batch clients, and taking improvement measures.
Wherein fig. 5 is a flow chart of a credit rating method of another object according to an embodiment of the present application, in step S406, as shown in fig. 5, performing a stress test of credit rating of a batch client may include, but is not limited to, the following steps:
s502, inputting target macro economic factors into a pre-trained target linear regression model to obtain a group of prediction financial indexes of different clients;
S504, inputting different prediction financial indexes of each client into a specified industry rating model in a rule engine to obtain qualitative default probability and quantitative default probability of each client, wherein the qualitative default probability is a classification result according to the rating model, the object can be divided into different default probability grades, such as high risk, medium risk, low risk and the like, and the quantitative default probability can be determined through a logistic regression model;
s506, the qualitative default probability and the quantitative default probability of each client are processed by using a data processing mode provided by a rule engine so as to obtain the target default probability of each client, and further, the credit rating results of the clients in batches are obtained;
s508, the qualitative default probability of each customer is processed by using the data processing mode provided by the rule engine, and the quantitative default probability and the interactive data generated by the customer account are processed to obtain the target default probability of each customer, so as to obtain the credit rating results of the batch customers.
According to the embodiment of the application, the target macro-economic factor is obtained, wherein the target macro-economic factor represents the macro-variation trend predicted for the financial data in a future period; inputting a target macro economic factor into a pre-trained target linear regression model to obtain a group of predicted financial indexes, wherein the target linear regression model is a model obtained by training an initial linear regression model by adopting a sample macro economic factor and a sample financial index, the sample macro economic factor and the sample financial index are financial data generated in a historical period, and the predicted financial index represents predicted financial data in a future period; inputting a group of prediction financial indexes into a target industry rating model determined based on a rule engine to obtain target credit rating of a target object, wherein the rule engine is used for recording industry rating models of different industries to generate the credit rating of the objects in different industries in batches, so that the aim of shortening the time-consuming time of carrying out credit rating on the objects is fulfilled, the technical effects of producing the credit rating in batches and saving computing resources are realized, and further, the technical problem that the production efficiency of the credit rating is lower due to longer production time of the credit rating is solved.
As an alternative, the inputting the set of predicted financial indexes into a target industry rating model determined based on a rule engine to obtain a target credit rating of the target object includes: obtaining a target configuration file from the rule engine; analyzing the target configuration file to obtain target calculation logic; processing the set of predicted financial indexes according to the target calculation logic to obtain a set of modeling indexes; determining a target default probability of the target object according to the set of modeling indexes; and determining the target credit rating on a preset scale according to the target default probability.
Alternatively, in the embodiment of the present application, the target profile may include, but is not limited to, an XML-format profile, where the target profile may be used to define conditions, flows, data requirements, and how to evaluate test results, and the target profile may include, for example, a total asset turnover rate of the object may be determined by a ratio of sales of the object to the total asset, and the set of modeling indexes may include, but is not limited to, a debt income ratio, a liability ratio, a total asset turnover rate, and the like.
Further, the above-mentioned target calculation logic is obtained by parsing the target configuration file, and the target calculation logic may be understood as an algorithm or a model for calculating and evaluating the credit rating of the object, and the target calculation logic defines how the credit rating of the object is obtained from a set of predicted financial indexes of the object, that is, the set of predicted financial indexes are processed based on the target calculation logic to obtain a set of modeling indexes, where any one of the set of modeling indexes may be determined by one or more predicted financial indexes of the set of predicted financial indexes, for example, a "total asset turnover rate" of the one of the target is obtained according to a "sales amount" of the one predicted financial index and another "total asset" of the other predicted financial index, and in generating the set of modeling indexes, data cleaning, outlier processing, normalization processing, missing value filling, and the like may be included, but not limited to. And further, combining the set of modeling indexes and the target industry rating model to generate qualitative default probabilities of the target objects, and quantifying the default probabilities, so as to obtain target default probabilities based on the qualitative default probabilities.
For example, the target offence probability of the target object is mapped to the preset scale to obtain a target credit level corresponding to the target offence probability, where the preset scale may be preset, for example, AAA indicates that the credit level is highest, AA indicates that the credit level is higher, a indicates that the credit level is high, and the like, each credit level corresponds to a specific range of target offence probabilities, for example, the target offence probability of the target object is greater than or equal to 0.9, and the corresponding target credit level of the target object is AA.
As an alternative, the determining the target default probability of the target object according to the set of modeling indexes includes: determining qualitative and quantitative default probabilities of the target object according to the set of modeling indexes; and determining the target default probability according to the qualitative default probability and the qualitative default probability.
Specifically, achieving the target credit rating for the target object based on a set of predicted financial indicators for the target object and a target industry rating model corresponding to the target object in a rules engine may be determined by:
s1, calculating to obtain qualitative default probability and quantitative default probability through the following formula:
S＝-∑I i ×W i
PD Qualitative nature ＝1/(1+exp(dxjzcs*S-dxcs))
PD Quantification of ＝1/(1+e -∑a j ×b j ))
Wherein PD Qualitative nature Representing qualitative default probabilities, PD Quantification of Indicating quantitative default probability, I is a qualitative index, W i For the weight of each qualitative index, i is the number of qualitative indexes, qualitative conversion is performed on S to obtain qualitative offence probability, dxjzcs is a score regression coefficient, dxcs is a score constant term, a is a quantitative index, b j For the weight of the quantitative index, j is the number of the quantitative index, and a group of predicted financial indexes comprise qualitative indexes and quantitative indexes.
S2, obtaining a target default probability by using the qualitative default probability and the quantitative default probability, wherein the target default probability (Probability of Default, PD) can represent the possibility that the object cannot fulfill the related obligations according to the contract requirements in a future period, and the target default probability is a key index of credit risk measurement and is used for evaluating the default risk of the object, and the specific implementation steps can include but are not limited to:
PD mixing ＝W Weighting of *(W Quantification of *PD Quantification of +W Qualitative nature *PD Qualitative nature )+
W Regression *(1/(1+e-(β Intercept of (intercept of) +β Qualitative nature *PD Qualitative nature +β Quantification of *PD Quantification of )))
K＝((1-CT)*default sample )/(1-default sample )*CT)
PD Target object ＝PD Mixing /((1-PD Mixing )*K+PD Mixing )
Wherein PD Target object Representing target violation probability, CT is long-term average violation probability, W Weighting of 、W Regression 、W Quantification of And W is equal to Qualitative nature All are preset weights and PD Mixing Representing a temporary parameter, beta, in the process of calculating the target violation probability by qualitative and quantitative violation probabilities Intercept of (intercept of) ，β Qualitative nature Beta Quantification of Default for preset coefficients sample Representing the modeled sample violation rate.
As an alternative, the determining the target breach probability according to the qualitative breach probability and the qualitative breach probability includes: acquiring behavior data of the target object; and determining the target default probability according to the behavior data, the qualitative default probability and the qualitative default probability.
Alternatively, in the present application, the above behavior data may be understood as interactive behavior data generated by an object account used by a target object, for example, a client account in a banking system, where the target object is a banking client, and the behavior data may include, but is not limited to, overdue condition, deposit condition, average credit ratio, and the like of the target object.
In an exemplary embodiment, the target breach probability of the target object may be determined by the following method, and the specific implementation steps may include, but are not limited to:
s1, summing the scores of the single qualitative indexes obtained by each qualitative module of the target object, and carrying out product processing on the result obtained by summation and a preset qualitative elastic management parameter to obtain a qualitative score;
S2, summing the scores of the single quantitative indexes obtained by each quantitative module, and multiplying the result obtained by summation with preset quantitative bullet management parameters to obtain quantitative scores;
s3, summing the scores of the single behavior indexes obtained by each behavior module, and multiplying the result obtained by summation with preset behavior elastic management parameters to obtain account behavior scores, wherein the behavior data comprise the behavior indexes;
s4, respectively distributing weights for qualitative scores, quantitative scores and account behavior scores for weighted summation to obtain customer scores;
s5, according to the target breach probability obtained by the following formula according to the customer score in S4, the target breach probability=max (e regression coefficient×customer score+constant term/(k+e regression coefficient×customer score+constant term), 0.6%).
As an alternative, the processing the set of predicted financial indicators according to the target calculation logic to obtain a set of modeling indicators includes: acquiring a first predicted financial index and a second predicted financial index, wherein the set of predicted financial indexes includes the first predicted financial index and the second predicted financial index; and calculating the first predicted financial index and the second predicted financial index according to the target calculation logic to determine the target modeling index, wherein the group of modeling indexes comprises the target modeling index, and the target calculation logic comprises a calculation mode used by the target industry rating model for the target modeling index.
Optionally, in this embodiment of the present application, the first predicted financial index and the second predicted financial index are predicted financial indexes in the set of predicted financial indexes, and the target calculation logic is configured to calculate how to process the first predicted financial index and the second predicted financial index to obtain the target modeling index, where the target modeling index is one modeling index in the set of modeling indexes.
In an exemplary embodiment, taking a banking system as an example, the target object is a banking customer, the first predicted financial index is a total amount of liabilities of the target object in a future period predicted according to a target linear regression model, which may include, but is not limited to, mobile liabilities and long-term liabilities, the second predicted financial index is a total amount of assets of the target object in the future period predicted according to the target linear regression model, which may include, but is not limited to, mobile assets and fixed assets, and the like, and one modeling index of the target object is an asset liability rate, and the target calculation logic includes the following formula:
liability = total liability/total asset x 100%
Further, assuming that the lower the asset liability of the target object is, it may indicate that the financial risk of the target object is lower and the liability is stronger; while a higher liability rate may indicate a higher financial risk and weaker liability for the target object.
As an alternative, before the target macro economic factor is input into the pre-trained target linear regression model to obtain a set of predicted financial indexes, the method further includes: acquiring the sample macro economic factor and the sample financial index, wherein the sample financial index is used for marking the sample macro economic factor; inputting the sample macro economic factors into an initial linear regression model to obtain sample predictive financial indexes; training the initial linear regression model according to the sample predicted financial index and the sample financial index to obtain the target linear regression model, wherein the target linear regression model is matched with the index type of the sample financial index, and different index types correspond to different target linear regression models.
Illustratively, the sample financial index history period corresponds to the sample macro economic factor, in other words, it is assumed that the sample macro economic factor indicates that the economy of the history period is in a low-vage period, and at this time, the sample financial index may reflect the economic condition of the history period as well.
Further, the sample macro economic factor is input into the initial linear regression model, the initial linear regression model predicts the sample financial index to obtain a sample predicted financial index, and the parameters of the initial linear regression model are continuously adjusted to enable the sample predicted financial index to be closer to the sample financial index, so that the purpose of training the initial linear regression model into the target linear regression model is achieved, at the moment, the target linear regression model can be used for predicting the financial index of a future period, namely, the target macro economic factor corresponding to the future period is input into the target linear regression model, and the target predicted financial index is obtained.
It should be noted that different sample financial indexes may correspond to different initial linear regression models, and each target linear regression model is trained to obtain different target linear regression models corresponding to different sample financial indexes.
As an alternative, the inputting the sample macro economic factor into the initial linear regression model to obtain the sample predicted financial index includes: acquiring the type number of the sample macro economic factors, and initializing a corresponding number of target coefficients based on the type number; and weighting the corresponding sample macro economic factors by using each target coefficient, and summing with a target white noise variable to obtain the sample prediction financial index.
Specifically, the initial linear regression model described above may be expressed in the form:
wherein X is t ＝(x 1t ，…，x kt ) Representing the sample macroeconomic factor, t represents time, k is the type number of the sample macroeconomic factor, and the target parameter is θ in the example i ，ε t The white noise variable is expressed as a variable having a mean value of zero and a variance in time series analysisThe white noise variable is a random variable sequence which is constant and uncorrelated with each other, can be used to model and describe the characteristics of random events, with randomness and unpredictability, in time series analysis, the white noise variable is used to verify whether the residuals of the model are random, and can be compared and evaluated as a benchmark for the model.
It should be noted that, in the above example, the number of types of the sample macro economic factors is K, where K is a positive integer, and K target parameters will exist at this time, and the initial linear regression model is trained by adjusting the values of the target parameters, so as to obtain the target linear regression model.
The foregoing is merely an example, and the present application is not limited in any way.
It will be apparent that the embodiments described above are only some, but not all, of the embodiments of the present application.
The present application is specifically described below with reference to specific examples:
in one exemplary embodiment, the present application utilizes the financial indicators involved in the Basel rating model, which is first modeled in association with the macro-economic factor, so that the second step conducts the pressure scenario of the target macro-economic factor to the target breach probability. When the second-step pressure scenario is conducted to the default probability, a configured batch processing mode is innovatively adopted, and when the two-step Basel default probability mapping model is used for pressure testing, two implementation schemes are generally adopted for conducting the pressure scenario to the default probability: firstly, an existing Basel rating model is utilized, which is generally realized by using a rule engine; secondly, realizing the Basel rating model again in a reconstruction mode, so that the Basel rating model can be used for rating clients in batches, wherein the whole flow of the pressure test is shown in figure 3 and can comprise, but is not limited to, defining a test target, determining risk factors, designing pressure scenes, setting assumption conditions, collecting processing test data, determining a test method, carrying out pressure test, analyzing test results, determining potential risks and fragile links, reporting test results, taking improvement measures and the like.
Further, the two-step Bassel default probability mapping model is a specific implementation of the step of performing pressure test in the whole pressure test flow, is a pressure test method combined with the Bassel rating result, and utilizes financial indexes related to the Bassel rating model to establish a linear model with macroscopic economic factors, so that the pressure scene of the macroscopic economic factors is conducted to the default probability. The method comprises the following two steps:
s1, establishing a linear regression model for each financial index Y, such as sales, total assets and the like:
wherein X is t ＝(x 1t ，…，x kt ) Is macro economic variable such as GDP, PPI, etc., t is time, θ is model super parameter, k is number of financial index, ε t Is a white noise variable, and after a model is built, the predicted value of the financial index can be obtained through the predicted value of the macroscopic factor under the pressure scene.
And S2, calculating a model entering index required by the Bassell rating model, for example, total asset turnover rate=sales amount/total asset, and calculating the client grade and the default probability through a rule engine.
The barfire rating model in the present application has two parts, namely a rule engine and rating data, the rule engine can export a target configuration file, the target configuration file is parsed by a target configuration file parser to generate model calculation logic, the rating data can be copied to a distributed database system, the two parts are simultaneously used as inputs for a batch of customer rating pressure tests, and the target configuration file can be imported to the rule engine again if the target parser finds that the calculation logic needs to be modified.
Further, in conducting a batch customer rating stress test, may include, but is not limited to: data preprocessing, modulus index calculation, qualitative and quantitative default probability obtaining and finally target default probability obtaining.
It should be noted that, the credit rating method of the object provided by the application may include, but is not limited to, being applied to an application scenario of a pressure test method for performing customer rating in batches as shown in fig. 3 to 4, deriving a configuration file through a rule engine, and implementing batch calculation of customer rating of each industry by analyzing a target configuration file, so as to play a role of a pressure test tool in prospective risk research.
In addition, the method separates the Bassel rating logic from the pressure testing logic in a mode of setting the target configuration file, improves maintainability of the system, does not need to deploy a ring environment separately for executing the pressure testing task, enables the testing environment and the production environment to be mutually independent through multiplexing the environment of the distributed database, and on the other hand, separates the Bassel rating logic from the pressure testing logic, when the Bassel rating logic is updated, only one target configuration file needs to be exported again, the pressure testing can be adjusted flexibly and synchronously, and maintainability and expandability of the system are improved.
From the description of the above embodiments, it will be clear to a person skilled in the art that the method according to the above embodiments may be implemented by means of software plus the necessary general hardware platform, but of course also by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), including several instructions for causing a front-end device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method of the embodiments of the present application.
According to another aspect of the embodiments of the present application, a device for accessing a system is further provided, where the device is used to implement the foregoing embodiments and preferred implementations, and the description is omitted herein. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
FIG. 6 is a block diagram of a credit rating device for an object according to an embodiment of the application, as shown in FIG. 6, the device comprising:
an acquisition module 602, configured to acquire a target macro-economic factor, where the target macro-economic factor represents a macro-variation trend predicted for the financial data in a future period;
the prediction module 604 is configured to input a target macro economic factor into a pre-trained target linear regression model to obtain a set of predicted financial indexes, where the target linear regression model is a model obtained by training an initial linear regression model with a sample macro economic factor and a sample financial index, the sample macro economic factor and the sample financial index are financial data generated in a historical period, and the predicted financial index represents predicted financial data in a future period;
The rating module 606 is configured to input a set of predicted financial indicators into a target industry rating model determined based on a rule engine, to obtain a target credit rating of the target object, where the rule engine is configured to record industry rating models of different industries, so as to generate the credit ratings of the objects in different industries in batches.
As an alternative, the apparatus is configured to input the set of predicted financial indicators into a target industry rating model determined based on a rules engine to obtain a target credit rating of the target object by: obtaining a target configuration file from the rule engine; analyzing the target configuration file to obtain target calculation logic; processing the set of predicted financial indexes according to the target calculation logic to obtain a set of modeling indexes; determining a target default probability of the target object according to the set of modeling indexes; and determining the target credit rating on a preset scale according to the target default probability.
As an alternative, the apparatus is configured to determine the target breach probability of the target object according to the set of modeling indexes by: determining qualitative and quantitative default probabilities of the target object according to the set of modeling indexes; and determining the target default probability according to the qualitative default probability and the qualitative default probability.
As an alternative, the apparatus is configured to determine the target breach probability based on the qualitative breach probability and the qualitative breach probability by: acquiring behavior data of the target object; and determining the target default probability according to the behavior data, the qualitative default probability and the qualitative default probability.
As an alternative, the apparatus is configured to process the set of predicted financial indicators according to the target calculation logic to obtain a set of modeling indicators by: acquiring a first predicted financial index and a second predicted financial index, wherein the set of predicted financial indexes includes the first predicted financial index and the second predicted financial index; and calculating the first predicted financial index and the second predicted financial index according to the target calculation logic to determine the target modeling index, wherein the group of modeling indexes comprises the target modeling index, and the target calculation logic comprises a calculation mode used by the target industry rating model for the target modeling index.
As an alternative, the above device is further configured to: inputting the target macro economic factors into a pre-trained target linear regression model, and acquiring the sample macro economic factors and the sample financial indexes before obtaining a group of predicted financial indexes, wherein the sample financial indexes are used for marking the sample macro economic factors; inputting the sample macro economic factors into an initial linear regression model to obtain sample predictive financial indexes; training the initial linear regression model according to the sample predicted financial index and the sample financial index to obtain the target linear regression model, wherein the target linear regression model is matched with the index type of the sample financial index, and different index types correspond to different target linear regression models.
As an alternative, the apparatus is configured to input the sample macro economic factor into an initial linear regression model to obtain a sample predicted financial index by: acquiring the type number of the sample macro economic factors, and initializing a corresponding number of target coefficients based on the type number; and weighting the corresponding sample macro economic factors by using each target coefficient, and summing with a target white noise variable to obtain the sample prediction financial index.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
It should be noted that each of the above modules may be implemented by software or hardware, and for the latter, it may be implemented by, but not limited to: the modules are all located in the same processor; alternatively, the above modules may be located in different processors in any combination.
Embodiments of the present application also provide a computer readable storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.
In one exemplary embodiment, the computer readable storage medium may include, but is not limited to: a usb disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing a computer program.
Embodiments of the present application also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.
In an exemplary embodiment, the electronic apparatus may further include a transmission device connected to the processor, and an input/output device connected to the processor.
Specific examples in this embodiment may refer to the examples described in the foregoing embodiments and the exemplary implementation, and this embodiment is not described herein.
It will be appreciated by those skilled in the art that the modules or steps of the application described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may be implemented in program code executable by computing devices, so that they may be stored in a storage device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than that shown or described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps of them may be fabricated into a single integrated circuit module. Thus, the present application is not limited to any specific combination of hardware and software.
The foregoing is merely a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and variations may be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application should be included in the protection scope of the present application.
Claims (10)
1. A method of credit rating of an object, comprising:
obtaining a target macro-economic factor, wherein the target macro-economic factor represents a macro-variation trend predicted for financial data in a future period;
inputting the target macro economic factors into a pre-trained target linear regression model to obtain a group of predicted financial indexes, wherein the target linear regression model is a model obtained by training an initial linear regression model by adopting sample macro economic factors and sample financial indexes, the sample macro economic factors and the sample financial indexes are financial data generated in a historical period, and the predicted financial indexes represent the predicted financial data in the future period;
and inputting the set of predicted financial indexes into a target industry rating model determined based on a rule engine to obtain target credit rating of the target object, wherein the rule engine is used for recording the industry rating models of different industries so as to generate the credit rating of the objects in different industries in batches.
2. The method of claim 1, wherein said inputting the set of predictive financial indicators into a target industry rating model determined based on a rules engine results in a target credit rating for the target object, comprising:
obtaining a target configuration file from the rule engine;
analyzing the target configuration file to obtain target calculation logic;
processing the set of predicted financial indexes according to the target calculation logic to obtain a set of modeling indexes;
determining a target default probability of the target object according to the set of modeling indexes;
and determining the target credit rating on a preset scale according to the target default probability.
3. The method of claim 2, wherein the determining the target breach probability of the target object from the set of modulo indices comprises:
determining qualitative and quantitative default probabilities of the target object according to the set of modeling indexes;
and determining the target default probability according to the qualitative default probability and the qualitative default probability.
4. The method of claim 3, wherein the determining the target breach probability based on the qualitative breach probability and the qualitative breach probability comprises:
Acquiring behavior data of the target object;
and determining the target default probability according to the behavior data, the qualitative default probability and the qualitative default probability.
5. The method of claim 2, wherein processing the set of predicted financial indicators according to the target calculation logic results in a set of modulo indicators, comprising:
obtaining a first predicted financial index and a second predicted financial index, wherein the set of predicted financial indexes includes the first predicted financial index and the second predicted financial index;
and calculating the first predicted financial index and the second predicted financial index according to the target calculation logic to determine the target modeling index, wherein the group of modeling indexes comprises the target modeling index, and the target calculation logic comprises a calculation mode used by the target industry rating model for the target modeling index.
6. The method of claim 1, wherein before inputting the target macro-economic factors into a pre-trained target linear regression model to obtain a set of predicted financial indicators, the method further comprises:
Acquiring the sample macro economic factor and the sample financial index, wherein the sample financial index is used for marking the sample macro economic factor;
inputting the sample macro economic factors into an initial linear regression model to obtain sample predictive financial indexes;
training the initial linear regression model according to the sample predicted financial index and the sample financial index to obtain the target linear regression model, wherein the target linear regression model is matched with the index type of the sample financial index, and different index types correspond to each other
Different said target linear regression models.
7. The method of claim 6, wherein said inputting the sample macroeconomic factors into an initial linear regression model results in sample predictive financial indicators comprising:
acquiring the type number of the sample macro economic factors, and initializing a corresponding number of target coefficients based on the type number;
and weighting the corresponding sample macro economic factors by using each target coefficient, and summing with a target white noise variable to obtain the sample prediction financial index.
8. A credit rating apparatus for an object, comprising:
The acquisition module is used for acquiring a target macro economic factor, wherein the target macro economic factor represents a macro change trend predicted for financial data in a future period;
the prediction module is used for inputting the target macro economic factors into a pre-trained target linear regression model to obtain a group of predicted financial indexes, wherein the target linear regression model is a model obtained by training an initial linear regression model by adopting sample macro economic factors and sample financial indexes, the sample macro economic factors and the sample financial indexes are financial data generated in a historical period, and the predicted financial indexes represent the predicted financial data in the future period;
the rating module is used for inputting the group of predictive financial indexes into a target industry rating model determined based on a rule engine to obtain target credit rating of a target object, wherein the rule engine is used for recording the industry rating models of different industries so as to generate the industry rating models of different industries in batches
Credit rating of an object.
9. A computer readable storage medium, characterized in that a computer program is stored in the computer readable storage medium, wherein the computer program, when being executed by a processor, implements the steps of the method according to any of the claims 1 to 7.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any one of claims 1 to 7 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410009648.9A CN117875770A (en) | 2024-01-02 | 2024-01-02 | Credit rating method and device for object, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410009648.9A CN117875770A (en) | 2024-01-02 | 2024-01-02 | Credit rating method and device for object, storage medium and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117875770A true CN117875770A (en) | 2024-04-12 |
Family
ID=90587768
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410009648.9A Pending CN117875770A (en) | 2024-01-02 | 2024-01-02 | Credit rating method and device for object, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117875770A (en) |
-
2024
- 2024-01-02 CN CN202410009648.9A patent/CN117875770A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7165043B2 (en) | Valuation prediction models in situations with missing inputs | |
| US7120599B2 (en) | Methods and systems for modeling using classification and regression trees | |
| US7096197B2 (en) | Methods and apparatus for simulating competitive bidding yield | |
| US6985881B2 (en) | Methods and apparatus for automated underwriting of segmentable portfolio assets | |
| US7031936B2 (en) | Methods and systems for automated inferred valuation of credit scoring | |
| US7720732B2 (en) | System and method for generating transaction based recommendations | |
| US7003484B2 (en) | Methods and systems for efficiently sampling portfolios for optimal underwriting | |
| US7039608B2 (en) | Rapid valuation of portfolios of assets such as financial instruments | |
| US8209251B2 (en) | Cross correlation tool for automated portfolio descriptive statistics | |
| US7082411B2 (en) | Methods and systems for optimizing return and present value | |
| US8577791B2 (en) | System and computer program for modeling and pricing loan products | |
| US7162445B2 (en) | Methods and systems for quantifying cash flow recovery and risk | |
| CN110009503A (en) | Finance product recommended method, device, computer equipment and storage medium | |
| CN113393328A (en) | Method and device for assessing pre-financing and pre-loan approval and computer storage medium | |
| CN112508689A (en) | Method for realizing decision evaluation based on multiple dimensions | |
| CN117875770A (en) | Credit rating method and device for object, storage medium and electronic device | |
| CN118071513B (en) | Personalized bank asset management method and system based on artificial intelligence driving | |
| CN117217522A (en) | Financial pre-billing risk management and control system based on artificial intelligence and operation method thereof | |
| Jeskanen | Sensitivity of loss given default in multi-stage modelling | |
| CN118505397A (en) | AI analysis method and system for financial information | |
| CN116862675A (en) | Credit risk assessment method, credit risk assessment device and nonvolatile storage medium | |
| CN116228443A (en) | Customer rating method, system, terminal and storage medium | |
| CN116542381A (en) | User credit score prediction method and device, storage medium and electronic equipment | |
| AU2600801A (en) | Valuation prediction models in situations with missing inputs |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |