CN114037519A

CN114037519A - Open risk assessment method and device, computer equipment and storage medium

Info

Publication number: CN114037519A
Application number: CN202111353701.XA
Authority: CN
Inventors: 胡文涛; 金纯亮; 黄剑文; 乔媛
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2021-11-16
Filing date: 2021-11-16
Publication date: 2022-02-11

Abstract

The application relates to an exposure risk assessment method, an exposure risk assessment device, computer equipment, a storage medium and a computer program product, which can be used in the technical field of big data and are used for assessing exposure risks in real time. The method comprises the following steps: obtaining a value distribution prediction result of a product to be evaluated through a value prediction model associated with the product to be evaluated; dividing the value distribution prediction result according to the number of preset risk assessment grades to obtain a value interval corresponding to each risk assessment grade; inquiring a value interval corresponding to each risk evaluation grade according to the real-time value of the product to be evaluated to obtain a target risk evaluation grade corresponding to the product to be evaluated; and determining a risk processing strategy of the product to be evaluated according to the real-time value and the target risk evaluation grade.

Description

Open risk assessment method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of big data technologies, and in particular, to an exposure risk assessment method, apparatus, computer device, and computer program product.

Background

With the vigorous development of financial institutions in the business of business transactions for guests and businesses, financial institutions have introduced a variety of financial products, such as precious metals, account energy, agricultural products, etc., for related businesses. However, in the case of an open foreign exchange, the financial institution may be lost in terms of economy due to the change in exchange rate, and in order to avoid the risk of exchange rate, a risk assessment is performed on the financial products that are open to the foreign exchange.

In the conventional method, a Weighted Aggregate Position (WAP) is usually used to evaluate the static Risk of an exposure, or a Risk Value model (Value at Risk, VaR) is used to estimate the maximum loss of a certain fund exposure in a certain period of time in the future. However, in actual operation, the exchange rate of the foreign exchange exposure is constantly changed, and the current exposure risk assessment method cannot provide corresponding risk information according to the real-time value of the product, so that the risk opportunity for coping is lost. Therefore, it is becoming increasingly important to conduct dynamic exposure risk assessment for the real-time changing value of a product.

Disclosure of Invention

In view of the above, it is desirable to provide an exposure risk assessment method, an apparatus, a computer device, a computer readable storage medium and a computer program product capable of assessing an exposure risk in real time.

In a first aspect, the present application provides an exposure risk assessment method. The method comprises the following steps:

obtaining a value distribution prediction result of a product to be evaluated through a value prediction model associated with the product to be evaluated;

dividing the value distribution prediction result according to the number of preset risk assessment grades to obtain a value interval corresponding to each risk assessment grade;

inquiring a value interval corresponding to each risk evaluation grade according to the real-time value of the product to be evaluated to obtain a target risk evaluation grade corresponding to the product to be evaluated;

and determining a risk processing strategy of the product to be evaluated according to the real-time value and the target risk evaluation grade.

In one embodiment, the dividing the value distribution prediction result according to the number of preset risk assessment levels to obtain a value interval corresponding to each risk assessment level includes:

according to the preset risk level evaluation quantity, the confidence intervals associated with the value distribution prediction results are divided to obtain the distribution probability of the product to be evaluated in each risk level;

converting the value distribution prediction result into a standard normal distribution prediction result according to the distribution probability;

and inquiring a standard normal distribution probability table to obtain data matched with the prediction result of the standard normal distribution, wherein the data is used as the value interval of the risk assessment grade.

In one embodiment, after dividing the value distribution prediction result according to the number of preset risk assessment levels to obtain a value interval corresponding to each risk assessment level, the method further includes:

establishing a first mapping relation between the risk evaluation grades and the barrel serial numbers in the barrel sequencing and a second mapping relation between the value intervals and the barrel serial numbers according to the value intervals corresponding to the risk evaluation grades;

storing each risk evaluation grade and a value interval corresponding to each risk evaluation grade into a corresponding bucket range data table of a product to be evaluated;

the inquiring the value interval corresponding to each risk assessment grade according to the real-time value of the product to be assessed to obtain the target risk assessment grade corresponding to the product to be assessed comprises the following steps:

inquiring the bucket range data table, and determining a target value interval corresponding to the real-time value;

inquiring the second mapping relation to obtain a target bucket serial number corresponding to the target value interval;

and inquiring the first mapping relation to obtain a risk evaluation grade corresponding to the target bucket serial number, and taking the risk evaluation grade as a target risk evaluation grade corresponding to the product to be evaluated.

In one embodiment, after querying the first mapping relationship to obtain a risk assessment level corresponding to the target bucket serial number, as a target risk assessment level corresponding to the product to be assessed, the method further includes:

generating bit information of the product to be evaluated under the target risk evaluation level;

and updating the historical bit information of the product to be evaluated under the historical risk evaluation level in the bucket sorting table into the bit information of the product to be evaluated under the target risk evaluation level.

In one embodiment, the determining a risk processing policy for the product to be evaluated according to the real-time value and the target risk evaluation level includes:

inputting the real-time value and the target risk evaluation grade into a strategy prediction model associated with the product to be evaluated to obtain a risk processing strategy of the product to be evaluated;

after determining the risk processing strategy of the product to be evaluated according to the real-time value and the target risk evaluation grade, the method further comprises the following steps:

and storing the target risk evaluation grade and the risk processing strategy into a product data table of the product to be evaluated.

In one embodiment, after storing the risk assessment level, the real-time value, and the risk processing policy corresponding to the product to be assessed in the product data table of the corresponding product to be assessed, the method further includes:

acquiring the updating frequency of the real-time value of the product to be evaluated;

calculating to obtain the average updating frequency of the real-time value of the product to be evaluated according to the updating frequency;

generating a risk assessment graph comprising the risk processing strategy, the risk assessment grade and the bit information according to the average updating frequency;

the risk assessment chart is used for representing the exposure risk assessment result of the product to be assessed.

In a second aspect, the application further provides an exposure risk assessment device. The device comprises:

the prediction module is used for obtaining a value distribution prediction result of the product to be evaluated through a value prediction model associated with the product to be evaluated;

the dividing module is used for dividing the value distribution prediction result according to the number of preset risk assessment grades to obtain a value interval corresponding to each risk assessment grade;

the evaluation module is used for inquiring the value interval corresponding to each risk evaluation grade according to the real-time value of the product to be evaluated to obtain a target risk evaluation grade corresponding to the product to be evaluated;

and the strategy module is used for determining a risk processing strategy of the product to be evaluated according to the real-time value and the risk evaluation grade.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the following steps when executing the computer program:

In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:

In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:

According to the method, the device, the computer equipment, the storage medium and the computer program product for evaluating the exposure risk, the value distribution prediction result of the product to be evaluated is obtained through the value prediction model associated with the product to be evaluated; dividing the value distribution prediction result according to the number of preset risk assessment grades so as to obtain a value interval corresponding to each risk assessment grade; inquiring a value interval corresponding to each risk evaluation grade according to the real-time value of the product to be evaluated to obtain a target risk evaluation grade corresponding to the product to be evaluated; and determining a corresponding risk processing strategy according to the real-time value of the product to be evaluated and the target risk evaluation level. By adopting the method, the future exposure risk of the product is not required to be estimated according to the prediction result of the historical value, and the real-time exposure risk estimation result is provided for the exposure operator by dynamically estimating the real-time value of the product to be estimated, so that the method is favorable for implementing corresponding risk countermeasures on the product in time.

Drawings

FIG. 1 is a diagram of an application environment of the exposure risk assessment method according to an embodiment;

FIG. 2 is a schematic flow chart of an exposure risk assessment method according to an embodiment;

FIG. 3 is a value normal distribution graph of the exposure risk assessment method according to an embodiment;

FIG. 4 is a schematic flow chart diagram of an exposure risk assessment method according to another embodiment;

FIG. 5 is a schematic flow chart diagram illustrating an exposure risk assessment method according to yet another embodiment;

FIG. 6 is a block diagram of an open risk assessment device according to an embodiment;

FIG. 7 is a diagram illustrating an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

It should be noted that the exposure risk assessment method, the apparatus, the computer device, and the computer program product provided in the embodiments of the present disclosure may be used in the field of big data technology to assess exposure risk in real time, and may also be used in any field other than the field of big data, for example, the financial field.

The exposure risk assessment method provided by the embodiment of the application can be applied to the application environment shown in fig. 1. Wherein the terminal 101 communicates with the server 102 via a network. The data storage system may store data that the server 102 needs to process. The data storage system may be integrated on the server 102, or may be located on the cloud or other network server. The server 102 obtains a value distribution prediction result of a product to be evaluated through a value prediction model associated with the product to be evaluated, then divides the value distribution prediction result according to the number of preset risk evaluation grades to obtain a value interval corresponding to each risk evaluation grade, then performs barrel sorting on the product to be evaluated according to the real-time value and the value interval of the product to be evaluated to obtain a target risk evaluation grade corresponding to the product to be evaluated, finally determines a risk processing strategy of the product to be evaluated according to the real-time value and the target risk evaluation grade of the product to be evaluated, and an open operator checks the risk processing strategy, the target risk evaluation grade, a risk evaluation graph and the like of the product to be evaluated through the terminal 101. The terminal 101 may be but not limited to various personal computers, notebook computers, smart phones, tablet computers, internet of things devices and portable wearable devices, and the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart car-mounted devices, and the like. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, and the like. The server 102 may be implemented as a stand-alone server or as a server cluster comprised of multiple servers.

In one embodiment, as shown in fig. 2, an exposure risk assessment method is provided, which is exemplified by the application of the method to the server in fig. 1, and includes the following steps:

step S201, obtaining a value distribution prediction result of the product to be evaluated through a value prediction model associated with the product to be evaluated.

The product to be evaluated is a financial product which needs to be subjected to exposure risk evaluation, and the server also stores identification information of the product to be evaluated.

The value prediction model associated with the product to be evaluated is used for calculating the maximum loss value of the product to be evaluated in a preset future time period.

In practical applications, the Value prediction model may be referred to as a Risk measurement model (Value at task, VaR),

specifically, one or more products to be evaluated, which need to be subjected to exposure risk evaluation, are determined, a preset future time period and a confidence interval are set for each product to be evaluated, and the preset future time period, the confidence interval and the historical value of the product to be evaluated are input into a value prediction model to obtain a value distribution prediction result of the product to be evaluated. The value distribution prediction result refers to a value normal distribution graph of the product to be evaluated in a preset future time period. When the value normal distribution diagram of the product to be evaluated is obtained, the average value, the standard deviation, the lowest price corresponding to the confidence interval, the highest price corresponding to the confidence interval and the profit-loss line price of the value distribution diagram can be obtained at the same time. The preset future time period may be a day, a week, etc., and may be adjusted according to actual situations, which is not specifically limited herein.

For example, the risk of exposure of each product to be evaluated is periodically evaluated by using a VaR model, the confidence interval of the product to be evaluated is set to 95%, the VaR of the product to be evaluated in the next week is calculated by a historical simulation method or monte carlo according to multiple or single factors (such as exchange rate) in the near future of the product to be evaluated, and then a value normal distribution diagram of the product to be evaluated in the next week is obtained, wherein the value normal distribution diagram is shown in fig. 3.

It should be noted that the VaR model predicts the loss of future time according to the historical information of the product, and cannot perform risk assessment on the real-time value, so the VaR model is used regularly to obtain a value distribution prediction result, and the subsequent real-time risk assessment step of exposure is performed by taking the data such as the average value, the standard deviation, the confidence interval and the like in the value distribution prediction result as the processing basis.

Step S202, according to the number of preset risk assessment levels, value distribution prediction results are divided, and a value interval corresponding to each risk assessment level is obtained.

The preset risk assessment level number refers to the level number set according to the exposure risk assessment requirement of the product to be assessed, and can be 5, 10, 19 and the like, and can be adjusted according to actual conditions.

Specifically, the server obtains the number of preset risk assessment grades, divides the distribution probability of each risk assessment grade from the lowest price of a confidence interval to the highest price of the confidence interval, calculates the distribution probability of a value interval behind each risk assessment grade, brings the average value and the standard deviation in a value distribution prediction result into a normal distribution formula, calculates to obtain a value interval corresponding to each wind assessment grade, and stores the risk assessment grade and the value interval corresponding to the risk assessment grade into a barrel range data table.

In practical application, the normal distribution formula of the value normal distribution diagram of the product to be evaluated is as follows:

X～N(u,δ²) (1)

wherein u represents the average value of the value normal distribution diagram of the product to be evaluated, and δ represents the standard deviation of the value normal distribution diagram of the product to be evaluated.

Step S203, inquiring a value interval corresponding to each risk evaluation grade according to the real-time value of the product to be evaluated to obtain a target risk evaluation grade corresponding to the product to be evaluated.

The real-time value refers to the numerical value of exposure risk influence factors of the product to be evaluated, such as real-time exchange rate price.

Specifically, the server receives the real-time value of the product to be evaluated, obtains a target risk level corresponding to the real-time value of the product to be evaluated based on a barrel sorting principle, regards each product to be evaluated as an element, uses a value interval as a value range of the elements in a barrel, obtains a mapping relation between the real-time value of the product to be evaluated and the value interval through a mapping function, obtains the value interval corresponding to the real-time value, queries the risk evaluation level corresponding to the value interval, and further obtains the target risk evaluation level corresponding to the product to be evaluated at the real-time price.

And S204, determining a risk processing strategy of the product to be evaluated according to the real-time value and the target risk evaluation level.

The risk processing strategy is processing strategy information set according to the exposure business requirement and used for indicating an exposure operator to carry out risk processing on the product. The relationship between the risk management policies and the risk assessment ratings is many-to-many, such as a product that contains multiple different risk management policies in one risk rating.

Specifically, the server inputs the real-time value and the target risk evaluation level of the product to be evaluated into a strategy prediction model associated with the product to be evaluated, the strategy prediction model judges the profit and loss condition of the product according to the real-time price, judges the future value of the product according to the target risk level, and outputs the risk processing strategy of the product to be evaluated. Wherein the risk policy comprises: 1. the leveling is urgently needed; 2. strongly suggesting a flat bin; 3. leveling can be considered; 4. no leveling is suggested; 5. suggesting a transition to self-sustaining.

In practical application, as shown in fig. 3, when the real-time value is an actual price 1, the product holder is in a loss state, the probability of obtaining the actual price 1 through calculation is a negative number, and the risk evaluation level of the product at the actual price 1 after bucket sorting is 0, the risk processing policy is set as: "5, suggest to go to self-sustaining".

In the open risk assessment method, a value distribution prediction result of a product to be assessed is obtained through a value prediction model associated with the product to be assessed; dividing the value distribution prediction result according to the number of preset risk assessment grades so as to obtain a value interval corresponding to each risk assessment grade; according to the real-time value of the product to be evaluated, barrel sorting is carried out on the product to be evaluated, and a target risk evaluation grade corresponding to the product to be evaluated is obtained; and determining a corresponding risk processing strategy according to the real-time value of the product to be evaluated and the target risk evaluation level. By adopting the method, the future exposure risk of the product is not required to be estimated according to the prediction result of the historical value, the real-time exposure risk estimation result is provided for the exposure operator by dynamically estimating the real-time value of the product to be estimated, and more accurate processing suggestion can be provided for the exposure operator by the risk estimation result, so that corresponding risk countermeasures can be implemented on the product in time.

In an embodiment, in step S202, the value distribution prediction result is divided according to the number of preset risk assessment levels to obtain a value interval corresponding to each risk assessment level, where the value interval specifically includes the following contents: according to the preset risk level evaluation quantity, the confidence intervals associated with the value distribution prediction results are divided to obtain the distribution probability of the product to be evaluated in each risk level; converting the value distribution prediction result into a standard normal distribution prediction result according to the distribution probability; and inquiring the standard normal distribution probability table to obtain data matched with the prediction result of the standard normal distribution, wherein the data is used as a value interval of the risk assessment grade.

The confidence interval associated with the value distribution prediction result is the confidence interval set for the product to be evaluated when the value prediction model of the product to be evaluated is calculated.

Specifically, the server averagely divides confidence intervals associated with the value distribution prediction results according to the preset risk level evaluation quantity to obtain the distribution probability of the product to be evaluated in each risk level; and according to the distribution probability, calculating the distribution probability of the value interval after each risk level (including the current risk level), converting the value distribution prediction result into a prediction result of standard normal distribution, inquiring data matched with the prediction result of the standard normal distribution in a standard normal distribution probability table to serve as the value interval of the risk evaluation level, and sequentially processing each risk evaluation level according to the steps to obtain the value intervals of all the risk evaluation levels.

In practical application, assuming that the risk level evaluation number is set to 19, the serial number of the product to be evaluated is set to 4, and the confidence interval of the product No. 4 is set to 95%, the value intervals from the lowest price of the confidence interval to the highest price of the confidence interval are 19, and the probability of each value interval is: 95% ÷ 19= 0.05. If the value interval of the 16 th risk assessment level is calculated, the distribution probability of the value interval after the 16 th risk assessment level is: 0.025+0.05 x 4= 0.225; where 0.025 refers to the probability of both ends outside the 95% confidence interval, 0.05 is the probability of each value interval, and 4 refers to the value interval after the 16 th risk assessment level, i.e., the 16 th, 17 th, 18 th, 19 th risk assessment level.

Assuming that the limit price of the 16 th risk assessment level is x, the average value of the output of the VaR model corresponding to the product No. 4 is u =2, and δ is 0.299, the value distribution prediction result of the product No. 4 is converted into a standard normal distribution by the formula (2).

z＝(x-u)/δ (2)

Further, the first value of P (Z-Z) ═ 0.225 in the normal distribution probability table (as shown in table 1) is found to be Z, and the value greater than 1 to 0.225 ═ 0.775 is referred to as Z.

TABLE 1 Standard Normal distribution probability Table

	0.00	0.01	......	0.05	0.06	......
							0.0	0.5000	0.5040	0.5199	0.5239
0.1	0.5398	0.5438		0.5596	0.5636
							......				0.7224
0.6	0.7257	......
							0.7	0.7580	0.7611	0.7734	0.7764

The first value greater than 1-0.225-0.775 in the standard normal distribution probability table is 0.7+ 0.06-0.76, and z-0.76 is substituted into the formula (2) to obtain x-2.2272 as the starting value of the value interval of the 16 th risk assessment level.

According to the method, the first value larger than 0.725 is inquired in the standard normal distribution probability table, the inquiry result is 0.6, namely z is (x-u)/delta is approximately equal to 0.6, x is 2.1794, the limit price of 15 risk assessment grades is 2.1794, therefore, the value interval of the 15 th risk assessment grade is [2.1797, 2.2272], which indicates that when the real-time value is in the [2.1797, 2.2272] interval, the product to be assessed belongs to the 15 th bucket, namely the risk assessment grade of the corresponding product to be assessed is 15.

In this embodiment, confidence intervals associated with the value distribution prediction results are divided averagely, so that the distribution probability of the product to be evaluated in each risk level is the same, and the accuracy of the product to be evaluated in bucket sorting is improved.

In one embodiment, after dividing the value distribution prediction result according to the number of preset risk assessment levels to obtain a value interval corresponding to each risk assessment level, the method further includes: establishing a first mapping relation between the risk evaluation levels and the bucket serial numbers in the bucket sequencing and a second mapping relation between the value intervals and the bucket serial numbers according to the value intervals corresponding to the risk evaluation levels; storing each risk evaluation grade and a value interval corresponding to each risk evaluation grade into a corresponding bucket range data table of a product to be evaluated; in step S203, querying a value interval corresponding to each risk assessment level according to the real-time value of the product to be assessed to obtain a target risk assessment level corresponding to the product to be assessed, including: inquiring a bucket range data table, and determining a target value interval corresponding to the real-time value; inquiring the second mapping relation to obtain a target bucket serial number corresponding to the target value interval; and inquiring the first mapping relation to obtain a risk evaluation grade corresponding to the target bucket serial number, and taking the risk evaluation grade as a target risk evaluation grade corresponding to a product to be evaluated.

The first mapping relation represents that one-to-one correspondence exists between the risk assessment level and the bucket serial number in the bucket sequencing; the second mapping relation represents that a one-to-one correspondence exists between the value interval and the bucket serial number, namely, the bucket serial number uniquely corresponding to the value interval can be inquired according to the value interval.

The bucket range data table is used for storing identification information of products to be evaluated, risk evaluation grades and value intervals corresponding to the risk evaluation grades.

In practical applications, for example, as shown in table 2, the identification information of the product to be evaluated may be a product serial number, which represents a serial number of a bucket element in the bucket sorting; the risk assessment grade represents the bucket serial number in the bucket sequencing, and the value interval represents the value range corresponding to the bucket serial number.

TABLE 2 bucket Range data sheet

Product identification	Risk assessment rating	Interval of value
			4	15	[2.1794，2.2272]

Specifically, after obtaining the value intervals corresponding to the risk assessment levels, the server establishes a first mapping relationship between the risk assessment levels and the bucket serial numbers in the bucket sorting and a second mapping relationship between the value intervals and the bucket serial numbers according to the value intervals corresponding to the risk assessment levels, and stores the risk assessment levels and the value intervals corresponding to the risk assessment levels in a bucket range data table. The bucket range data table stores risk assessment grades set for different products to be assessed and value intervals corresponding to the risk assessment grades. After receiving the real-time value of the product to be evaluated, the server firstly queries the bucket range data table according to the real-time value to obtain a target value interval matched with the real-time value of the product to be evaluated, then queries the second mapping relation to obtain a target bucket serial number corresponding to the target value interval, queries the first mapping relation according to the target bucket serial number to obtain a risk evaluation grade corresponding to the target value interval, and takes the risk evaluation grade as a target risk evaluation grade corresponding to the product to be evaluated.

It should be noted that the calculation complexity of the bucket sorting algorithm is linearly related to the number of products, that is, the time complexity of the bucket sorting algorithm is o (n), which can meet the requirement of real-time processing of the risk of exposure assessment.

In the embodiment, by means of the advantage of low complexity of the bucket sequencing time, the target risk level of the product to be evaluated can be quickly obtained, the instantaneity of the exposure risk assessment of the product to be evaluated is facilitated to be improved, the future exposure risk of the product is not required to be estimated according to the prediction result of the historical value, the real-time value of the product to be evaluated is dynamically assessed through the bucket sequencing, a real-time exposure risk assessment result is provided for an exposure operator, and corresponding risk response measures can be timely implemented on the product.

In one embodiment, after querying the first mapping relationship to obtain a risk assessment level corresponding to the target bucket serial number, as a target risk assessment level corresponding to a product to be assessed, the method further includes: generating bit information of a product to be evaluated under a target risk evaluation level; and updating the historical bit information of the product to be evaluated under the historical risk evaluation level in the bucket sorting table into the bit information of the product to be evaluated under the target risk evaluation level.

The bit information is binary information that uses one bit (bit) to mark a value corresponding to a product.

For example, the serial numbers of the products are incremented from 0, if the serial number of a certain product to be evaluated is 4, the bit information corresponding to the product to be evaluated is ".. 000001000B", and then the fourth bit in the binary bit information is 1, which indicates that the current bucket includes product number 4.

Specifically, according to a bitmap algorithm, identification information of a product to be evaluated is converted into bit information, after a risk evaluation grade corresponding to the real-time price of the product to be evaluated is obtained, a historical risk evaluation grade corresponding to the last real-time price of the product to be evaluated in a bucket sorting table is inquired, 0 is set in the bit information corresponding to the historical risk evaluation grade of the product to be evaluated, a target risk evaluation grade in the bucket sorting table is inquired, and the bit information corresponding to the target risk evaluation grade is modified into the bit information of the product to be evaluated under the target risk evaluation grade.

The bucket sorting table is used for storing the latest risk evaluation grade of the product to be evaluated.

In practical applications, as shown in table 3, the example in table 3 shows that the bucket 15 contains product No. 4, that is, product No. 4 has a risk assessment rating of 15.

TABLE 3 bucket orderliness table

Bucket number (Risk assessment grade)	bitmap (bit information)
		15	...000001000B

If a conventional data storage mode is adopted, data of one int type (integer) stored in a database needs 4 bytes, and each byte occupies 8 bits (bit), then data of one int type needs 32 bits.

Assuming that there are 10 hundred million products, if the identification information of the 10 hundred million products is stored in int type, the occupied storage space is 1000000000 × 4 ÷ 1024 ÷ 1024 ≈ 3.72G, and if the 10 hundred million data is stored in the form of bit information after being converted by bitmap, the occupied storage space is 1000000000 ÷ 8 ÷ 1024 ÷ 1024 ≈ 0.116G. Therefore, the identification information of the product to be evaluated is converted into bit information through the bitmap algorithm, and the storage space of data can be reduced.

In this embodiment, the storage space of data can be greatly saved by converting the identification information of the product to be evaluated into the unit of bits to store the data.

In an embodiment, the step S204 of determining a risk processing policy of the product to be evaluated according to the real-time value and the target risk evaluation level includes: inputting the real-time value and the target risk evaluation grade into a strategy prediction model associated with the product to be evaluated to obtain a risk processing strategy of the product to be evaluated; after determining the risk processing strategy of the product to be evaluated according to the real-time value and the target risk evaluation level, the method further comprises the following steps: and storing the target risk evaluation grade and the risk processing strategy into a product data table of the product to be evaluated.

The product data table is used for storing relevant information of the product to be evaluated. The product data sheet comprises identification information of products to be evaluated, service types, currencies, transaction modes, exposure types, real-time values, quotation sources, risk evaluation grades and risk processing strategies; the identification information, the business type, the currency, the transaction mode and the exposure type are fixed data in the exposure risk assessment process, and the real-time value, the quotation source, the risk assessment grade and the risk processing strategy of a new product are mainly used in the exposure risk assessment process.

The risk processing strategy is used for representing risk handling suggestions of the product to be evaluated.

In practical applications, as shown in table 4, the data in each field of product No. 4 in the product data table is shown by taking the opening of the foreign exchange as an example.

TABLE 4 product data sheet

Wherein the risk processing policy comprises: 1. the leveling is urgently needed; 2. strongly suggesting a flat bin; 3. leveling can be considered; 4. no leveling is suggested; 5. suggesting a transition to self-sustaining. The currency refers to the currency number of the foreign exchange. The service categories include: account foreign exchange, immediate sale exchange, forward sale exchange, account crude oil and the like. The deadline code includes: 0 day, 7 days, one month, etc. The transaction mode comprises the following steps: buy first and sell second, sell first and buy second. The open type includes: multiple head, empty head. Sources of offers include: EBS, Thomson road penetration, Fxall, and the like.

Describing the example in table 4 with reference to fig. 3, when the real-time value of product No. 4 is actual price 4, the product holder is in a profit state, the probability of calculating actual price 1 is positive and greater than 0.5, which represents more profit with small probability, the risk evaluation level of the product is 15, and the risk processing policy is set as: "2, strong suggest leveling".

It should be noted that before the exposure risk assessment is performed for the first time every day, the four fields of the real-time value, the offer source, the risk assessment level and the risk processing policy in the product data table are initialized, that is, the data stored in the fields are emptied, and at the same time, the bit information in the bucket sorting table is initialized, that is, all bit positions 0 of the bit information are initialized, and when the exposure risk assessment is formally started, the relevant data such as the real-time value of the product to be assessed is received and corresponding operation is performed.

Specifically, the real-time value and the target risk evaluation grade are input into a strategy prediction model associated with the product to be evaluated, and a risk processing strategy of the product to be evaluated is obtained. The strategy prediction model is constructed according to the actual demand of a product to be evaluated, the parameters, branch logic and the like of the strategy prediction model are set in the server in advance, the calculation complexity of the strategy prediction model is linearly related to the quantity of the product, namely the time complexity of the strategy prediction model is O (n), and the requirement of real-time processing of the exposure evaluation risk can be met. And storing the target risk evaluation grade and the risk processing strategy into a product data table of the product to be evaluated.

For example, as shown in fig. 3, when the real-time value is the actual price 2, the product holder is in a loss state, the actual price 1 is calculated to be a positive number and less than 0.5, which represents that the large probability is less that the loss will occur within the var simulation time interval, the risk assessment level of the product is updated, and the risk processing policy is set as: "4, not suggest flat bin".

For another example, as shown in fig. 3, when the real-time value is an actual price 3, the product holder is in a loss state, the probability of obtaining the actual price 3 is calculated to be a positive number and greater than 0.5, which represents that the large probability is less in loss within the var simulation time interval and the small probability is more in profit, the risk assessment level of the product is updated, and the risk handling policy is set as: "3, can consider the flat storehouse".

For another example, as shown in fig. 3, when the real-time value is the actual price 5, the product holder is in a profit state, the probability that the actual price 1 is calculated is positive and greater than 0.95, which represents that the minimum probability is more profitable, and at this time, the risk assessment level of the product is set to be null, and the risk handling policy is set to: "1, need to put down the storehouse urgently", mean that this product can put down the storehouse directly.

It should be further noted that, in the data update of the product data table in this embodiment, when the data of the bucket sorting table in the foregoing embodiment is updated, there is no strict sequential limitation in the update of the two embodiments, and the data in the product data table in the foregoing embodiment may be updated first, or the data in the bucket sorting table in this embodiment may be updated first.

In this embodiment, according to the real-time value and the target risk assessment level of the product to be assessed, the risk processing strategy of the product to be assessed can be obtained, the exposure risk can be assessed in real time, meanwhile, a corresponding risk processing strategy can be provided, and corresponding risk countermeasures can be implemented on the product in time.

In one embodiment, after storing the risk assessment level, the real-time value and the risk processing policy corresponding to the product to be assessed into the product data table of the corresponding product to be assessed, the method further includes: acquiring the updating frequency of the real-time value of a product to be evaluated; calculating the average updating frequency of the real-time value of the product to be evaluated according to the updating frequency; generating a risk evaluation graph comprising a risk processing strategy, a target risk evaluation grade and bit information according to the average updating frequency; the risk assessment chart is used for representing the exposure risk assessment result of the product to be assessed.

The risk assessment graph is a view aiming at an exposure risk assessment result generated according to the related information of the product to be assessed, and the presentation forms of the risk assessment graph are various.

Specifically, the updating frequency of the real-time value of all products to be evaluated is obtained, then the average updating frequency of the real-time value of the products to be evaluated is obtained through calculation according to all the updating frequencies, the stored data such as the risk processing strategy, the target risk evaluation grade and the bit information are generated into a risk evaluation graph through a view generation tool according to the average updating frequency at fixed frequency, the risk evaluation graph is sent to a terminal for an exposure operator to check the exposure risk evaluation result of the products to be evaluated, and the exposure operator can operate the received risk evaluation graph through the terminal according to different service requirements.

For example, the terminal responds to the screening operation triggered by the exposure operator, queries products with a risk processing policy of "5 and a suggestion of conversion into self-sustaining", displays the query result, responds to the change operation of the exposure service operator, changes the risk processing policy of the products to "0. self-sustaining exposure", and can also quickly level the products with the risk processing policy of "urgent need leveling".

For another example, the terminal responds to the requirement of the exposure operator to know the demand of how many products are in each risk evaluation level, inquires bit information in the risk evaluation graph, counts the number of bit bits of 1 in the bit information corresponding to each risk evaluation level, and then the terminal obtains the number of the products contained in each risk level and displays the number. Wherein the risk assessment ratings are all arranged in a loss-to-profit pattern.

In the embodiment, according to the average updating frequency, the stored data such as the risk processing strategy, the target risk evaluation level and the bit information are generated into the risk evaluation graph at a fixed frequency, the risk evaluation graph is sent to the terminal to be checked by the exposure operator, the risk condition of real-time value to all products can be provided for the exposure operator through the risk evaluation graph, the value preference degree of the current environment is further obtained, comprehensive exposure risk decision reference is provided for the exposure operator, and corresponding risk response measures can be implemented on the products in time.

In one embodiment, as shown in fig. 4, another method for evaluating exposure risk is provided, which is illustrated by applying the method to the server in fig. 1, and includes the following steps:

step S401, obtaining a value distribution prediction result of the product to be evaluated through a value prediction model associated with the product to be evaluated.

And S402, according to the preset risk level evaluation quantity, dividing confidence intervals associated with the value distribution prediction result to obtain the distribution probability of the product to be evaluated in each risk level.

Step S403, according to the distribution probability, the value distribution prediction result is converted into a prediction result of standard normal distribution.

Step S404, inquiring a standard normal distribution probability table to obtain data matched with the prediction result of the standard normal distribution, and using the data as a value interval of the risk assessment grade.

Step S405, according to the value interval corresponding to each risk evaluation level, a first mapping relation between the risk evaluation level and the bucket serial number in the bucket sequencing and a second mapping relation between the value interval and the bucket serial number are established.

Step S406, storing each risk assessment grade and the value interval corresponding to each risk assessment grade into a corresponding bucket range data table of the product to be assessed.

Step S407, inquiring a bucket range data table, and determining a target value interval corresponding to the real-time value; and querying the second mapping relation to obtain the target bucket serial number corresponding to the target value interval.

Step S408, inquiring the first mapping relation to obtain a risk evaluation grade corresponding to the target barrel serial number, and taking the risk evaluation grade as a target risk evaluation grade corresponding to a product to be evaluated.

Step S409, generating bit information of a product to be evaluated under a target risk evaluation level; and updating the historical bit information of the product to be evaluated under the historical risk evaluation level in the bucket sorting table into the bit information of the product to be evaluated under the target risk evaluation level.

Step S410, inputting the real-time value and the target risk evaluation grade into a strategy prediction model associated with the product to be evaluated to obtain a risk processing strategy of the product to be evaluated; and storing the target risk evaluation grade and the risk processing strategy into a product data table of the product to be evaluated.

According to the open risk assessment method, the value distribution prediction result of the product to be assessed is obtained through the value prediction model associated with the product to be assessed; dividing the value distribution prediction result according to the number of preset risk assessment grades so as to obtain a value interval corresponding to each risk assessment grade; according to the real-time value and the value interval of the product to be evaluated, bucket sorting is carried out on the product to be evaluated, and a target risk evaluation grade corresponding to the product to be evaluated is obtained; and determining a corresponding risk processing strategy according to the real-time value of the product to be evaluated and the target risk evaluation level. By adopting the method, the future exposure risk of the product is not required to be estimated according to the prediction result of the historical value, the real-time value of the product to be estimated is dynamically estimated through bucket sequencing, the real-time exposure risk estimation result is provided for an exposure operator, and the method is favorable for implementing corresponding risk countermeasures on the product in time.

In order to clarify the exposure risk assessment method provided by the embodiments of the present disclosure more clearly, the exposure risk assessment method is specifically described below with a specific embodiment. In an embodiment, as shown in fig. 5, there is provided an exposure risk assessment method, which specifically includes the following steps:

the timing processing unit is used for preparing data required in the exposure risk assessment, and specifically comprises the following contents:

0. self-sustained exposure and Weighted Aggregate exposure Position (WAP): calculating the total risk value of all products under a certain exposure by using a traditional self-sustaining exposure and WAP metering method, wherein the total risk value can be used as a reference for an exposure evaluation result;

1. risk metric model (VaR): estimating each product by using a VaR model at regular time, wherein the model can output a normal distribution diagram of the exchange rate of each product in a future period of time by a historical simulation method or Monte Carlo, and simultaneously obtain the average value u of the distribution diagram, the minimum price, the maximum price and the profit-loss line price corresponding to the standard deviation delta and the 95% confidence interval;

2. calculating a value interval: and dividing the number of required value intervals from the lowest price of the confidence interval to the highest price of the confidence interval according to the u, delta and standard normal distribution probability table of each product output by the risk measurement var model, wherein the distribution probabilities corresponding to the value intervals are the same, taking the value range of the value interval as the value range of each barrel in the barrel sequencing, and updating the value interval into a barrel range data table.

The real-time processing unit is used for carrying out exposure risk assessment according to the real-time value, and specifically comprises the following contents:

3. determining the risk evaluation grade of the product according to the real-time value, determining a risk processing strategy, and updating the risk processing strategy to a product data table, wherein the method specifically comprises the following steps: establishing a barrel sorting table and a product data table, wherein the barrel sorting table and the product data table are used for storing relevant data of barrel sorting of products, initializing four fields of real-time value, quotation source, risk evaluation grade and risk processing strategy in the product data table before the first open risk evaluation every day, and initializing bit information in the barrel sorting table; and determining the risk evaluation grade of the product according to the real-time value, determining a risk processing strategy, and updating the risk evaluation grade to a product data table.

4. Updating a bucket sequencing table: inquiring bitmap bit information corresponding to the historical risk level in the barrel sorting table according to the historical risk evaluation level of the product, updating the bit corresponding to the bit information to 0, inquiring bitmap bit information corresponding to the target risk level in the barrel sorting table according to the target risk evaluation level of the product, and updating the bit corresponding to the target risk level in the bit information to 1.

The risk warning unit is used for feeding back a risk evaluation result of the product, and specifically comprises the following contents:

5. receiving data of a real-time processing module and refreshing a view, specifically comprising: and generating different risk evaluation graphs according to the average updating frequency of all products and the data in the bucket sorting table and the product data table at a fixed frequency, updating the historical view by using the newly generated view, and sending the risk evaluation graphs to the terminal for the reference of the exposure operator.

6. Open operation side leveling: and the open operator makes a corresponding flat-cabin strategy according to the risk assessment chart.

The beneficial effects of the embodiment include the following aspects:

(1) the future exposure risk of the product is not required to be estimated according to the prediction result of the historical value, the real-time value of the product to be estimated is dynamically estimated through bucket sequencing, a real-time exposure risk estimation result is provided for an exposure operator, and a more accurate processing suggestion can be provided for the exposure operator through the risk estimation result, so that corresponding risk response measures can be implemented on the product in time;

(2) the confidence intervals associated with the value distribution prediction results are averagely divided, so that the distribution probability of the products to be evaluated in each risk level is the same, and the accuracy of the products to be evaluated in barrel sorting is improved;

(3) by virtue of the advantage of low complexity of the bucket sorting time, the target risk level of the product to be evaluated can be quickly obtained, and the instantaneity of the open risk evaluation of the product to be evaluated is favorably improved;

(4) through the risk assessment graph, the risk condition of real-time value to all products can be provided for the exposure operator, so that the value preference degree of the current environment is obtained, and a quick and comprehensive exposure risk decision reference is provided for the exposure operator.

It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.

Based on the same inventive concept, the embodiment of the present application further provides an exposure risk assessment apparatus for implementing the above-mentioned exposure risk assessment method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the method, so specific limitations in one or more embodiments of the exposure risk assessment device provided below can be referred to the limitations of the exposure risk assessment method in the foregoing, and details are not described herein again.

In one embodiment, as shown in fig. 6, there is provided an exposure risk assessment apparatus 600, comprising: a prediction module 601, a partitioning module 602, an evaluation module 603, and a policy module 604, wherein:

the prediction module 601 is used for obtaining a value distribution prediction result of the product to be evaluated through a value prediction model associated with the product to be evaluated;

the dividing module 602 is configured to divide the value distribution prediction result according to the number of preset risk assessment levels to obtain a value interval corresponding to each risk assessment level;

the evaluation module 603 is configured to query, according to the real-time value of the product to be evaluated, a value interval corresponding to each risk evaluation level, and obtain a target risk evaluation level corresponding to the product to be evaluated;

and the policy module 604 is configured to determine a risk processing policy of the product to be evaluated according to the real-time value and the risk evaluation level.

In one embodiment, the dividing module 602 is further configured to divide the confidence interval associated with the value distribution prediction result according to a preset risk level evaluation quantity, so as to obtain a distribution probability of a product to be evaluated in each risk level; converting the value distribution prediction result into a standard normal distribution prediction result according to the distribution probability; and inquiring the standard normal distribution probability table to obtain data matched with the prediction result of the standard normal distribution, wherein the data is used as a value interval of the risk assessment grade.

In one embodiment, the open risk assessment apparatus 600 further includes a first storage module, configured to establish a first mapping relationship between the risk assessment level and the bucket serial number in the bucket sorting and a second mapping relationship between the value interval and the bucket serial number according to the value interval corresponding to each risk assessment level; storing each risk evaluation grade and a value interval corresponding to each risk evaluation grade into a corresponding bucket range data table of a product to be evaluated;

the evaluation module 603 is further configured to query the bucket range data table, and determine a target value interval corresponding to the real-time value; inquiring the second mapping relation to obtain a target bucket serial number corresponding to the target value interval; and inquiring the first mapping relation to obtain a risk evaluation grade corresponding to the target bucket serial number, and taking the risk evaluation grade as a target risk evaluation grade corresponding to a product to be evaluated.

In one embodiment, the exposure risk assessment apparatus 600 further includes an information generating module, configured to generate bit information of the product to be assessed at the target risk assessment level; and updating the historical bit information of the product to be evaluated under the historical risk evaluation level in the bucket sorting table into the bit information of the product to be evaluated under the target risk evaluation level.

In one embodiment, the policy module 604 is further configured to input the real-time value and the target risk assessment level into a policy prediction model associated with a product to be assessed, so as to obtain a risk processing policy for the product to be assessed;

the exposure risk assessment apparatus 600 further includes a second storage module, configured to store the target risk assessment level and the risk processing policy in a product data table of the product to be assessed.

In one embodiment, the exposure risk assessment apparatus 600 further includes a view module for obtaining an update frequency of a real-time value of a product to be assessed; calculating the average updating frequency of the real-time value of the product to be evaluated according to the updating frequency; generating a risk evaluation graph comprising a risk processing strategy, a target risk evaluation grade and bit information according to the average updating frequency; the risk assessment chart is used for representing the exposure risk assessment result of the product to be assessed.

The modules in the above-mentioned exposure risk assessment apparatus can be implemented wholly or partially by software, hardware and their combination. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used for storing data such as a value interval, a target risk evaluation level, bit information, real-time value and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an exposure risk assessment method.

Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.

In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.

In an embodiment, a computer program product is provided, comprising a computer program which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.

It should be noted that, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), Magnetic Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. An exposure risk assessment method, the method comprising:

2. The method according to claim 1, wherein the dividing the value distribution prediction result according to a preset number of risk assessment levels to obtain a value interval corresponding to each risk assessment level comprises:

3. The method according to claim 2, wherein after dividing the value distribution prediction result according to a preset number of risk assessment levels to obtain a value interval corresponding to each risk assessment level, the method further comprises:

4. The method according to claim 3, wherein after querying the first mapping relationship to obtain a risk assessment level corresponding to the target bucket number as a target risk assessment level corresponding to the product to be assessed, the method further comprises:

5. The method of claim 1, wherein determining a risk processing policy for the product to be assessed based on the real-time value and the target risk assessment rating comprises:

6. The method of claim 4, wherein after storing the risk assessment rating, the real-time value, and the risk processing policy corresponding to the product to be assessed in a product data table of the corresponding product to be assessed, further comprising:

generating a risk assessment graph comprising the risk processing strategy, the target risk assessment level and the bit information according to the average updating frequency;

7. An exposure risk assessment apparatus, the apparatus comprising:

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.

9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 6 when executed by a processor.