HK40022016B - Risk control management method, device and electronic apparatus of asset securitization, and storage medium - Google Patents

Description

Wind control management method and device for securitization of assets, electronic equipment and storage medium

Technical Field

The invention relates to the internet financial technology, in particular to a wind control management method and device for securitization of assets, electronic equipment and a storage medium.

Background

Asset-Backed Security (ABS) refers to a process of issuing Asset support certificates (e.g., various financial products) based on credit accreditation through structured design with cash flow generated in the future of consuming financial assets as reimbursement support. And the consumption financial assets are the assets with risks, such as the small credit type assets, and the situation that people are overdue possibly exists.

In the related technology, before ABS distribution of the consumption financial assets to investors, certain wind control management measures are taken to deal with the risks of the assets, and the income safety of the investors is guaranteed. The internet finance is the combination of the traditional finance and the internet technology, and a typical difference with the traditional finance technology is that people in the traditional credit society are replaced by strangers in the network, the ABS risk control technology provided by the related technology is difficult to adapt to the new form of the internet finance, and frequent risk problems cause unsmooth fund flow of the ABS business system, so that the operation efficiency of the business system is influenced.

Disclosure of Invention

The embodiment of the invention provides a method and a device for wind control management of asset securitization, electronic equipment and a storage medium, which can effectively control the risk of an asset securitization business system and further improve the operation efficiency of the business system.

The technical scheme of the embodiment of the invention is realized as follows:

the embodiment of the invention provides a wind control management method for securitization of assets, which comprises the following steps:

acquiring credit investigation data of a corresponding lender from a credit investigation system aiming at each asset in an asset package provided by an financing party;

carrying out risk prediction on credit investigation data of the lender of each asset through an artificial intelligence model to obtain a risk score of each asset;

according to the risk score of each asset, the assets in the asset package are divided into corresponding risk levels;

and filtering the bad assets in each risk level in the asset package, and issuing corresponding security products to a trading exchange system according to the assets left after the asset package is filtered.

The embodiment of the invention provides a wind control management device for securitization of assets, which comprises:

the acquisition module is used for acquiring credit investigation data of a corresponding lender from the credit investigation system aiming at each asset in the asset package provided by the financing party;

the prediction module is used for carrying out risk prediction on credit investigation data of the lender of each asset through the artificial intelligence model to obtain a risk score of each asset;

the grading module is used for grading the assets in the asset pack to corresponding risk grades according to the risk scores of each asset;

the filtering module is used for filtering the bad assets in each risk level in the asset pack;

and the issuing module is used for issuing the corresponding security products to the exchange system aiming at the assets left after the asset package is filtered.

In the above scheme, the obtaining module is further configured to send a transaction carrying the identification information of the lender to a blockchain network, where a consensus node of the blockchain network includes a status database corresponding to at least one of a bank credit investigation system and a third party credit investigation system, so that the consensus node in the blockchain network queries the status database according to the identification information in the transaction, and responds to the transaction by using the queried credit investigation data as a transaction response.

In the above scheme, the prediction module is further configured to initiate a transaction to a blockchain network, where the transaction carries an identifier of an intelligent contract corresponding to an artificial intelligence model and parameters representing the resource package and the lender, so that a consensus node in the blockchain network executes the intelligent contract corresponding to the artificial intelligence model, and performs risk prediction on credit data of the lender of each asset in the resource package through the artificial intelligence model to obtain a risk score of each asset.

In the above scheme, the grading module is further configured to divide the value range of the risk scores of all the assets in the asset pack into a plurality of score segments, and each score segment corresponds to one risk grade; and according to the risk score of each asset in the asset package, dividing the assets into corresponding risk levels.

In the above scheme, the filtering module is further configured to filter out the assets of the lender corresponding to the lender from the asset package for the lender who cannot obtain the corresponding credit investigation data from the credit investigation system before performing risk prediction on the credit investigation data of the lender of each asset through the artificial intelligence model.

In the above scheme, the filtering module is further configured to determine the reject ratio corresponding to the asset pack based on the risk level and the reject ratio corresponding to the risk level, where the reject ratio corresponding to the risk level is a ratio of assets with default in the same risk level to total assets; when the reject ratio of the asset pack exceeds the expected reject ratio, respectively filtering the bad assets in each risk grade in the asset pack until the reject ratio of the asset pack does not exceed the expected reject ratio; or sequentially filtering the bad assets in the asset pack according to the descending order of the risk score until the reject ratio of the asset pack does not exceed the expected reject ratio.

In the above scheme, the filtering module is further configured to obtain weights of assets corresponding to the risk levels respectively; and weighting the reject ratio corresponding to the weight and the risk grade to obtain the reject ratio of the resource package.

In the above scheme, the apparatus further comprises:

the monitoring module is used for carrying out risk prediction on credit investigation data of lenders of each asset contained in the security product after issuing the corresponding security product to the exchange system so as to obtain a risk score of each asset; executing a wind control measure when the risk of the security product is determined to be in an ascending trend according to the risk score; wherein the wind control measures include at least one of: triggering an instruction for increasing the repayment frequency of the lender; and triggering the command of the financing party for replacing the risk assets.

The embodiment of the invention provides a wind control management device for securitization of assets, which comprises:

a memory for storing executable instructions;

and the processor is used for realizing the wind control management method for securitization of the assets provided by the embodiment of the invention when executing the executable instructions stored in the memory.

The embodiment of the invention provides a storage medium, which stores executable instructions and is used for causing a processor to execute the executable instructions so as to realize the wind control management method for securitization of assets provided by the embodiment of the invention.

The embodiment of the invention has the following beneficial effects:

the credit investigation data of the lender of each asset is obtained from the credit investigation system, and the risk score of each asset is accurately predicted by means of artificial intelligence, so that the risk grades divided according to the risk scores can effectively represent the structural risk of the asset pack, and therefore, the security products are issued after bad assets in each risk grade in the asset pack are filtered, the risk of securitization of the assets is effectively reduced, and the operation efficiency of a service system is further ensured.

Drawings

FIG. 1 is a schematic diagram of an alternative application scenario 100-1 of a method for windage management of asset securitization provided by an embodiment of the present invention;

FIG. 2 is a schematic diagram of another alternative application scenario 100-2 of a method for windage management of asset securitization provided by an embodiment of the present invention;

FIG. 3 is a schematic block diagram of a wind management device 800 for securitization of assets provided by an embodiment of the present invention;

4A-4D are schematic flow diagrams of a method for wind management of asset securitization provided by an embodiment of the present invention;

FIG. 5 is a schematic diagram of an ABS transaction flow provided by an embodiment of the invention;

FIG. 6 is a schematic diagram of a computing process for determining asset screening criteria provided by an embodiment of the present invention;

fig. 7 is a schematic diagram of asset package screening results provided by the embodiment of the invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail with reference to the accompanying drawings, the described embodiments should not be construed as limiting the present invention, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to be limiting of the invention.

Before further detailed description of the embodiments of the present invention, terms and expressions mentioned in the embodiments of the present invention are explained, and the terms and expressions mentioned in the embodiments of the present invention are applied to the following explanations.

1) The wind control management system comprises: the system for managing and controlling the risk of securitization of the consumed assets comprises two functions of credit assessment screening and credit management and control.

2) The credit investigation system comprises: systems for collecting and managing personal credit data of a user, such as bank credit investigation systems and various third party credit investigation systems.

3) Special Purpose vectors (SPV, special Purpose plasmid Vehicle): also known as special purpose organizations/companies, whose function is to purchase, package, and based on securities, finance the securities with investors in the offshore securities securitization process, referring to a special entity that accepts the sponsor's portfolio of assets and issues securities supported thereby.

4) Consumption of financial assets: assets formed by various consumer financial products include personal loans, consumer stages in various scenes, vehicle mortgage loans, house mortgage loans, and the like.

5) And 4, financing the resource: namely, the asset provider is an organization which distributes consumption-like fund financing to security products and collects investment funds to the society.

6) And (3) resource pack: the packaged plurality of consumed financial assets, for example, an amount of consumed assets, may be a user's car purchase installment loan.

7) The exchange: an organization that packages a consumer financial asset into a financial product for sale to an investor.

8) An asset service platform: a system responsible for the operation of consuming financial assets.

9) Security products: the resource package can be bought through the ABS to form the securities, and has various income modes, such as cost-keeping floating income, non-cost-keeping floating income products and the like.

10 Transaction (Transaction), equivalent to the computer term "Transaction," includes operations that need to be committed to a blockchain network for execution and does not refer solely to transactions in the business context, which is followed by embodiments of the present invention in view of the convention of colloquially using the term "Transaction" in blockchain technology.

11 Block chain (Blockchain) is an encrypted, chained storage structure formed of blocks (blocks).

12 Block chain Network (Blockchain Network) that incorporates new blocks into a set of nodes of a block chain in a consensus manner.

13 Ledger (legger), which is a general term for blockchains (also called Ledger data) and state databases synchronized with blockchains. Wherein, the blockchain records the transaction in the form of a file in a file system; the state database records the transactions in the blockchain in the form of different types of Key (Key) Value pairs for supporting fast query of the transactions in the blockchain.

14 Smart Contracts (Smart Contracts), also known as chain codes (chaincodes) or application codes, programs deployed in nodes of a blockchain network that execute the Smart Contracts called in received transactions to update or query the key-value data of the state database.

The inventor finds that the wind control management measures in the related art are difficult to adapt to the new form of internet finance in the process of implementing the embodiment of the invention, and frequent risk problems cause unsmooth fund flow of the ABS business system, so that the operation efficiency of the business system is influenced. The following is an analysis and explanation specifically combining various wind control management measures provided by the related art.

Related art wind control measures include internal credit augmentation and external credit augmentation. The internal credit increase mainly comprises asset structure design, quality insurance, excess interest difference and the like, and the external credit increase comprises guarantee, performance guarantee risk and the like, which are respectively explained below.

Asset structure design the underlying asset to be transferred is structured, e.g. designed to be in priority and inferior levels, with the proportions being 80% and 20% respectively, 80% of the assets being securitized to yield securities which are issued to priority investors, the remaining 20% being self-sustained by the asset provider (financer). When the principal and the income are paid, the principal and the fixed income are obtained by priority and then distributed to the secondary. The design is such that the risk loss of the securitization of the assets is always borne first by the secondary investor, thereby enhancing the security of the priority investor.

The quality insurance fund is a quality insurance fund which is stored in a specified account in a certain proportion by an asset provider in advance when securities are issued, and once the assets are subjected to risk loss, the quality insurance fund can be used for making up the loss.

Excess interest is the setting of interest rates for assets higher than the interest rate of the securities issued, so that interest income beyond principal can be used to offset the risk loss of the asset.

The security is provided by a third party security company for securitization of the issued assets, and the security company compensates for the default.

The insurance of performing guarantee refers to that the insurance company guarantees the securitized assets, if the overdue of cashing occurs, the insurance company fulfills the insurance responsibility according to the policy agreement, and the benefit of investors is guaranteed.

However, the related art wind control measures are designed by transaction structures to avoid risks, and a third-party assessment organization generally issues an assessment report, and the report is generally used for assessing the risks of assets to be subjected to ABS according to the operation conditions of asset providers and the historical performances of the assets. However, the method greatly depends on the historical operating conditions of the asset provider, so that the risk is high for the quality of the underlying assets behind the ABS, and no accurate objective quantitative judgment is provided. Therefore, this method of determination may fail in the event of a large change in operating conditions or the asset provider does not disclose accurate historical data. When the risk breaks through the measures of internal credit accruing, there is also the possibility of external credit accruing to decline the acceptance for various reasons, ultimately resulting in impaired profits for the investor. Especially for ABS assets butted on an Internet financing platform, the facing investors are ordinary users, the risk resistance is poor, if a risk default event occurs, the income safety of the investors cannot be guaranteed, and the reputation of the financing platform is greatly influenced. Meanwhile, frequent risk problems cause unsmooth capital transfer of the ABS service system, and further affect the operating efficiency of the service system.

Aiming at the technical problem that frequent risk problems exist in the scheme of the embodiment of the invention, the capital circulation of an ABS service system is not smooth, and the operation efficiency of the service system is further influenced, the embodiment of the invention provides a method and a device for wind control management of asset securitization, electronic equipment and a storage medium, and the risk of the asset securitization service system can be effectively controlled, so that the operation efficiency of the service system is improved.

An exemplary application of the asset securitization wind control management system provided by the embodiment of the present invention is described below, and the asset securitization wind control management device provided by the embodiment of the present invention may be implemented based on a server or a server cluster, for example, a server deployed in a cloud, and executes the following wind control schemes provided by the embodiment of the present invention: and filtering the bad assets in each risk level in the asset package according to the risk score of each asset in the asset package, and issuing corresponding security products to the exchange system according to the assets left after the filtration of the asset package.

Referring to fig. 1, fig. 1 is a schematic diagram of an optional application scenario 100-1 of a method for managing wind for securitization of assets according to an embodiment of the present invention, where entities include: terminal 200, wind control management system 400, credit investigation system 500 and exchange system 600. The exchange system 600 is connected via a network 300, and the network 300 may be a wide area network or a local area network, or a combination thereof.

The wind control management system 400 performs credit investigation evaluation and screening on the asset package of the financing party by combining credit investigation data acquired from the credit investigation system 500, and then issues corresponding security products to the exchange system 600, the exchange system 600 issues securities through its own security issue channel, for example, issues to the financing APP 210 in the terminal 200, and the financing party can purchase a certain amount of security products in the financing APP 210 and acquire and check profits in the financing APP 210 according to an agreed profit manner. In addition, the wind control management system 400 may further perform credit investigation management and control on the asset pack, and execute corresponding wind control management measures when the asset pack is at risk to ensure the fund security of the investor.

In some embodiments, the embodiments of the present invention may also be implemented in combination with a Blockchain technology, where a Blockchain (Blockchain) is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, and an encryption algorithm. The blockchain is essentially a decentralized database, which is a string of data blocks associated by using cryptography, each data block contains information of a batch of network transactions, and the information is used for verifying the validity (anti-counterfeiting) of the information and generating the next block. The blockchain network may include a blockchain underlying platform, a platform product services layer, and an application services layer.

The underlying platform of the blockchain network may include processing modules for user management, basic services, intelligent contracts, and operation monitoring. The user management module is responsible for identity information management of all blockchain participants, and comprises the steps of maintaining public and private key generation (account management), key management, user real identity and blockchain address corresponding relation maintenance (authority management) and the like, and under the authorized condition, supervising and auditing the transaction condition of some real identities, and providing rule configuration (wind control audit) of risk control; the basic service module is deployed on nodes of all block chain networks and used for verifying the validity of the service request, recording the valid request after consensus is completed on storage, for a new service request, the basic service firstly performs interface adaptation analysis and authentication processing (interface adaptation), then encrypts service information (consensus management) through a consensus algorithm, transmits the encrypted service information to a shared account book (network communication) completely and consistently, and performs recording and storage; the intelligent contract module is responsible for registering and issuing contracts, triggering the contracts and executing the contracts, developers can define contract logics through a certain programming language, issue the contract logics to nodes of a block chain network (contract registration), call keys or other event triggering and executing according to the logics of contract clauses, complete the contract logics and simultaneously provide the function of canceling contract upgrading and canceling; the operation monitoring module is mainly responsible for deployment, configuration modification, contract setting, cloud adaptation in the product release process and visual output of real-time states in product operation, such as: alarm, monitoring network conditions, monitoring node equipment health status, and the like.

Referring to fig. 2, fig. 2 is a schematic diagram of another optional application scenario 100-2 of the method for managing wind for securitization of assets according to the embodiment of the present invention. As shown in fig. 2, the entities involved in the application scenario 100-2 of the wind management method for asset securitization include a terminal 200, a network 300, a risk management system 400, a credit investigation system 500, an exchange system 600 and a blockchain network 700 (a consensus node 710-1 to a consensus node 710-3 are exemplarily shown). The type of blockchain network 700 is flexible and may be, for example, any of a public chain, a private chain, or a federation chain.

Taking a federation chain as an example, the wind management system 400, the credit investigation system 500 and the exchange system 600 may all access the blockchain network 700 to form a class of special nodes, called client nodes, which are special nodes different from the consensus nodes owned by the blockchain network 700 and are used for initiating a transaction for requesting uplink data or querying data to the consensus nodes, and the consensus nodes process the transaction by executing an intelligent contract call indicated in the transaction and return the processing result to the client nodes.

For example, the credit investigation system 500 initiates a transaction to the blockchain network 700 through the network 300 for the held credit investigation data to be stored in the ledger of the blockchain network 700, and the wind control management system 400 initiates a transaction to the blockchain network 700, so that the consensus node inquires the credit investigation data in the ledger by executing an intelligent contract and returns the credit investigation data to the wind control management system 400 as a transaction response; the wind control management system 400 performs credit investigation evaluation and screening on the asset package of the financing party in combination with the credit investigation data, and then issues a corresponding security product to the exchange system 600, in addition, the wind control management system 400 may also initiate a transaction to a consensus node of the blockchain network 700 to invoke an intelligent contract for credit investigation and control, the consensus node executes the intelligent contract for credit investigation and control to monitor the risk of the security product, and executes a corresponding wind control measure to avoid the risk when the risk is on an increasing trend.

The wind control management system 400 for asset securitization provided by the embodiment of the present invention is composed of one or more wind control management devices, which may be a server or a server cluster, and the following description is continued to describe the structure of the wind control management device in the wind control management system 400 for asset securitization provided by the embodiment of the present invention, referring to fig. 3, where fig. 3 is a schematic structural diagram of a wind control management device 800 for asset securitization provided by the embodiment of the present invention, and the wind control management device 800 for asset securitization shown in fig. 3 includes: at least one processor 810, a memory 850, at least one network interface 820, and a user interface 830. The various components in the asset securitization wind management device 800 are coupled together by a bus system 840. It is understood that bus system 840 is used to enable communications among the components. The bus system 840 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are designated as the bus system 840 in fig. 3.

The Processor 810 may be an integrated circuit chip having Signal processing capabilities, such as a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like, wherein the general purpose Processor may be a microprocessor or any conventional Processor, or the like.

The user interface 830 includes one or more output devices 831 including one or more speakers and/or one or more visual display screens that enable the presentation of media content. The user interface 830 also includes one or more input devices 832 including user interface components to facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

The memory 850 can include volatile memory or nonvolatile memory, and can also include both volatile and nonvolatile memory. The non-volatile Memory may be a Read Only Memory (ROM), and the volatile Memory may be a Random Access Memory (RAM). The memory 850 described in connection with the embodiments of the invention is intended to comprise any suitable type of memory. Memory 850 may optionally include one or more storage devices physically located remote from processor 810.

In some embodiments, memory 850 can store data to support various operations, examples of which include programs, modules, and data structures, or subsets or supersets thereof, as exemplified below.

An operating system 851, including system programs for handling various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and for handling hardware-based tasks;

a network communication module 852 to communicate with other computing devices via one or more (wired or wireless) network interfaces 820, exemplary network interfaces 820 including: bluetooth, wireless compatibility authentication (WiFi), and Universal Serial Bus (USB), and the like;

a display module 853 to enable presentation of information (e.g., a user interface for operating peripherals and displaying content and information) via one or more output devices 831 (e.g., a display screen, speakers, etc.) associated with the user interface 830;

an input processing module 854 for detecting one or more user inputs or interactions from one of the one or more input devices 832 and translating the detected inputs or interactions.

In some embodiments, the wind control management Device for asset securitization provided by the embodiments of the present invention may be implemented by combining software and hardware, and by way of example, the wind control management Device for asset securitization provided by the embodiments of the present invention may be a processor in the form of a hardware decoding processor, which is programmed to execute the wind control management method for asset securitization provided by the embodiments of the present invention, for example, the processor in the form of a hardware decoding processor may employ one or more Application Specific Integrated Circuits (ASICs), DSPs, programmable Logic Devices (PLDs), complex Programmable Logic Devices (CPLDs), field Programmable Gate Arrays (FPGAs), or other electronic components.

In other embodiments, the apparatus for windward management of asset securitization provided by the embodiments of the present invention may be implemented in software, and fig. 3 shows a windward management apparatus 855 for asset securitization stored in a memory 850, which may be software in the form of programs, plug-ins, and the like, and includes a series of modules including an acquisition module 8551, a prediction module 8552, a ranking module 8553, a filtering module 8554, an issuing module 8555, and a monitoring module 8556; the obtaining module 8551, the predicting module 8552, the grading module 8553, the filtering module 8554, the issuing module 8555 and the monitoring module 8556 are used for implementing the wind control management method for securitization of assets provided by the embodiment of the invention.

The method for managing the wind control of the securitization of the assets provided by the embodiment of the invention is described below by combining the exemplary application and implementation of the terminal provided by the embodiment of the invention.

Referring to fig. 4A, fig. 4A is a flowchart illustrating a method for managing wind for securitization of assets according to an embodiment of the present invention, which is described with reference to the steps shown in fig. 4A.

In step 101, the wind control management system obtains credit investigation data of a corresponding lender from the credit investigation system for each asset in the asset package provided by the financing party.

The credit investigation data may include any credit investigation point, credit investigation credit, default data, and other data related to credit investigation.

In some embodiments, the step of obtaining credit investigation data of the corresponding lender from the credit investigation system comprises: and sending the transaction carrying the identification information of the lender to the blockchain network, wherein the consensus node of the blockchain network comprises a state database corresponding to at least one of a bank credit investigation system and a third party credit investigation system, so that the consensus node in the blockchain network queries the state database according to the identification information in the transaction, and responds to the transaction by taking the queried credit investigation data as a transaction response.

In some examples, the wind control management system sends a transaction carrying identification information of a lender to the blockchain network, broadcasts the transaction to a consensus node in the blockchain network, when the consensus node in the blockchain network receives the transaction, a digital certificate and a digital signature carried by the transaction are verified, after the verification is successful, whether the wind control management system has a transaction right is determined according to identity information of the wind control management system carried in the transaction, and any verification judgment of the digital signature and the right verification will cause the transaction to fail. And after the verification is successful, signing the digital signature of the node, and continuously broadcasting in the block chain network.

And after the consensus node in the block chain network receives the transaction which is successfully verified, filling the transaction into a new block and broadcasting. When a new block is broadcasted by a consensus node in the block chain network, performing a consensus process on the new block, if the consensus is successful, adding the new block to the tail part of the block chain stored by the new block, updating a state database according to a transaction result, and executing a transaction in the new block: for a submitted transaction carrying the lender's identification information, a key-value pair comprising the lender's identification information is added to the status database. The corresponding credit investigation data can be processed by the wind control management system by calling an intelligent contract deployed in the blockchain network, the credit investigation data is stored in the account book by the intelligent contract, and the credit investigation data of the corresponding lender can be inquired from the account book by the wind control management system.

In step 102, the wind control management system performs risk prediction on credit investigation data of lenders of each asset through an artificial intelligence model to obtain a risk score of each asset.

Wherein the artificial intelligence model can be a neural network based risk scoring model. Specifically, build a 3-layer neural network, its structure does in proper order: input layer → hidden layer → output layer, wherein the input layer receives a plurality of indicators selected for risk assessment: income, deposits, loans; the hidden layer extracts features from the index data received by the input layer; the output layer maps the features extracted by the hidden layer to a risk score.

Taking the historical loan record of a lender as a sample, taking the credit score of each loan of the lender as a label, and the training process comprises the following steps: and extracting characteristics of one or more convolutional layers in the artificial intelligence model from the historical loan records of the sample user, and mapping the characteristics into a risk score. Initializing the connection weight and the threshold in the range of (0,1), then training the sample, and updating the connection weight and the threshold (chain derivation) after obtaining the output result of the model so as to minimize the loss function. The loss function may take various forms, such as a 0-1 loss function, a squared loss function, an absolute value loss function, a logarithmic loss function, and so forth.

In some embodiments, the risk prediction of credit data of the lender of each asset through the artificial intelligence model to obtain the risk score of each asset comprises: and initiating a transaction to the block chain network, wherein the transaction carries an identification of an intelligent contract corresponding to the artificial intelligent model and parameters representing the resource package and the lender, so that the consensus node in the block chain network executes the intelligent contract corresponding to the artificial intelligent model, and risk prediction is performed on credit data of the lender of each asset in the resource package through the artificial intelligent model to obtain a risk score of each asset.

The artificial intelligence model is deployed in the block chain network, the wind control management system submits intelligent contracts (including the artificial intelligence model) needing to be called to nodes in the block chain network in a transaction initiating mode, scores are calculated by the intelligent contracts, and the intelligent contracts are carried in transaction responses and returned to the wind control management system.

In some examples, the wind control management system initiates a transaction to the blockchain network, wherein the transaction carries an identifier of an intelligent contract corresponding to the artificial intelligence model and parameters representing the asset package and the lender, and broadcasts the transaction to the consensus nodes in the blockchain network, when the consensus nodes in the blockchain network receive the transaction, the digital certificate and the digital signature carried by the transaction are verified, after the verification is successful, whether the wind control management system has the transaction right is determined according to the identity information of the wind control management system carried by the transaction, and any verification judgment of the digital signature and the right verification will result in the transaction failure. And after the verification is successful, signing the digital signature of the node, and continuously broadcasting in the block chain network.

And after the consensus node in the block chain network receives the transaction which is successfully verified, filling the transaction into a new block and broadcasting. When a new block is broadcasted by a consensus node in the block chain network, performing a consensus process on the new block, if the consensus is successful, adding the new block to the tail part of the block chain stored by the new block, updating a state database according to a transaction result, and executing a transaction in the new block: and adding the identifier of the intelligent contract carrying the corresponding artificial intelligent model and the key value pair representing the parameters of the asset package and the lender into the state database for the submitted transaction carrying the identifier of the intelligent contract carrying the corresponding artificial intelligent model and the parameters representing the asset package and the lender. The risk score of each asset can be processed by the wind control management system by calling an intelligent contract which is deployed in the blockchain network and carries a corresponding artificial intelligence model, the intelligent contract stores the risk score of each asset into an account book, and the wind control management system can inquire the risk score of each asset from the account book.

It is noted that the artificial intelligence model may also be deployed in a wind management system, which executes the artificial intelligence model to calculate the score.

Compared with the artificial intelligence model deployed in the wind control management system, the artificial intelligence model is deployed in the block chain network, so that the obtained risk score has higher reliability.

In some embodiments, referring to fig. 4B, fig. 4B is an optional flowchart of a method for wind control management of asset securitization according to an embodiment of the present invention, where based on fig. 4B, before performing risk prediction on credit data of a lender of each asset through an artificial intelligence model, the method further includes:

and 106, filtering the assets of the corresponding lenders from the asset package aiming at the lenders which cannot obtain the corresponding credit investigation data from the credit investigation system.

In some examples, for the credit investigation data available to the credit investigation system, the timeliness of the credit investigation data also needs to be considered, for example, removing the credit investigation data that is older, or assigning a relatively smaller weight compared to the newer credit investigation data.

In other examples, data of third party payments (e.g., weChat payments) may also be used as credit investigation data. Meanwhile, for the lenders lacking the credit investigation data, the credit investigation data is spread according to the social relationship. For example, for a lender lacking credit investigation data, the credit investigation data is weighted according to the credit investigation data of a user having a social relationship with the lender and the social distance of the user having the social relationship with the lender to be used as corresponding credit investigation data.

Therefore, the assets corresponding to the lenders which cannot obtain credit investigation data are filtered out, or the credit investigation data which lasts for a long time are removed, so that the risk score of the assets is more accurate and credible.

In step 103, the wind management system assigns the assets in the asset pack to corresponding risk levels according to the risk score of each asset.

In some embodiments, the step of assigning assets in the asset pack to corresponding risk levels according to the risk score of each asset comprises: dividing the value range of the risk scores of all the assets in the asset pack into a plurality of score sections, wherein each score section corresponds to one risk grade; and according to the risk score of each asset in the asset package, dividing the assets into corresponding risk levels.

For example, the value of the risk score of all the assets in the asset pack ranges from 1 to 100, and the value ranges from 1 to 10 points, from 11 to 20 points, from 21 to 30 points, and … …, and so on, the risk score is divided into 10 score segments, each score segment corresponds to one risk level, and the risk level ranges from 1 to 10. It is understood that risk level 1 corresponds to assets having a risk score of 1 to 10 and risk level 2 corresponds to assets having a risk score of 11 to 20.

In step 104, the wind management system filters the undesirable assets in each risk level in the asset pack.

In step 105, the wind management system issues the corresponding security product to the exchange system for the assets remaining after the asset pack filtering.

In some embodiments, after issuing the corresponding security product to the exchange system, further comprising: carrying out risk prediction on credit investigation data of a lender of each asset contained in the security product to obtain a risk score of each asset; when the risk of the security product is determined to be in an ascending trend according to the risk score, executing a wind control measure; wherein the wind control measures comprise at least one of the following: triggering an instruction for increasing the repayment frequency of the lender; and triggering an instruction of the financing party for replacing the risk assets.

For example, after the security product is issued, the risk prediction of credit data of lenders of each asset included in the security product is continuously carried out periodically or aperiodically, and the risk score of each asset is obtained. And executing a wind control measure when the risk of the security product is determined to be in an ascending trend according to the risk score. For example, after the securities products are issued, the monitoring shows that the proportion of the assets with the highest risk level in the asset pack accounts for more than 10 percent, the collection urging force can be enhanced, for example, the borrower is reminded to pay every month in the past, and the reminding frequency is increased to remind the borrower once every week; in addition, the financing assets can be reminded to replace the high-risk assets.

Referring to fig. 4C, fig. 4C is an alternative flowchart of a method for managing assets securitization according to an embodiment of the present invention, and in some embodiments, fig. 4C shows that step 104 can be implemented by step 1041 and step 1042 shown in fig. 4C.

In step 104, the bad assets in each risk level in the asset package are filtered, including: in step 1041, determining a reject ratio corresponding to the asset pack based on the risk level and the reject ratio corresponding to the risk level, wherein the reject ratio corresponding to the risk level is a ratio of assets having default in the same risk level to total assets; in step 1042, when the reject ratio of the asset pack exceeds the expected reject ratio, respectively filtering the bad assets in each risk level in the asset pack until the reject ratio of the asset pack does not exceed the expected reject ratio; or sequentially filtering the bad assets in the asset pack according to the descending order of the risk scores until the reject ratio of the asset pack does not exceed the expected reject ratio.

In step 1041, assuming that the assets with risk scores of 1 to 10 corresponding to risk level 1 have 1000 total assets, wherein 100 of the assets have default, the reject rate corresponding to risk level 1 is 10%.

In some embodiments, determining the corresponding fraction of defects of the asset pack based on the risk level and the fraction of defects corresponding to the risk level includes: acquiring weights of assets corresponding to the risk levels respectively; and weighting the reject ratio corresponding to the weight and the risk grade to obtain the reject ratio of the resource package.

The weight and the risk level are in positive correlation, that is, the higher the risk level is, the larger the corresponding weight is.

For example, assume that the risk score of all assets in the asset package ranges from 1 to 30 points, with risk level 1 corresponding to assets having a risk score of 1 to 10, risk level 2 corresponding to assets having a risk score of 11 to 20, and risk level 3 corresponding to assets having a risk score of 21 to 30. Wherein, the reject ratio corresponding to risk levels 1 to 3 is bad rate1=5%, bad rate2=7% and bad rate3=10%, the weight values of the assets corresponding to risk levels 1 to 3 are 0.2, 0.3 and 0.5, respectively, and the reject ratio of the asset pack is bad rate =8.1% according to bad rate = bad rate1 + 0.2+ bad rate 2+ 0.3+ bad rate 3+ 0.5.

In step 1042, when the reject rate of the asset pack exceeds the expected reject rate, an asset screening criteria is determined, and the rejected assets in each risk class in the asset pack are filtered, which is described below with reference to different filtering methods.

In a first mode

And when the reject ratio of the resource package exceeds the expected reject ratio, sequentially filtering the bad assets in the resource package according to the descending order of the risk scores until the reject ratio of the resource package does not exceed the expected reject ratio.

For example, if the financing party provides an asset pack with a reject rate of 8.1% and an expected reject rate of 5%, the rejected assets in the asset pack are sequentially filtered in descending order of risk score to reduce the reject rate of the asset pack to below 5%. For convenience of explanation, it is assumed that the higher the risk score is, the higher the risk corresponding to the asset is, the whole asset pack is taken as a whole, and the condition of the reject ratio change of the asset pack after the high-risk assets with different proportions are removed (i.e. the high risk is preferentially removed) is measured. And determining an asset screening standard according to the expected reject ratio of the asset pack, namely, screening out the high-risk assets with the high proportion in the asset pack.

Mode two

And when the reject ratio of the resource package exceeds the expected reject ratio, respectively filtering the bad assets in each risk grade in the resource package until the reject ratio of the resource package does not exceed the expected reject ratio.

For example, assuming that the qualification rate of the asset pack provided by the financier is 8.1% and the expected qualification rate is 5%, the asset screening criteria for each risk level in the asset pack are determined, and the bad assets in each risk level in the asset pack are filtered respectively, so that the qualification rate of the asset pack is reduced to below 5%. For convenience of explanation, it is assumed that the higher the risk score is, the higher the risk corresponding to the asset is, and for each risk level, the variation of the reject ratio of the asset pack after the high-risk asset with different proportions is removed (i.e. the risk is removed preferentially) is measured. And determining asset screening standards of each risk grade in the asset pack according to the expected reject ratio of the asset pack.

Different from the first mode, the second mode can avoid the situation that some assets with low risk levels are not filtered all the time.

In some embodiments, referring to fig. 4D, fig. 4D is an optional flow chart of a method for managing assets securitization and wind control according to an embodiment of the present invention, based on fig. 4D, in step 107, the exchange system receives the underwriting amount paid by the investor for the security product and pays the investing amount to the investor according to the security product.

With reference to the method for wind control management of asset securitization and the exemplary application thereof in the wind control management device of asset securitization provided by the embodiment of the present invention, a wind control management scheme in which each module of the wind control management device 855 of asset securitization provided by the embodiment of the present invention cooperates to implement asset securitization will be described.

An obtaining module 8551, configured to obtain credit investigation data of a corresponding lender from a credit investigation system for each asset in an asset package provided by an financing party;

the prediction module 8552 is used for carrying out risk prediction on credit investigation data of the lender of each asset through an artificial intelligence model to obtain a risk score of each asset;

a grading module 8553, configured to classify the assets in the asset pack into corresponding risk grades according to the risk score of each asset;

a filtering module 8554 for filtering the bad assets in each risk level in the asset package;

an issuing module 8555 for issuing the corresponding security product to the exchange system for the assets remaining after the asset package filtering.

In the above scheme, the obtaining module 8551 is further configured to send a transaction carrying identification information of the lender to a blockchain network, where a common node of the blockchain network includes a status database corresponding to at least one of a bank credit investigation system and a third-party credit investigation system, so that the common node in the blockchain network queries the status database according to the identification information in the transaction, and uses the queried credit investigation data as a transaction response to respond to the transaction.

In the above scheme, the prediction module 8552 is further configured to initiate a transaction to a blockchain network, where the transaction carries an identifier of an intelligent contract corresponding to an artificial intelligence model and parameters representing the resource package and the lender, so that a consensus node in the blockchain network executes the intelligent contract corresponding to the artificial intelligence model, and performs risk prediction on credit data of the lender of each asset in the resource package through the artificial intelligence model to obtain a risk score of each asset.

In the above scheme, the grading module 8553 is further configured to divide the value range of the risk scores of all the assets in the asset pack into a plurality of score segments, and each score segment corresponds to one risk grade;

and according to the risk score of each asset in the asset package, dividing the assets into corresponding risk levels.

In the above scheme, the filtering module 8554 is further configured to, before risk prediction is performed on credit investigation data of a lender of each asset through an artificial intelligence model, filter out assets of the lender from the asset package for lenders who cannot obtain corresponding credit investigation data from the credit investigation system;

in the above scheme, the filtering module 8554 is further configured to determine the reject ratio corresponding to the asset pack based on the risk level and the reject ratio corresponding to the risk level, where the reject ratio corresponding to the risk level is a ratio of assets with default in the same risk level to total assets;

when the reject ratio of the asset pack exceeds the expected reject ratio, respectively filtering the bad assets in each risk grade in the asset pack until the reject ratio of the asset pack does not exceed the expected reject ratio; or sequentially filtering the bad assets in the asset pack according to the descending order of the risk score until the reject ratio of the asset pack does not exceed the expected reject ratio;

in the above scheme, the filtering module 8554 is further configured to obtain weights of assets corresponding to the risk levels, respectively;

and weighting the reject ratio corresponding to the weight and the risk grade to obtain the reject ratio of the resource package.

In the above solution, the wind control management apparatus 855 for securitization of assets further includes:

the monitoring module 8556 is used for performing risk prediction on credit data of lenders of each asset included in the security product after issuing the corresponding security product to the exchange system, so as to obtain a risk score of each asset; executing a wind control measure when the risk of the security product is determined to be in an ascending trend according to the risk score; wherein the wind control measures include at least one of: and triggering an instruction for increasing the repayment frequency of the lender and a risk asset replacement instruction of the financing party.

In the following, an exemplary application of the embodiments of the present invention in a practical application scenario will be described.

The embodiment of the invention provides a wind control management method for asset securitization, which is characterized in that a risk score can be given to each asset in an asset package to be subjected to ABS securitization by utilizing a credit investigation model, namely, the risk is quantitatively evaluated. Moreover, the scoring depends on credit data (which can be owned or third-party), and the evaluation is relatively objective. Therefore, a relatively accurate quantitative judgment is made on the whole asset pack. And (4) grading and screening the assets in the asset pack by using the risk scores, and issuing security products.

In addition, after the ABS security products are issued, the risk scores of the asset packs are evaluated regularly through the credit investigation model, the risk conditions of the asset packs can be monitored, and corresponding wind control measures are taken in time when early warning occurs.

Referring to fig. 5, fig. 5 is a schematic diagram of an ABS transaction flow provided by an embodiment of the present invention, and a basic flow of a complete ABS transaction is as follows: evaluating and screening the assets provided by the financing party through a credit investigation model, and packaging the screened assets into an asset package; sold to a Special Purpose agency (SPV) by way of creditor transfer, or the SPV actively purchases securitizable assets; then the SPV collects the assets into an asset pool, and the cash flow generated by the asset pool is used as a support for the listed transaction at the exchange; the exchange issues corresponding security products and sells the security products to investors so as to achieve the purpose of collecting funds to the investors; the exchange receives the subscription fee paid by the investor for the security product and pays the investment income to the investor according to the security product; after the security product is issued, the risk monitoring of the security product is continued on a regular or irregular basis. The asset service platform is responsible for the operation of assets, and the supervision bank guarantees the transaction fund security of the buyer and the seller.

The implementation scheme of the wind control management of the asset securitization of the embodiment of the invention comprises the following steps: 1) Credit investigation evaluation screening; 2) And (5) credit investigation and monitoring. The method comprises the following specific steps:

1) Credit assessment screening

Before ABS is performed, the assets provided by the financer are first evaluated, i.e. each asset in the asset pack provided by the financer is scored by credit investigation model, for example, a credit investigation scoring system of the people's bank can be developed based on credit investigation report of the people's bank. When developing credit investigation scoring model, the credit investigation model is developed by taking actual occurred historical loans as samples; after the model is constructed, predicting the risk score of the property based on the loan record of the lender in the property, and dividing the property into different risk levels according to the risk score; and according to the historical default records of the lenders, counting the reject rate of the assets with different risk levels. The default is history default record, default proportion is obtained based on history data, and score is obtained based on actual default proportion and other factors forecast. For example, if there are 1000 assets with a risk score of 500-550, and there are 100 defaults, then the assets with a risk score of 500-550 correspond to a failure rate of 10%.

And for assets which cannot be scored without inquiring credit investigation data, not selecting the issued asset pool. For scored assets, obtaining ratings according to the scores (each rating corresponding to a score segment); and then, according to the distribution of the asset ratings and the reject ratio corresponding to the ratings, the estimated reject ratio of the asset package can be obtained, as shown in table 1.

TABLE 1

In table 1, the assets in the asset pack are divided into 10 risk levels, with risk level 1 corresponding to the highest asset risk. And according to the distribution of the asset grades and the reject ratio corresponding to the grades, obtaining the reject ratio of the whole asset pack to be 1.2% through weighting calculation.

And after asset evaluation, selecting a part with relatively good quality and relatively low risk in the asset package according to the risk score to perform ABS. The specific method comprises the following steps:

1. according to the scores, the assets in the asset pack are ranked and graded from high to low according to the risks;

2. for each risk level, calculating the change condition of the reject ratio of the asset pack after removing high-risk assets with different proportions (namely, preferentially removing high risk); or taking the asset pack as a whole, and sequentially filtering the bad assets in the asset pack according to the descending order of the risk scores, wherein the bad rate change condition of the asset pack is obtained;

3. and determining an asset screening standard according to the expected reject ratio of the asset pack, namely, what proportion of high-risk assets in the asset pack need to be screened.

As shown in fig. 6, the assets package is taken as a whole, the bad assets in the assets package are sequentially filtered according to the descending order of the risk score, and in order to reduce the bad rate of the assets package to below 5%, the screening standard can be set to remove the assets with the highest risk of 30%.

In summary, the credit investigation evaluation screening is to remove the part of the assets that are not matched with the scores and have higher risk shown by the scores in the asset package, as shown in fig. 7, fig. 7 is a schematic diagram of the screening result of the asset package provided by the embodiment of the present invention.

2) Credit investigation monitoring

After ABS release, each asset in the asset pack may continue to be scored using the credit model each month. And then monitoring whether the asset risk is in a rising trend according to the rating distribution. When the grading shows that the risk has an obvious deterioration trend, wind control measures such as strengthening the collection urging force and prompting the financing party to replace the high-risk assets can be taken in advance. As shown in the table 1, the assets with the highest risk of 1-3 grades are removed during the issuing process, and if the monitoring shows that the percentage of the assets with the risk of 1-3 grades in the asset package exceeds 10 percent after the issuing process, certain wind control measures are taken.

In an example, by the method for managing the securitization of the assets, provided by the embodiment of the invention, the assets provided by a financing party can be evaluated and screened, and then after ABS, the financing products generated by packaging are put on a financing platform to be provided for investors.

Embodiments of the present invention provide a storage medium storing executable instructions, which when executed by a processor, will cause the processor to perform a method for wind management of asset securitization provided by embodiments of the present invention.

In some embodiments, the storage medium may be memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories.

In some embodiments, the executable instructions may be in the form of a program, software module, script, or code written in any form of programming language, including compiled or interpreted languages, or declarative or procedural languages, and it may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

By way of example, executable instructions may correspond, but do not necessarily have to correspond, to files in a file system, and may be stored in a portion of a file that holds other programs or data, such as in one or more scripts in a hypertext Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).

By way of example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.

In summary, the embodiment of the invention has the following beneficial effects:

1. and acquiring credit investigation data of the lender of each asset from the credit investigation system, and performing risk prediction on the credit investigation data through an artificial intelligence model to more accurately acquire the risk score of each asset.

2. Credit data of lenders of each asset and the risk score of each asset are obtained through the blockchain network, so that the credibility of the risk score of the asset is higher.

3. According to the risk score of each asset, the assets in the asset pack are divided into corresponding risk levels, bad assets in each risk level in the asset pack are filtered, risks of the asset securitization business system can be effectively controlled, and operation efficiency of the operation system is improved.

4. The credit data of the lender for each asset corresponding to the issued security product is continuously monitored periodically or aperiodically so that the risk is always in a controllable state.

The above description is only an example of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and scope of the present invention are included in the protection scope of the present invention.

Claims (10)

1. A method for windage management of securitization of assets, comprising:

acquiring credit investigation data of a corresponding lender from a credit investigation system aiming at each asset in an asset package provided by an financing party;

carrying out risk prediction on credit investigation data of lenders of each asset through an artificial intelligence model to obtain a risk score of each asset;

according to the risk score of each asset, the assets in the asset package are divided into corresponding risk levels;

determining the reject ratio corresponding to the asset pack based on the risk grade and the reject ratio corresponding to the risk grade, wherein the reject ratio corresponding to the risk grade is the proportion of assets with default in the same risk grade to the total assets;

when the reject ratio of the resource pack exceeds the expected reject ratio, respectively filtering the bad assets in each risk grade in the resource pack until the reject ratio of the resource pack does not exceed the expected reject ratio, or

Sequentially filtering the bad assets in the asset pack according to the descending order of the risk score until the reject ratio of the asset pack does not exceed the expected reject ratio;

and aiming at the assets remaining after the asset package is filtered, issuing corresponding security products to an exchange system.

2. The method of claim 1, wherein said obtaining credit investigation data of the corresponding lender from the credit investigation system comprises:

sending a transaction carrying identification information of the lender to a blockchain network, wherein a common identification node of the blockchain network comprises a state database corresponding to at least one of a bank credit system and a third-party credit system so as to ensure that the common identification node of the blockchain network comprises the state database

And querying the state database by a consensus node in the block chain network according to the identification information in the transaction, and responding to the transaction by taking the queried credit investigation data as a transaction response.

3. The method of claim 1, wherein the risk prediction of credit data of lenders of each asset by an artificial intelligence model to obtain a risk score of each asset comprises:

initiating a transaction to a blockchain network, wherein the transaction carries an identification of an intelligent contract corresponding to an artificial intelligence model, and parameters representing the asset pack and the lender, such that

And executing an intelligent contract corresponding to the artificial intelligence model by a consensus node in the block chain network, and performing risk prediction on credit investigation data of lenders of each asset in the asset package through the artificial intelligence model to obtain a risk score of each asset.

4. The method of claim 1, wherein prior to risk prediction of credit data for lenders of each asset using the artificial intelligence model, the method further comprises:

and for the lenders who cannot obtain the corresponding credit investigation data from the credit investigation system, filtering the assets of the corresponding lenders from the asset package.

5. The method of claim 1, wherein the assigning the assets in the asset pack to corresponding risk levels according to the risk score of each asset comprises:

dividing the value range of the risk scores of all the assets in the asset pack into a plurality of score sections, wherein each score section corresponds to one risk grade;

and according to the risk score of each asset in the asset package, dividing the assets into corresponding risk levels.

6. The method of claim 1, wherein determining the fraction defective corresponding to the asset pack based on the risk level and the fraction defective corresponding to the risk level comprises:

acquiring weights of assets corresponding to the risk levels respectively;

and weighting the reject ratio corresponding to the weight and the risk grade to obtain the reject ratio of the resource package.

7. The method of claim 1, wherein after issuing the corresponding security product to the exchange system, the method further comprises:

carrying out risk prediction on credit investigation data of a lender of each asset contained in the security product to obtain a risk score of each asset;

executing a wind control measure when the risk of the security product is determined to be in an ascending trend according to the risk score;

wherein the wind control measures include at least one of:

triggering an instruction for increasing the repayment frequency of the lender;

and triggering the command of the financing party for replacing the risk assets.

8. A wind management device for securitization of assets, the device comprising:

the acquisition module is used for acquiring credit investigation data of a corresponding lender from the credit investigation system aiming at each asset in the asset package provided by the financing party;

the prediction module is used for carrying out risk prediction on credit investigation data of the lender of each asset through the artificial intelligence model to obtain a risk score of each asset;

the grading module is used for grading the assets in the asset pack to corresponding risk grades according to the risk scores of each asset;

the filtering module is used for determining the reject ratio corresponding to the asset pack based on the risk grade and the reject ratio corresponding to the risk grade, wherein the reject ratio corresponding to the risk grade is the proportion of assets with default in the same risk grade to the total assets;

when the reject ratio of the asset pack exceeds the expected reject ratio, respectively filtering the bad assets in each risk grade in the asset pack until the reject ratio of the asset pack does not exceed the expected reject ratio, or

Sequentially filtering the bad assets in the asset pack according to the descending order of the risk score until the reject ratio of the asset pack does not exceed the expected reject ratio;

and the issuing module is used for issuing the corresponding security products to the exchange system aiming at the assets left after the asset package is filtered.

9. A computer readable storage medium having stored thereon executable instructions for causing a processor to perform, when executed, the method of windmanaging asset securitization of any one of claims 1 to 7.

10. A computing device, comprising:

a memory for storing executable instructions;

a processor for implementing the method of windmanagement of asset securitization of any one of claims 1 to 7 when executing executable instructions stored in the memory.