Risk Rating Method and Device for Precious Metal Leasing Transactions

Abstract

The present application provides a risk rating method and apparatus for precious metal lease transactions, which can be used in the financial field or other fields. The method includes: receiving a risk rating request for a target precious metal lease transaction sent by a business system, and obtaining the business data of the target precious metal lease transaction from a database server according to the risk rating request; determining the default loss rate and risk exposure of the target precious metal lease transaction according to the business data of the target precious metal lease transaction, a preset default loss rate model, and a risk exposure rule; determining the risk level of the target precious metal lease transaction according to the risk exposure, default loss rate, and a preset risk rating standard, and returning it to the business system. The preset risk rating standard includes the corresponding relationship between a risk exposure interval, a default loss rate interval, and a risk level. The present application can improve the accuracy and efficiency of the risk rating of precious metal lease transactions, and thus can improve the security of precious metal lease transactions.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly to a risk rating method and device for precious metal lease transactions. Background Art

[0002] With the development of social economy, the market risks faced by financial enterprises are also increasing, which are likely to cause losses to the enterprises. At present, when financial enterprises conduct risk rating for precious metal lease transactions, usually business personnel manually evaluate the risks of precious metal lease transactions, relying on the personal abilities of business personnel. However, affected by different business personnel, there are problems such as low accuracy and long time consumption in the risk rating work. Summary of the Invention

[0003] Aiming at the problems of low accuracy and efficiency in the risk rating of precious metal lease transactions in the prior art, this application proposes a risk rating method and device for precious metal lease transactions.

[0004] To solve the above technical problems, this application provides the following technical solutions:

[0005] In a first aspect, this application provides a risk rating method for precious metal lease transactions, including:

[0006] Receiving a risk rating request for a target precious metal lease transaction sent by a business system, and obtaining the business data of the target precious metal lease transaction from a database server according to the risk rating request;

[0007] Determining the default loss rate and risk exposure of the target precious metal lease transaction according to the business data of the target precious metal lease transaction, a preset default loss rate model, and a risk exposure rule;

[0008] Determining the risk level of the target precious metal lease transaction according to the risk exposure, the default loss rate, and a preset risk rating standard, and returning it to the business system. The preset risk rating standard includes: the corresponding relationship between a risk exposure interval, a default loss rate interval, and a risk level.

[0009] Further, after determining the default loss rate and risk exposure of the target precious metal lease transaction according to the business data of the target precious metal lease transaction, a preset default loss rate model, and a risk exposure rule, it further includes:

[0010] Determining a predicted default result of the target precious metal lease transaction according to the business data and a preset default prediction model. The preset default prediction model is pre-trained according to the business data, actual default results, and a first classification model of multiple historical precious metal lease transactions;

[0011] Based on the risk exposure, loss given default, predicted default result, and a preset risk rating model, determine the risk level of the target precious metal lease transaction and return it to the business system. The preset risk rating model is pre-trained based on the risk exposure, loss given default, actual default result, risk level, and a second classification model of multiple historical precious metal lease transactions.

[0012] Further, before determining the predicted default result of the target precious metal lease transaction according to the business data and the preset default prediction model, it further includes:

[0013] Obtain the business data and actual default results of multiple historical precious metal lease transactions;

[0014] Train the first classification model according to the business data and actual default results of each historical precious metal lease transaction to obtain the default prediction model.

[0015] Further, before determining the risk level of the target precious metal lease transaction according to the risk exposure, loss given default, predicted default result, and the preset risk rating model and returning it to the business system, it further includes:

[0016] Obtain the risk exposure, loss given default, actual default result, and risk level of multiple historical precious metal lease transactions;

[0017] Train the second classification model according to the risk exposure, loss given default, actual default result, and risk level of each historical precious metal lease transaction to obtain the risk rating model.

[0018] Further, the business data includes: the applied amount in the precious metal lease contract;

[0019] Correspondingly, determining the loss given default and risk exposure of the target precious metal lease transaction according to the business data of the target precious metal lease transaction, the preset loss given default model, and the risk exposure rule includes:

[0020] Determine the loss given default of the target precious metal lease transaction according to the business data and the preset loss given default model;

[0021] Determine the risk exposure by multiplying the applied amount in the precious metal lease contract and the preset credit conversion coefficient.

[0022] Further, after determining the risk level of the target precious metal lease transaction and returning it to the business system, it further includes:

[0023] Send the risk rating result of the target precious metal lease transaction to a terminal device and output it for display.

[0024] Further, receiving a risk rating request for a target precious metal lease transaction sent by a business system, and obtaining business data of the target precious metal lease transaction from a database server according to the risk rating request, including:

[0025] Receiving a risk rating request for a target precious metal lease transaction sent by a business system;

[0026] Sending the risk rating request to the database server, and receiving the packaged business data corresponding to the risk rating request sent by the database server;

[0027] Decompressing the business data.

[0028] In a second aspect, the present application provides a risk rating device for precious metal lease transactions, including:

[0029] An obtaining module, configured to receive a risk rating request for a target precious metal lease transaction sent by a business system, and obtain business data of the target precious metal lease transaction from a database server according to the risk rating request;

[0030] A determining module, configured to determine a default loss rate and a risk exposure of the target precious metal lease transaction according to the business data of the target precious metal lease transaction, a preset default loss rate model, and a risk exposure rule;

[0031] A rating module, configured to determine a risk level of the target precious metal lease transaction according to the risk exposure, the default loss rate, and a preset risk rating standard, and return it to the business system, where the preset risk rating standard includes: the corresponding relationship between a risk exposure interval, a default loss rate interval, and a risk level.

[0032] Further, the risk rating device for precious metal lease transactions further includes:

[0033] A predicted default result determining module, configured to determine a predicted default result of the target precious metal lease transaction according to the business data and a preset default prediction model, where the preset default prediction model is pre-trained according to business data, actual default results, and a first classification model of multiple historical precious metal lease transactions;

[0034] An output module, configured to determine a risk level of the target precious metal lease transaction according to the risk exposure, the default loss rate, the predicted default result, and a preset risk rating model, and return it to the business system, where the preset risk rating model is pre-trained according to the risk exposure, the default loss rate, the actual default results, the risk level, and a second classification model of multiple historical precious metal lease transactions.

[0035] Furthermore, the risk rating device for precious metal lease transactions further includes:

[0036] A first historical data acquisition module, configured to acquire the business data and actual default results of multiple historical precious metal lease transactions;

[0037] A first training module, configured to train a first classification model according to the business data and actual default results of each historical precious metal lease transaction to obtain the default prediction model.

[0038] Furthermore, the risk rating device for precious metal lease transactions further includes:

[0039] A second historical data acquisition module, configured to acquire the risk exposure, default loss rate, actual default results, and risk levels of multiple historical precious metal lease transactions;

[0040] A second training module, configured to train a second classification model according to the risk exposure, default loss rate, actual default results, and risk levels of each historical precious metal lease transaction to obtain the risk rating model.

[0041] Furthermore, the business data includes: the applied amount in the precious metal lease contract;

[0042] Correspondingly, the determination module includes:

[0043] A first determination unit, configured to determine the default loss rate of the target precious metal lease transaction according to the business data and a preset default loss rate model;

[0044] A second determination unit, configured to determine the product of the applied amount in the precious metal lease contract and a preset credit conversion coefficient as the risk exposure.

[0045] Furthermore, the risk rating device for precious metal lease transactions further includes:

[0046] A display module, configured to send the risk rating result of the target precious metal lease transaction to a terminal device and output it for display.

[0047] Furthermore, the acquisition module includes:

[0048] A receiving unit, configured to receive a risk rating request for a target precious metal lease transaction sent by a business system;

[0049] A packaging unit, configured to send the risk rating request to a database server and receive the packaged business data corresponding to the risk rating request sent by the database server;

[0050] A decompression unit for decompressing the service data.

[0051] In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the risk rating method for the precious metal lease transaction as described above is implemented.

[0052] In a fourth aspect, the present application provides a computer-readable storage medium, on which computer instructions are stored. When the instructions are executed, the risk rating method for the precious metal lease transaction as described above is implemented.

[0053] As can be seen from the above technical solutions, the present application provides a risk rating method and device for precious metal lease transactions. Among them, the method includes: receiving a risk rating request for a target precious metal lease transaction sent by a service system, and obtaining the service data of the target precious metal lease transaction from a database server according to the risk rating request; determining the default loss rate and risk exposure of the target precious metal lease transaction according to the service data of the target precious metal lease transaction, a preset default loss rate model, and a risk exposure rule; determining the risk level of the target precious metal lease transaction according to the risk exposure, the default loss rate, and a preset risk rating standard, and returning it to the service system. The preset risk rating standard includes: the corresponding relationship between a risk exposure interval, a default loss rate interval, and a risk level, which can improve the accuracy and efficiency of the risk rating of precious metal lease transactions, and further improve the security of precious metal lease services (i.e., precious metal lease transactions); specifically, it can improve the automation degree of the risk rating of metal lease services, reduce labor costs, safeguard the interests of financial enterprises, and provide support for credit decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0055] Figure 1 It is a flowchart of the risk rating method for precious metal lease transactions in an embodiment of the present application;

[0056] Figure 2 It is a flowchart of the risk rating method for precious metal lease transactions in another embodiment of the present application;

[0057] Figure 3 It is a flowchart of the risk rating method for precious metal lease transactions in yet another embodiment of the present application;

[0058] Figure 4 It is a schematic structural diagram of a risk rating device for precious metal lease transactions in an embodiment of the present application;

[0059] Figure 5 It is a schematic structural diagram of a risk rating device for precious metal lease transactions in an embodiment of the present application;

[0060] Figure 6 It is a schematic block diagram of the system composition of an electronic device according to an embodiment of the present application. Specific implementation manners

[0061] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0062] In view of the problems existing in the manual assessment of precious metal lease risks in the prior art, the present application provides a risk rating method and device for precious metal lease transactions. By mining and analyzing the cleaned historical default data and loss data, key risk factors affecting the default loss rate of debt items such as financing business varieties, types of collateral, remaining loan term, borrower regions, and borrower industries are studied, and a preliminary debt item rating system that meets the requirements of the New Basel Capital Accord and is suitable for risk management practices is created, scientifically estimating the transaction risks of debt items, being able to determine the risk levels of precious metal lease transactions through the lease default loss rate (LGD) of metals and exposure, etc., being able to reduce labor costs, and providing support for credit decision-making.

[0063] In order to improve the accuracy and efficiency of precious metal lease transaction risk rating, an embodiment of the present application provides a risk rating device for precious metal lease transactions. The device can be a server or a client device. The client device can include smart phones, tablet electronic devices, network set-top boxes, portable computers, desktop computers, personal digital assistants (PDAs), vehicle-mounted devices, and smart wearable devices, etc. Among them, the smart wearable devices can include smart glasses, smart watches, and smart bracelets, etc.

[0064] In practical applications, the part for performing the risk rating of precious metal lease transactions can be executed on the server side as described above, or all operations can be completed in the client device. Specifically, it can be selected according to the processing capabilities of the client device and the limitations of the user usage scenarios, etc. The present application does not limit this. If all operations are completed in the client device, the client device may further include a processor.

[0065] The above-mentioned client device may have a communication module (i.e., a communication unit), which can communicate with a remote server to achieve data transmission with the server. The server may include a server on the task scheduling center side, and in other implementation scenarios, it may also include a server of an intermediate platform, such as a server of a third-party server platform having a communication link with the task scheduling center server. The server may include a single computer device, or a server cluster composed of multiple servers, or a server structure of a distributed device.

[0066] Any suitable network protocol can be used for communication between the server and the client device, including network protocols not yet developed on the filing date of this application. The network protocol may, for example, include TCP / IP protocol, UDP / IP protocol, HTTP protocol, HTTPS protocol, etc. Of course, the network protocol may also include, for example, the RPC protocol (Remote Procedure Call Protocol) and the REST protocol (Representational State Transfer) used on top of the above-mentioned protocols.

[0067] It should be noted that the risk rating method and device for precious metal lease transactions disclosed in this application can be used in the financial technology field, and can also be used in any field other than the financial technology field. The application field of the risk rating method and device for precious metal lease transactions disclosed in this application is not limited. In the technical solutions of this application, the acquisition, storage, use, processing, etc. of data all comply with the relevant provisions of national laws and regulations.

[0068] Specifically, it will be described through the following various embodiments.

[0069] In order to improve the accuracy and efficiency of the risk rating of precious metal lease transactions, this embodiment provides a risk rating method for precious metal lease transactions whose execution entity is a risk rating device for precious metal lease transactions. The risk rating device for precious metal lease transactions includes, but is not limited to, a server, as Figure 1 shown, and the method specifically includes the following content:

[0070] Step 100: Receive a risk rating request for a target precious metal lease transaction sent by a business system, and obtain the business data of the target precious metal lease transaction from a database server according to the risk rating request.

[0071] Specifically, the business system includes, but is not limited to, servers; business data of the target precious metal lease transaction can be pre-stored in the database server; the risk rating request may include a unique identifier of the target precious metal lease transaction, and the business data of the target precious metal lease transaction can be obtained from the database server according to this unique identifier. The unique identifier is used to distinguish different precious metal lease transactions and can be a string composed of numbers and letters; the business data of the target precious metal lease transaction may include: precious metal lease contract information, precious metal lease note information, precious metal lease guarantee information, and precious metal lease debt item information of the target precious metal lease transaction; among them, the precious metal lease contract information may include: application amount, currency, repayment date, loan release date, interest rate information, guarantee method, and other information in the lease contract; the precious metal lease note information may include: balance, currency, release date, maturity date, 12-level classification, execution interest rate, and other information in the precious metal lease note; the precious metal lease guarantee information may include: guarantee amount, currency, and other information in the guarantee contract and mortgage contract of the target precious metal lease transaction; the precious metal lease debt item information may include: handling fee, credit conversion factor ccf, qualitative scoring, and other information.

[0072] Step 200: Determine the default loss rate and risk exposure of the target precious metal lease transaction according to the business data of the target precious metal lease transaction, the preset default loss rate model, and the risk exposure rule.

[0073] Specifically, the risk exposure rule may be: 1) At the time of contract application (i.e., during the risk rating before executing the target precious metal lease transaction): Risk exposure = Application amount in the precious metal lease contract × Credit conversion factor; or, 2) At the time of contract release (i.e., during the regular risk rating after executing the target precious metal lease transaction): Risk exposure = Balance in the precious metal lease note; The preset default loss rate model may be as follows:

[0074] LGD = BETAINV(X, Alpha, Beta, 0, 1)

[0075] X = NORMDIST(Constant term + Coefficient 01 * W01 + …… + Coefficient 10 * W10)

[0076] Among them, LGD represents the loss given default; Alpha and Beta are coefficients 01 to 10, which are the weight coefficients of various LGD impact factors; W01 to W10 are the WOE values of various LGD impact factors; the LGD impact factors can be obtained through the corresponding relationship conversion based on the above precious metal lease transaction data. The LGD impact factors include: customer affiliation, economic nature, industry subclass, loan form, guarantee form, business variety, customer risk exposure, tangible assets / total liabilities, VTL, and mitigation type; the corresponding relationship between business data and LGD impact factors can be preset according to actual needs, and this application does not limit it; BETAINV(probability, alpha, beta, 0, 1) represents the inverse function value of the specified beta distribution cumulative distribution function; NORMSDIST(Z) represents the value of the standard normal cumulative distribution function.

[0077] Step 300: Determine the risk level of the target precious metal lease transaction according to the risk exposure, the loss given default, and the preset risk rating criteria, and return it to the business system. The preset risk rating criteria include: the corresponding relationship between the risk exposure interval, the loss given default interval, and the risk level.

[0078] Specifically, the risk rating can be performed before the target precious metal lease transaction to facilitate timely prediction of transaction risks; it can also be executed regularly after the target precious metal lease transaction to facilitate real-time monitoring of transaction risks; the preset risk rating criteria can be set according to the actual situation, and this application does not limit it; the risk level of the target precious metal lease transaction can be determined according to the risk exposure interval to which the risk exposure belongs and the loss given default interval to which the loss given default belongs, and returned to the business system; for example, if the risk exposure belongs to risk exposure interval 1 and the loss given default belongs to loss given default interval 1, then the risk level corresponding to risk exposure interval 1 and loss given default interval 1 is determined as the risk level of the target precious metal lease transaction.

[0079] To further improve the accuracy and intelligence of the risk rating, refer to Figure 2 , in an embodiment of this application, after step 200, it further includes:

[0080] Step 400: Determine the predicted default result of the target precious metal lease transaction according to the business data and the preset default prediction model. The preset default prediction model is pre-trained according to the business data, actual default results, and the first classification model of multiple historical precious metal lease transactions.

[0081] Specifically, the business data can be input into a preset default prediction model, and the output result of the preset default prediction model can be determined as the predicted default result of the target precious metal lease transaction. The predicted default result can be default or compliance.

[0082] Step 500: According to the risk exposure, loss given default, predicted default result, and a preset risk rating model, determine the risk level of the target precious metal lease transaction and return it to the business system. The preset risk rating model is pre-trained based on the risk exposure, loss given default, actual default result, risk level, and a second classification model of multiple historical precious metal lease transactions.

[0083] Specifically, the risk exposure, loss given default, and predicted default result can be input into the preset risk rating model, and the output result of the preset risk rating model can be determined as the risk level of the target precious metal lease transaction. By determining the risk level of the target precious metal lease transaction and returning it to the business system, on the basis of the predicted default result, the loss caused by the risk to the financial enterprise can be further evaluated, as well as the potential risk of the precious metal lease transaction, improving the accuracy of the precious metal lease transaction rating.

[0084] In order to improve the reliability of the default prediction model, and then apply a reliable default prediction model to obtain an accurate predicted default result, in an embodiment of the present application, before step 400, it further includes:

[0085] Step 041: Obtain the business data and actual default results of multiple historical precious metal lease transactions.

[0086] Specifically, the actual default result can be the true default result of the historical precious metal lease transaction, and the actual default result is default or compliance.

[0087] Step 042: Train the first classification model according to the business data and actual default results of each historical precious metal lease transaction to obtain the default prediction model.

[0088] Specifically, the first classification model can be one of a nearest neighbor node model, a decision tree model, a Bayesian classification model, a support vector machine model, etc.

[0089] In order to improve the reliability of the risk rating model, and then apply a reliable risk rating model to obtain an accurate risk rating result, in an embodiment of the present application, before step 500, it further includes:

[0090] Step 051: Obtain the risk exposure, loss given default, actual default result, and risk level of multiple historical precious metal lease transactions.

[0091] It can be understood that the default loss rate of historical precious metal lease transactions can be determined by applying the business data of historical precious metal lease transactions and a preset default loss rate model; the risk exposure of historical precious metal lease transactions can be determined by applying the business data and risk exposure of historical precious metal lease transactions; the risk levels of individual historical precious metal lease transactions can be set according to actual circumstances, and this application does not limit this.

[0092] Step 052: Train the second classification model based on the risk exposure, default loss rate, actual default result, and risk level of each historical precious metal lease transaction to obtain the risk rating model.

[0093] Specifically, the second classification model can be one of a nearest neighbor node model, a decision tree model, a Bayesian classification model, a support vector machine model, etc.; the first classification model and the second classification model can be the same or different.

[0094] To improve the accuracy of obtaining the risk exposure, refer to Figure 3 In an embodiment of this application, the business data includes: the applied amount in the precious metal lease contract; correspondingly, step 200 includes:

[0095] Step 201: Determine the default loss rate of the target precious metal lease transaction according to the business data and a preset default loss rate model;

[0096] Step 202: Multiply the applied amount in the precious metal lease contract by a preset credit conversion coefficient to determine the risk exposure.

[0097] Specifically, the risk exposure rule can be: risk exposure = applied amount in the precious metal lease contract × credit conversion coefficient; the preset credit conversion coefficient can be set according to actual circumstances, and this application does not limit this. Preferably, the credit conversion coefficient is 1. The business data may also include: the balance in the precious metal lease note.

[0098] To improve the visualization of the risk rating result while improving the accuracy and efficiency of the risk rating of precious metal lease transactions, in an embodiment of this application, after step 300 or step 500, it further includes:

[0099] Step 600: Send the risk rating result of the target precious metal lease transaction to a terminal device and output it for display.

[0100] Specifically, the terminal device can be a desktop computer or a laptop computer of business personnel, etc.

[0101] In order to improve the reliability of business data storage and the security and efficiency of data interaction on the basis of improving the accuracy and efficiency of the risk rating of precious metal lease transactions, in an embodiment of the present application, step 100 includes:

[0102] Step 101: Receive a risk rating request for a target precious metal lease transaction sent by a business system.

[0103] Step 102: Send the risk rating request to the database server and receive the packaged business data corresponding to the risk rating request sent by the database server.

[0104] Step 103: Decompress the business data.

[0105] To further illustrate the present solution, the present application provides an application example of a risk rating method for precious metal lease transactions, which is specifically described as follows:

[0106] Step 1: Aggregate and calculate the precious metal lease transaction data at the calculation time point; Step 1 includes:

[0107] Step 11: Extract the precious metal lease contract information. Obtain information such as the applied amount, currency, repayment date, loan release date, interest rate information, and guarantee method on the contract, and summarize it in the debt rating contract information table to provide data support for subsequent calculation of business risks.

[0108] Step 12: Extract the precious metal lease note information. Obtain information such as the balance, currency, release date, maturity date, 12-level classification, and execution interest rate on the note, and summarize it in the debt rating note information table. Calculate the precious metal lease risk exposure according to the balance and the unissued amount * credit conversion coefficient. The unissued amount is the contract applied amount minus the issued amount, and the credit conversion coefficient is provided by the business department.

[0109] Step 13: Extract the precious metal lease guarantee information. Through the guarantee contract and pledge contract in the precious metal business, obtain information such as the guarantee amount and currency on the contract; obtain information such as the amount and currency of the margin, and summarize it in the debt rating guarantee contract information table, the debt rating pledge contract information table, and the debt rating margin information table to provide data support for subsequent statistics of the guarantee coverage of the risk exposure.

[0110] Step 14: Extract the precious metal lease debt item information. Obtain information such as the handling fee, credit conversion coefficient ccf (currently 1), and qualitative scoring card set for the precious metal lease transaction, and summarize it in the latest basic information table of the stock debt items. In an example, the qualitative scoring card is shown in Table 1. Calculate the qualitative score according to different indicators, and convert the total score to obtain the risk adjustment coefficient according to the comparison table.

[0111] Table 1

[0112]

[0113]

[0114]

[0115] Step 2: Apply a precious metal lease transaction risk rating model that supports flexible configuration. Based on the data model established for previous precious metal lease transactions, obtain the loss given default (LGD) of precious metal leases through the loss given default model.

[0116] Furthermore, the loss given default (LGD) grade can be increased or decreased according to the risk adjustment coefficient, and the above intermediate calculation information and LGD results are summarized in the debt item rating snapshot table.

[0117] From a software perspective, in order to improve the accuracy and efficiency of precious metal lease transaction risk rating, this application provides an embodiment of a risk rating device for precious metal lease transactions that implements all or part of the content of the risk rating method for the precious metal lease transactions. See Figure 4 The risk rating device for precious metal lease transactions specifically includes the following:

[0118] An acquisition module 10, configured to receive a risk rating request for a target precious metal lease transaction sent by a business system, and obtain the business data of the target precious metal lease transaction from a database server according to the risk rating request;

[0119] A determination module 20, configured to determine the loss given default and risk exposure of the target precious metal lease transaction according to the business data of the target precious metal lease transaction, a preset loss given default model, and a risk exposure rule;

[0120] A rating module 30, configured to determine the risk level of the target precious metal lease transaction according to the risk exposure, the loss given default, and a preset risk rating standard, and return it to the business system. The preset risk rating standard includes the corresponding relationship between a risk exposure interval, a loss given default interval, and a risk level.

[0121] See Figure 5 In an embodiment of this application, the risk rating device for precious metal lease transactions further includes:

[0122] A default prediction module 40, configured to determine the predicted default result of the target precious metal lease transaction according to the business data and a preset default prediction model. The preset default prediction model is pre-trained according to the business data, actual default results, and a first classification model of multiple historical precious metal lease transactions;

[0123] A risk rating module 50, configured to determine the risk level of the target precious metal lease transaction according to the risk exposure, loss given default, predicted default result, and a preset risk rating model, and return it to the business system. The preset risk rating model is pre-trained according to the risk exposure, loss given default, actual default result, risk level of multiple historical precious metal lease transactions, and a second classification model.

[0124] In an embodiment of the present application, the risk rating device for precious metal lease transactions further includes:

[0125] A first historical data acquisition module, configured to acquire the business data and actual default result of multiple historical precious metal lease transactions;

[0126] A first training module, configured to train a first classification model according to the business data and actual default result of each historical precious metal lease transaction to obtain the default prediction model.

[0127] In an embodiment of the present application, the risk rating device for precious metal lease transactions further includes:

[0128] A second historical data acquisition module, configured to acquire the risk exposure, loss given default, actual default result, and risk level of multiple historical precious metal lease transactions;

[0129] A second training module, configured to train a second classification model according to the risk exposure, loss given default, actual default result, and risk level of each historical precious metal lease transaction to obtain the risk rating model.

[0130] In an embodiment of the present application, the business data includes: the applied amount in the precious metal lease contract;

[0131] Correspondingly, the determination module includes:

[0132] A loss given default determination unit, configured to determine the loss given default of the target precious metal lease transaction according to the business data and a preset loss given default model;

[0133] A risk exposure determination unit, configured to determine the product of the applied amount in the precious metal lease contract and a preset credit conversion coefficient as the risk exposure.

[0134] In an embodiment of the present application, the risk rating device for precious metal lease transactions further includes:

[0135] A display module, configured to send the risk rating result of the target precious metal lease transaction to a terminal device and output it for display.

[0136] In an embodiment of the present application, the acquisition module includes:

[0137] A receiving unit, configured to receive a risk rating request for a target precious metal leasing transaction sent by a service system;

[0138] A sending unit, configured to send the risk rating request to a database server and receive the packaged service data corresponding to the risk rating request sent by the database server;

[0139] A decompression unit, configured to decompress the service data.

[0140] The embodiment of the risk rating device for precious metal leasing transactions provided in this specification can specifically be used to execute the processing flow of the embodiment of the above-mentioned risk rating method for precious metal leasing transactions. Its functions will not be elaborated here, and reference can be made to the detailed description of the embodiment of the above-mentioned risk rating method for precious metal leasing transactions.

[0141] As can be seen from the above description, the risk rating method and device for precious metal leasing transactions provided in this application can improve the accuracy and efficiency of the risk rating of precious metal leasing transactions, and thus can improve the security of precious metal leasing transactions; specifically, it can improve the automation level of the risk rating of metal leasing business, reduce labor costs, safeguard the interests of financial enterprises, and provide support for credit decisions.

[0142] Figure 6 FIG. is a schematic physical structure diagram of an electronic device provided by an embodiment of the present invention. As Figure 6 shown, the electronic device may include: a processor 401, a communication interface 402, a memory 403, and a communication bus 404. Among them, the processor 401, the communication interface 402, and the memory 403 communicate with each other through the communication bus 404. The processor 401 can call the logical instructions in the memory 403 to execute the following method: receive a risk rating request for a target precious metal leasing transaction sent by a service system, and obtain the service data of the target precious metal leasing transaction from a database server according to the risk rating request; determine the default loss rate and risk exposure of the target precious metal leasing transaction according to the service data of the target precious metal leasing transaction, a preset default loss rate model, and a risk exposure rule; determine the risk level of the target precious metal leasing transaction according to the risk exposure, the default loss rate, and a preset risk rating standard, and return it to the service system. The preset risk rating standard includes: the corresponding relationship between a risk exposure interval, a default loss rate interval, and a risk level.

[0143] In addition, when the logical instructions in the above-mentioned memory 403 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs.

[0144] This embodiment discloses a computer program product. The computer program product includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the methods provided in the above-mentioned method embodiments. For example, it includes: receiving a risk rating request for a target precious metal leasing transaction sent by a business system, and obtaining the business data of the target precious metal leasing transaction from a database server according to the risk rating request; determining the default loss rate and risk exposure of the target precious metal leasing transaction according to the business data of the target precious metal leasing transaction, a preset default loss rate model, and a risk exposure rule; determining the risk level of the target precious metal leasing transaction according to the risk exposure, the default loss rate, and a preset risk rating standard, and returning it to the business system. The preset risk rating standard includes: the corresponding relationship between a risk exposure interval, a default loss rate interval, and a risk level.

[0145] This embodiment provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. The computer program causes the computer to execute the methods provided in the above-mentioned method embodiments. For example, it includes: receiving a risk rating request for a target precious metal leasing transaction sent by a business system, and obtaining the business data of the target precious metal leasing transaction from a database server according to the risk rating request; determining the default loss rate and risk exposure of the target precious metal leasing transaction according to the business data of the target precious metal leasing transaction, a preset default loss rate model, and a risk exposure rule; determining the risk level of the target precious metal leasing transaction according to the risk exposure, the default loss rate, and a preset risk rating standard, and returning it to the business system. The preset risk rating standard includes: the corresponding relationship between a risk exposure interval, a default loss rate interval, and a risk level.

[0146] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0147] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0148] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0149] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0150] In the description of this specification, the descriptions referring to terms such as "one embodiment", "a specific embodiment", "some embodiments", "for example", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in a suitable manner in any one or more embodiments or examples.

[0151] The above-described specific embodiments have further elaborated on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above is only the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. A risk rating method for precious metal lease transactions, characterized in that Including: Receiving a risk rating request for a target precious metal lease transaction sent by a business system, and obtaining the business data of the target precious metal lease transaction from a database server according to the risk rating request; Determining the loss given default (LGD) and the exposure at default of the target precious metal lease transaction according to the business data of the target precious metal lease transaction, a preset loss given default model, and an exposure at default rule, wherein the preset loss given default model is as follows: LGD = BETAINV(X, Alpha, Beta, 0, 1); X = NORMDIST(constant term + coefficient 01 × W01 + …… + coefficient 10 × W10); Wherein, LGD represents the loss given default; Alpha and Beta are the weight coefficients of each LGD influencing factor from coefficient 01 to coefficient 10; W01 to W10 are the WOE values of each LGD influencing factor; BETAINV(X, Alpha, Beta, 0, 1) represents returning the inverse function value of the specified beta distribution cumulative distribution function; NORMSDIST(constant term + coefficient 01 × W01 + …… + coefficient 10 × W10) represents returning the standard normal cumulative distribution function value; The exposure at default rule includes at least one of the following: At the time of contract application: the exposure at default is equal to the application amount in the precious metal lease contract multiplied by the credit conversion coefficient; or, at the time of contract disbursement: the exposure at default is equal to the balance in the precious metal lease note; Determining the risk level of the target precious metal lease transaction according to the exposure at default, the loss given default, and a preset risk rating standard, and returning it to the business system, wherein the preset risk rating standard includes the corresponding relationship between the exposure at default interval, the loss given default interval, and the risk level.

2. The risk rating method for precious metal lease transactions according to claim 1, characterized in that, After determining the loss given default and the exposure at default of the target precious metal lease transaction according to the business data of the target precious metal lease transaction, a preset loss given default model, and an exposure at default rule, it further includes: Determining the predicted default result of the target precious metal lease transaction according to the business data and a preset default prediction model, wherein the preset default prediction model is pre-trained according to the business data, actual default results, and a first classification model of multiple historical precious metal lease transactions; Determining the risk level of the target precious metal lease transaction according to the exposure at default, the loss given default, the predicted default result, and a preset risk rating model, and returning it to the business system, wherein the preset risk rating model is pre-trained according to the exposure at default, the loss given default, the actual default results, the risk levels, and a second classification model of multiple historical precious metal lease transactions.

3. The risk rating method for precious metal lease transactions according to claim 2, wherein Before determining the predicted default result of the target precious metal lease transaction according to the business data and a preset default prediction model, it further includes: Obtaining the business data and actual default results of multiple historical precious metal lease transactions; Training the first classification model according to the business data and actual default results of each historical precious metal lease transaction to obtain the default prediction model.

4. The risk rating method for precious metal lease transactions according to claim 2, wherein Before determining the risk level of the target precious metal lease transaction according to the risk exposure, loss given default, predicted default result and a preset risk rating model and returning it to the business system, the following steps are further included: Obtain the risk exposure, loss given default, actual default result and risk level of multiple historical precious metal lease transactions; Train a second classification model according to the risk exposure, loss given default, actual default result and risk level of each historical precious metal lease transaction to obtain the risk rating model.

5. The risk rating method for precious metal leasing transactions according to claim 1, wherein The business data includes: the applied amount in the precious metal lease contract; Correspondingly, determining the loss given default and risk exposure of the target precious metal lease transaction according to the business data of the target precious metal lease transaction, a preset loss given default model and a risk exposure rule includes: Determine the loss given default of the target precious metal lease transaction according to the business data and the preset loss given default model; Determine the product of the applied amount in the precious metal lease contract and a preset credit conversion coefficient as the risk exposure.

6. The risk rating method for precious metal leasing transactions according to claim 1 or 2, characterized in that, After determining the risk level of the target precious metal lease transaction and returning it to the business system, the following steps are further included: Send the risk rating result of the target precious metal lease transaction to a terminal device and output it for display.

7. The risk rating method for precious metal lease transactions according to claim 1, wherein Receiving a risk rating request for a target precious metal lease transaction sent by a business system and obtaining the business data of the target precious metal lease transaction from a database server according to the risk rating request includes: Receive a risk rating request for a target precious metal lease transaction sent by a business system; Send the risk rating request to the database server and receive the packaged business data corresponding to the risk rating request sent by the database server; Decompress the business data.

8. A risk rating device for precious metal lease transactions, characterized in that, It includes: An acquisition module, configured to receive a risk rating request for a target precious metal lease transaction sent by a business system and obtain the business data of the target precious metal lease transaction from a database server according to the risk rating request; A determination module, configured to determine the loss given default and risk exposure of the target precious metal lease transaction according to the business data of the target precious metal lease transaction, a preset loss given default model and a risk exposure rule, where the preset loss given default model is as follows: LGD = BETAINV(X, Alpha, Beta, 0, 1); X = NORMDIST(constant term + coefficient01 × W01 + …… + coefficient10 × W10); Where, LGD represents the loss given default; Alpha and Beta are the weight coefficients of each LGD influencing factor from coefficient01 to coefficient10; W01 to W10 are the WOE values of each LGD influencing factor; BETAINV(X, Alpha, Beta, 0, 1) represents returning the inverse function value of the specified beta distribution cumulative distribution function; NORMSDIST(constant term + coefficient01 × W01 + …… + coefficient10 × W10) represents returning the standard normal cumulative distribution function value; The risk exposure rule at least includes one of the following: At the time of contract application: the risk exposure is equal to the application amount in the precious metal lease contract multiplied by the credit conversion factor; or, at the time of contract disbursement: the risk exposure is equal to the balance in the precious metal lease note. A rating module, configured to determine the risk level of the target precious metal lease transaction according to the risk exposure, the loss given default, and a preset risk rating standard, and return it to the business system, where the preset risk rating standard includes the corresponding relationship between the risk exposure interval, the loss given default interval, and the risk level.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the risk rating method for the precious metal lease transaction according to any one of claims 1 to 7.

10. A computer-readable storage medium having computer instructions stored thereon, characterized in that, When the instruction is executed, it implements the risk rating method for the precious metal lease transaction according to any one of claims 1 to 7.

Images