CN112950287A - Pricing request response method, device, equipment and storage medium - Google Patents
Pricing request response method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112950287A CN112950287A CN202110347748.9A CN202110347748A CN112950287A CN 112950287 A CN112950287 A CN 112950287A CN 202110347748 A CN202110347748 A CN 202110347748A CN 112950287 A CN112950287 A CN 112950287A
- Authority
- CN
- China
- Prior art keywords
- pricing
- category
- request
- client
- customer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application discloses a pricing request response method, a pricing request response device, pricing request equipment and a pricing request storage medium, and relates to the technical field of big data, wherein the pricing request response method comprises the following steps: receiving a pricing request of a client, and determining the category of the client according to the pricing request; inputting the category of the customer into a pricing parameter adaptive adjustment model according to the category of the customer to obtain an economic capital target return rate output by the pricing parameter adaptive adjustment model; the pricing parameter self-adaptive adjustment model is obtained by training according to sample data of the category of a client; determining a calculation result of the pricing request by adopting a preset pricing method according to the economic capital target return rate and the pricing additional information; by the technical scheme, the pricing result matched with the pricing request is automatically determined according to the pricing request of the client.
Description
Technical Field
The embodiment of the application relates to the technical field of big data, in particular to a pricing request response method, device, equipment and storage medium.
Background
At present, after the interest rate is marketized, the central bank does not determine the deposit interest rate and the loan interest rate of the commercial bank any more, and the commercial bank becomes a free pricing subject. Whether traditional business products are priced or financial derivative innovative products are priced, the pricing method becomes a core problem in business bank operation.
Typically, commercial banks typically have specialized pricing management systems for differentiated automated pricing requests from customers. However, the existing pricing management system has the following problems: firstly, a mode of manually adjusting parameters for multiple times to obtain economic capital return rate needs to consume a large amount of manpower and material resources; secondly, the data differentiation combination of multiple dimensions can result in a large data volume, so that the data processing is very slow and may also generate errors.
Therefore, improvement is urgently needed to solve the problems of the conventional pricing management system.
Disclosure of Invention
The application provides a pricing request response method, a pricing request response device, equipment and a storage medium, so that economic capital return rate parameters are automatically acquired, manual parameter adjustment is avoided, and a pricing result matched with the pricing request can be automatically determined according to the pricing request of a client.
In a first aspect, an embodiment of the present application provides a method for responding to a pricing request, where the method includes:
receiving a pricing request of a client, and determining the category of the client according to the pricing request;
inputting the category of the customer into a pricing parameter adaptive adjustment model according to the category of the customer to obtain an economic capital target return rate output by the pricing parameter adaptive adjustment model; the pricing parameter self-adaptive adjustment model is obtained by training according to sample data of the category of a client;
and determining a calculation result of the pricing request by adopting a preset pricing method according to the economic capital target return rate and the pricing additional information.
In a second aspect, an embodiment of the present application further provides an apparatus for responding to a pricing request, where the apparatus includes:
the client category determining module is used for receiving a pricing request of a client and determining the category of the client according to the pricing request;
the return rate determining module is used for inputting the category of the customer into a pricing parameter adaptive adjustment model according to the category of the customer to obtain an economic capital target return rate output by the pricing parameter adaptive adjustment model; the pricing parameter self-adaptive adjustment model is obtained by training according to sample data of the category of a client;
a pricing result determination module to determine a pricing result based on the economic capital objective.
In a third aspect, an embodiment of the present application further provides an electronic device, where the device includes:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement any one of the pricing request response methods provided by embodiments of the first aspect.
In a fourth aspect, embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements any one of the pricing request response methods provided in the embodiments of the first aspect.
The method comprises the steps of receiving a pricing request of a client, and determining the category of the client according to the pricing request; inputting the category of the customer into a pricing parameter adaptive adjustment model according to the category of the customer to obtain an economic capital target return rate output by the pricing parameter adaptive adjustment model; the pricing parameter self-adaptive adjustment model is obtained by training according to sample data of the category of a client; then, determining a calculation result of the pricing request by adopting a preset pricing method according to the economic capital target return rate and the pricing additional information; by the technical scheme, the economic capital return rate parameter adaptive to the client category is automatically acquired according to the client category based on the predetermined pricing parameter adaptive adjustment model, manual parameter adjustment is avoided, and the pricing result matched with the pricing request can be automatically determined according to the pricing request of the client.
Drawings
FIG. 1 is a flow chart of a method for responding to a pricing request according to an embodiment of the present application;
FIG. 2 is a flowchart of a pricing request response method according to a second embodiment of the present application;
FIG. 3 is a flowchart of a method for responding to a pricing request according to a third embodiment of the present application;
FIG. 4 is a schematic diagram of a pricing request response apparatus according to a fourth embodiment of the present application;
fig. 5 is a schematic view of an electronic device provided in this application embodiment five.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be further noted that, for the convenience of description, only some of the structures related to the present application are shown in the drawings, not all of the structures.
Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the steps as a sequential process, many of the steps can be performed in parallel, concurrently or simultaneously. In addition, the order of the steps may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Example one
Fig. 1 is a flowchart of a pricing request response method according to an embodiment of the present application. The embodiment of the application can be applied to the situation that the pricing result matched with the pricing request is determined according to the pricing request of the client. The method can be executed by a pricing request responding device, which can be realized by software and/or hardware, and is specifically configured in an electronic device, which can be a mobile terminal or a fixed terminal.
Referring to fig. 1, a method for responding to a pricing request provided in an embodiment of the present application includes:
and S110, receiving a pricing request of the client, and determining the category of the client according to the pricing request.
The pricing request of the client refers to that when the client (including enterprises, individuals and the like) transacts business in a financial institution, the client needs to initiate a pricing request to the financial institution for transacted commercial bank products. After receiving a pricing request initiated by a client, a financial institution needs to measure and calculate the price of a commercial bank product in the pricing request.
In this embodiment, the customer's pricing request may include information about the customer itself (e.g., the customer's name) and information about the commercial bank product (e.g., the product type) to be priced.
The category of the client is that the client is divided through preset index characteristics, so that the client can be divided into a plurality of different categories.
According to the method and the system, different pricing strategies are adopted in consideration of the obvious difference of the clients in the aspects of profit contribution degree, product requirements, cooperation prospect and the like of financial institutions. Therefore, when pricing is carried out on the customer, the category of the customer is firstly identified, and after the category of the customer is determined, different commercial bank product prices are determined for the customer according to different categories of the customer.
Alternatively, the customer's pricing request may be a loan pricing request or a deposit pricing request.
Specifically, if the pricing request of the client is a loan pricing request, the client is a borrower, and the financial institution can obtain corresponding payment by lending funds to the borrower; if the pricing request of the client is a deposit pricing request, the client is a depositor, and the financial institution can invest funds of the depositor to obtain corresponding reward.
It will be appreciated that since the business that a customer is required to transact at a financial institution is of many forms, the customer's pricing request will accordingly be of many forms.
S120, inputting the category of the customer into a pricing parameter adaptive adjustment model according to the category of the customer to obtain an economic capital target return rate output by the pricing parameter adaptive adjustment model; the pricing parameter self-adaptive adjustment model is obtained by training according to sample data of the category of the client.
The economic capital target return rate refers to an economic capital return rate adapted to a customer category, and customers of different categories can correspond to different economic capital return rates.
The pricing parameter adaptive adjustment model refers to a pre-established optimization model, and the model can be obtained by training according to sample data of the category of the client, wherein the sample data comprises the execution interest rate of each pricing and the category of the client. And (3) self-adaptive adjustment of the model based on the pre-trained pricing parameters, and when the category of the customer is input into the model, the economic capital target return rate matched with the category of the customer can be automatically determined according to the category of the customer.
In this embodiment, a big data platform is further provided, and the big data platform can collect and store relevant information required for pricing, for example, the big data platform can collect personal information, product types, other relevant information and the like of customers, and meanwhile, the big data platform can also store historical pricing list data; in addition, the big data platform can also provide the historical pricing list data of stock for the given price parameter self-adaptive adjustment model regularly, so as to realize the training and the updating of the model.
It can be understood that the general means for obtaining the optimal economic return on capital is to adopt a plurality of times of manually adjusting the parameters to obtain the economic return on capital, and a great amount of manpower and material resources are consumed in the process of continuously adjusting the parameters. Therefore, a pricing parameter adaptive adjustment model can be trained based on a large amount of sample data, so that the economic capital target return rate matched with the client category can be automatically determined according to the client category.
In this embodiment, as for a specific determination process of the pricing parameter adaptive adjustment model, the following embodiment will explain this in detail.
And S130, determining a calculation result of the pricing request by adopting a preset pricing method according to the economic capital target return rate and the pricing additional information.
Wherein, the pricing additional information refers to other information related to pricing of the commercial bank products besides the economic capital target return rate.
When the pricing is carried out on the commercial bank products, the influence factors such as cost, benefit, operation, risk and tax are considered, and therefore the pricing additional information of the method comprises information such as capital cost rate, operation cost rate, risk cost rate and tax rate.
In this embodiment, considering that the commercial banking product business may bring certain risks, the economic capital occupation meter must be referred to the product pricing to ensure that the business' capital return rate reaches the minimum requirement, that is, the calculated economic capital return rate is multiplied by the economic capital occupation to obtain the capital return rate, so as to calculate the final price of the product according to the capital return rate.
Optionally, if the pricing request is a loan pricing request, determining the calculation result of the pricing request is to determine the loan interest rate of the loan; or if the pricing request is a deposit pricing request, determining the calculation result of the pricing request as determining the deposit interest rate of the deposit.
Specifically, loan pricing refers to the loan interest rate which is comprehensively determined by a financial institution according to the own capital cost, loan expense, loan risk and profit targets, the loan capital supply and demand conditions, the customer cooperation relationship and other factors; deposit pricing refers to comprehensively determining the deposit interest rate after a financial institution comprehensively analyzes factors such as the attraction of the deposit interest rate to depositors, the bearing capacity, the fund use, the profit capacity and the fund price trend of the financial institution and the like on the premise of an operation target.
It will be appreciated that determining an appropriate price for a commercial bank product is extremely important to the profitability, competitiveness, market share, future development, etc. of the financial institution.
In general, when pricing commercial bank products, the sampled pricing methods may include a benchmark interest rate additive pricing method, a customer profitability analysis pricing method, and a cost additive pricing method. According to different pricing strategies, a corresponding appropriate pricing method can be selected. The pricing method is not limited in selection, and the specific preset pricing method can be selected according to actual conditions.
Typically, the preset pricing method is a cost-plus pricing method.
Specifically, when the price is determined by using the cost-added pricing method, various capital costs, operating costs and risk costs of commercial bank products need to be measured and calculated, corresponding tax situations need to be considered, and after the pricing additional information is converted into corresponding interest rates, the deposit interest rate or loan interest rate of the financial institution within the budget period needs to be calculated by adding the capital cost rate, the operating cost rate, the risk cost rate and the tax rate and finally adding the capital return rate expected by the financial institution.
It can be understood that, from the perspective of making a profit for a financial institution, the embodiment of the present application adopts a cost-added pricing method to price commercial bank products, and meanwhile, the cost-added pricing method is simple and easy to implement, and data required by pricing are also easy to obtain.
According to the embodiment, after a calculation result matched with the pricing request is determined according to the pricing request of a client, newly generated pricing information is stored in a big data platform for storage.
The method comprises the steps of receiving a pricing request of a client, and determining the category of the client according to the pricing request; inputting the category of the customer into a pricing parameter adaptive adjustment model according to the category of the customer to obtain an economic capital target return rate output by the pricing parameter adaptive adjustment model; the pricing parameter self-adaptive adjustment model is obtained by training according to sample data of the category of a client; then, determining a calculation result of the pricing request by adopting a preset pricing method according to the economic capital target return rate and the pricing additional information; by the technical scheme, the economic capital return rate parameter adaptive to the client category is automatically acquired according to the client category based on the predetermined pricing parameter adaptive adjustment model, manual parameter adjustment is avoided, and the pricing result matched with the pricing request can be automatically determined according to the pricing request of the client.
Example two
Fig. 2 is a flowchart of a pricing request response method according to a second embodiment of the present application, and the present embodiment is an optimization of the foregoing solution based on the foregoing embodiment.
Further, the determination process of the category of the customer is specifically detailed, and the detailed process is detailed as that the personal information of the customer is acquired from a business database according to the customer identification in the pricing request; and acquiring product information of the product from the service database according to the product identifier in the pricing request; and inputting the personal information and the product information into a preset customer classification model to obtain the category of the customer so as to complete the determination process of the category of the customer.
Wherein explanations of the same or corresponding terms as those of the above-described embodiments are omitted.
Referring to fig. 2, the method for responding to a pricing request provided in this embodiment includes:
s210, receiving a pricing request of a client, and acquiring personal information of the client from a business database according to a client identifier in the pricing request; and acquiring product information of the product from the business database according to the product identifier in the pricing request.
The business database is a database related to business banking, and personal information related to the customer, historical pricing information of the customer, business banking information, and the like are stored in the business data.
In this embodiment, the client identifier may be composed of a preset number (e.g., 16 bits) of numbers and letters, and has uniqueness; correspondingly, the product identifier can also be formed by a preset number (such as 8 bits) of numbers and letters, and has uniqueness.
And S220, inputting the personal information and the product information into a preset customer classification model to obtain the category of the customer.
The client classification model is an optimization model for classifying the clients in the pricing request, and the client classification model can classify the clients according to preset index features.
Wherein the predetermined target characteristics can be considered and selected from the customer itself and the product to be priced itself. Generally, the index features which can be selected are various according to customers and products to be priced, and the more the index features are selected, the more detailed the customer is divided, so that the final price calculation is facilitated.
Specifically, the preset index features may include commercial banking product types (including short-term, medium-term, and long-term loans, etc.), customer size, customer property status, customer historical pricing status, and customer credit rating, etc. Taking the selected client scale index characteristics as an example, according to the client scale, the client can be classified into enterprises and personal categories, and if the client is determined to belong to the enterprise category, the client can be further classified into large-scale enterprises, general-scale enterprises and small-scale enterprises.
It can be understood that, as the index features are selected differently, the classification result for the client category is also different. The more suitable the index features are selected, the more accurate the classification and identification of the customers can be, and meanwhile, the more the number of the index features is, the clearer the portrayal of the customers can be, and the division of the customers is facilitated. However, the combination of the differentiated features in multiple dimensions results in a large data volume, so that the data processing is very slow and may generate errors.
In this embodiment, the specific selection condition of the index features (including the number of the index features and the index features) may be selected according to actual requirements, and the selection of the index features in this embodiment is not limited at all.
Typically, the customer classification model may classify the customers from four dimensions, customer size, customer region, customer credit rating, and product category.
The client scale refers to the scale of the client, for example, the client can be classified according to large-scale clients, medium-scale clients and small-scale clients; the region to which the client belongs refers to a region where the client transacts business banking product business in a financial institution, and if the client transacts business in a certain place, the region to which the client belongs is a position region where the certain place branch is located; the credit rating of the client refers to the credit rating of the client, for example, the client can be classified into three categories according to the credit rating, medium and low, and the client can be classified into three categories according to the actual service condition, and the categories are represented by symbols: AAA, AA, A, BBB, BB, B, CCC, CC, C; the product category refers to the category of commercial bank products to be priced, such as whether the products are deposit products or loan products, if the product category is loan products, the loan products can be further classified according to short-term, medium-term and long-term loans according to the time scale, and of course, the products can also be classified according to specific business conditions, such as classified classification according to fixed asset financing, flowing asset loan and real estate development loan.
The client classification model can be used for considering information of both the client and the product, classifying the client according to four dimensions of client scale, client belonging area, client credit rating and product category, accurately identifying the client, controlling the number of selected index features within a reasonable range, and avoiding large data volume caused by multi-dimensional differential feature combination.
In this embodiment, the client classification model may be a support vector machine model, a decision tree classification model, or a bayesian classification model, and the selection of a specific client classification model may be determined according to actual requirements, which is not specifically limited in this embodiment of the present application.
S230, inputting the category of the client into a pricing parameter self-adaptive adjustment model according to the category of the client to obtain an economic capital target return rate output by the pricing parameter self-adaptive adjustment model; the pricing parameter self-adaptive adjustment model is obtained by training according to sample data of the category of the client.
S240, determining a calculation result of a pricing request by adopting a preset pricing method according to the economic capital target return rate and the pricing additional information.
On the basis of the above embodiment, the embodiment of the present application specifically refines the determination process of the category of the customer, acquires the personal information of the customer from a business database according to the customer identifier in the pricing request, and acquires the product information of the product from the business database according to the product identifier in the pricing request; inputting the personal information and the product information into a preset customer classification model to obtain the category of the customer; according to the technical scheme, the information of the client and the product is considered to divide the client category, the automatic division of the client category is realized based on the preset client classification model, and the complex process of manual classification is avoided.
EXAMPLE III
Fig. 3 is a flowchart of a pricing request response method provided in the third embodiment of the present application, and the present embodiment is an optimization of the foregoing scheme based on the foregoing embodiments.
Further, the training process of the pricing parameter self-adaptive adjustment model is specifically refined into 'obtaining historical pricing list data', and at least one group of sample data is determined according to the historical pricing list data; wherein the historical pricing bill data comprises an executed interest rate of each pricing and a category of the customer; inputting the sample data to an initial model; and training based on the output result of the initial model according to a predetermined target benefit evaluation function to obtain the pricing parameter self-adaptive adjustment model so as to perfect the determination process of the pricing parameter self-adaptive adjustment model.
Wherein explanations of the same or corresponding terms as those of the above-described embodiments are omitted.
Referring to fig. 3, the method for responding to a pricing request provided in this embodiment includes:
s310, receiving a pricing request of the client, and determining the category of the client according to the pricing request.
S320, obtaining historical pricing list data, and determining at least one group of sample data according to the historical pricing list data; wherein the historical pricing bill data includes the executed interest rate of each pricing and the category of the customer.
The historical pricing list data can be obtained from a big data storage platform regularly, and can be used as training or initial data for solving economic capital target return rate parameters through obtaining of the historical pricing list data.
The execution interest rate of the pricing refers to the interest rate of the pricing list in actual execution, namely the real interest rate.
Optionally, before obtaining historical pricing schedule data and determining at least one set of sample data from the historical pricing schedule data, the method further comprises: determining a pricing mode of the user according to user input data; and searching a target benefit evaluation function matched with the pricing mode from a pre-established mapping table according to the mapping relation between the pricing mode and the benefit evaluation function.
The user input data may be input data with the pricing total passing rate as the main pricing demand, or may also be input data with the economic capital target total rate of return and the pricing total passing rate balanced as the pricing demand.
In the mapping table pre-established in this embodiment, at least one set of pricing method and benefit evaluation function is stored according to the mapping relationship between the pricing method and the benefit evaluation function, and after the pricing method of the user is determined, the target benefit evaluation function matched with the pricing method can be searched in the mapping table according to the pricing method of the user.
It can be understood that, when pricing is performed, a user can determine a proper pricing mode according to the pricing requirement of the user, so that a target benefit evaluation function matched with the pricing mode is found out according to the pricing mode, and further, training and generation of a subsequent pricing parameter self-adaptive adjustment model can be guided according to the target benefit evaluation function.
Optionally, the benefit evaluation function comprises a first benefit evaluation function, a second benefit evaluation function and a third benefit evaluation function.
Specifically, the benefit evaluation function can be divided into the above three different benefit evaluation functions according to different function types, wherein the first benefit evaluation function is associated with the user input data with the economic capital target overall rate of return as the main pricing requirement, the second benefit evaluation function is associated with the user input data with the pricing overall rate as the main pricing requirement, and the third benefit evaluation function is associated with the user input data with the equilibrium economic capital target overall rate of return and the pricing overall rate as the pricing requirement.
It can be understood that the current pricing method cannot timely evaluate the influence of the adjusted economic return on the price and benefit of all financial institutions, and cannot timely convert the adjusted economic return into production parameters. Therefore, the method reasonably estimates the result after parameter adjustment by adopting different angle metering methods through various different benefit evaluation functions, and can feed back and adjust the economic capital return rate parameters according to the result after parameter adjustment.
Accordingly, the first benefit assessment function in embodiments of the present application is associated with the economic capital target overall rate of return; the second benefit assessment function is associated with a pricing overall pass rate; the third benefit assessment function is associated with an economic capital target overall rate of return and a pricing overall rate of passage.
For example, the first benefit assessment function may be represented by F1(X1, X2, …, Xn) ═ F1 (economic capital target overall rate of return); the second benefit assessment function may be represented by F2(X1, X2, …, Xn) ═ Lg (1/(N% -F2 (pricing total passage rate)); the third benefit evaluation function may be represented by F3(X1, X2, …, Xn) ═ SUM ((economic capital target overall rate of return) × F3 (pricing overall rate of pass)).
Where Xn represents the economic capital target return rate corresponding to the customer category n; n is expressed as the total price list number; f1, f2, and f3 may be polynomial functions, such as univariate linear functions; the economic capital target total return rate is avg (return rate per pricing), and the pricing total passing rate is the number of passing price list/total number of passing price list.
In this embodiment, whether each pricing order passes the pricing requirement or not may be determined according to a difference between the executed interest rate and the target interest rate of each pricing order, and if the actual executed interest rate of the pricing order is greater than the target interest rate, it is determined that the pricing order passes the pricing requirement. Wherein the target interest rate can be calculated according to the operation cost rate, the expected loss rate, the economic capital occupancy rate, the capital cost rate, the economic profit rate, the income tax rate and the business tax and the additional rate of each pricing list.
It should be noted that, the first benefit evaluation function, the second benefit evaluation function, and the third benefit evaluation function may also be subjected to corresponding function replacement and function combination, so as to obtain a new benefit evaluation function, for example, the first benefit evaluation function may be replaced by a logarithmically related function, or a combination of the first benefit evaluation function and the second benefit evaluation function may also be used as a final target benefit evaluation function.
And S330, inputting the sample data into the initial model.
The initial model refers to an untrained initial pricing parameter adaptive adjustment model.
And S340, training based on the output result of the initial model according to a predetermined target benefit evaluation function to obtain a pricing parameter self-adaptive adjustment model.
Optionally, the pricing parameter adaptive adjustment model further comprises an overall economic profit margin constraint; the constraint condition is used to determine the economic capital target rate of return when the pricing parameter adaptive adjustment model is conditioned to meet an overall economic profitability constraint.
The overall economic profit margin refers to the overall profit requirement of the financial institution.
It can be understood that by setting the overall economic profit margin constraint condition for the pricing parameter adaptive adjustment model, the economic capital target return rate can be determined by the model on the premise of meeting the overall economic profit margin constraint. If the model calculated economic capital target return cannot meet the overall economic profit margin requirement, the calculated economic capital target return cannot be accepted.
In this embodiment, according to the category of the customer, there are many model optimization algorithms for determining the economic capital target return rate for the customer, including a particle swarm algorithm, a genetic algorithm, a simulated annealing algorithm, and the like, and the selection of a specific optimization algorithm may be selected according to actual requirements.
Typically, the training algorithm of the pricing parameter adaptive adjustment model is a genetic algorithm.
Specifically, when the economic capital target return rate output by the model is solved by using a genetic algorithm, an initial economic capital return rate can be correspondingly set for each category of the customer, and the initial economic capital return rate is used as an initial solution of the model, for example, the initial solution can be represented by (X1, X2, …, Xn); meanwhile, according to the number m of the population in the genetic algorithm, a set of initial population solutions can be obtained, such as the solution can be expressed by { (X01, X02, …, X0 n); (X11, X12, …, X1 n); …, respectively; (Xm1, Xm2, …, Xmn) }; in the search evolution process of the genetic algorithm, the quality of a solution is evaluated through a benefit evaluation function and is used as a basis for subsequent genetic operation.
Referring to Table 1, exemplary customer category versus economic capital target return rate is given.
TABLE 1
| Customer area | Size of customer | Credit rating | Product classification | Client categories | Economic capital target rate of return |
| A1 | B1 | C1 | D1 | P1 | X1 |
| A2 | B2 | C2 | D2 | P2 | X2 |
| … | … | … | … | … | … |
| A3 | B3 | C3 | D3 | P3 | Xn |
It can be understood that the simulation of the genetic algorithm on the evolution process (mating, gene mutation, and vicious) of the natural life can find the optimal solution or the approximate optimal solution of the problem through continuous iterative evolution.
In consideration of the existing economic capital target rate of return parameter, the financial institution's capital rate of return parameter is configured as a whole. However, the actual situation is that the economic development level of different regions is different, and the total economic profit margin obtained for commercial bank products is also different.
The embodiment of the application can also receive a parameter manually set by a user, such as a preference setting parameter, and the preference setting parameter can be the regional target economic capital overall return rate. The regional target economic capital overall return rate means that different overall economic profit rates can be set for customers in different regions. Specifically, the initial regional target economic capital overall rate of return in the pricing parameter adaptive adjustment model is updated according to the regional target economic capital overall rate of return input by the user.
The initial regional target economic capital overall return rate is a pricing parameter, model parameters of a model default are adjusted in a self-adaptive mode, and the model parameters can be updated according to input information of a subsequent user.
Referring to Table 2, the target economic capital overall rate of return for different zones is shown by way of example.
Table 2:
| long triangular region (Jiangsu, Shanghai and Zhejiang) | 4％ |
| Pearl triangular region (Guangdong, Shenzhen) | 3.9％ |
| Northeast region | 1.5％ |
It should be noted that the data given in table 2 are only examples and do not constitute a specific definition of the regional target economic capital overall rate of return for the application, and the specific regional target economic capital overall rate of return may be set according to practical situations.
It can be understood that the parameters are configured differently according to different regions, so as to realize the differential control of the overall target interest rate requirement of the commercial bank product, thereby meeting the personalized requirements in pricing management.
S350, inputting the category of the client into the pricing parameter self-adaptive adjusting model according to the category of the client to obtain the economic capital target return rate output by the pricing parameter self-adaptive adjusting model; the pricing parameter self-adaptive adjustment model is obtained by training according to sample data of the category of the client.
And S360, determining a calculation result of the pricing request by adopting a preset pricing method according to the economic capital target return rate and the pricing additional information.
On the basis of the embodiment, the training process of the pricing parameter self-adaptive adjustment model is specifically refined, and at least one group of sample data is determined according to historical pricing list data by acquiring the historical pricing list data; wherein the historical pricing bill data comprises an executed interest rate of each pricing and a category of the customer; inputting the sample data to an initial model; training based on the output result of the initial model according to a predetermined target benefit evaluation function to obtain the pricing parameter self-adaptive adjustment model; by the technical scheme, the initial model is trained and solved based on sample data determined by historical pricing bill data, and the trained pricing parameter self-adaptive adjusting model is finally obtained.
Example four
Fig. 4 is a schematic structural diagram of a pricing request response apparatus according to a fourth embodiment of the present application. Referring to fig. 4, an apparatus for responding to a pricing request provided in an embodiment of the present application includes: a customer category determination module 410, a rate of return determination module 420, and a pricing result determination module 430.
A client category determining module 410, configured to receive a pricing request of a client, and determine a category of the client according to the pricing request;
a return rate determining module 420, configured to input the category of the customer into a pricing parameter adaptive adjustment model according to the category of the customer, so as to obtain an economic capital target return rate output by the pricing parameter adaptive adjustment model; the pricing parameter self-adaptive adjustment model is obtained by training according to sample data of the category of a client;
and a pricing result determining module 430, configured to determine a calculation result of the pricing request by using a preset pricing method according to the economic capital target return rate and the pricing additional information.
The method comprises the steps of receiving a pricing request of a client, and determining the category of the client according to the pricing request; inputting the category of the customer into a pricing parameter adaptive adjustment model according to the category of the customer to obtain an economic capital target return rate output by the pricing parameter adaptive adjustment model; the pricing parameter self-adaptive adjustment model is obtained by training according to sample data of the category of a client; then, determining a calculation result of the pricing request by adopting a preset pricing method according to the economic capital target return rate and the pricing additional information; by the technical scheme, the economic capital return rate parameter adaptive to the client category is automatically acquired according to the client category based on the predetermined pricing parameter adaptive adjustment model, manual parameter adjustment is avoided, and the pricing result matched with the pricing request can be automatically determined according to the pricing request of the client.
Further, if the pricing request is a loan pricing request, determining the calculation result of the pricing request as the loan interest rate of the loan; or if the pricing request is a deposit pricing request, determining the calculation result of the pricing request as determining the deposit interest rate of the deposit.
Further, the preset pricing method is a cost addition pricing method.
Further, the customer category determination module 410 includes:
the information acquisition unit is used for acquiring personal information of the client from a service database according to the client identification in the pricing request; and acquiring product information of the product from the service database according to the product identifier in the pricing request;
and the customer category determining unit is used for inputting the personal information and the product information into a preset customer classification model to obtain the category of the customer.
Further, the customer classification model divides the customers from four dimensions of customer scale, customer affiliated area, customer credit rating and product category.
Further, the rate of return determination module 420 includes:
the sample data determining unit is used for acquiring historical pricing list data and determining at least one group of sample data according to the historical pricing list data; wherein the historical pricing bill data comprises an executed interest rate of each pricing and a category of the customer;
a data input unit for inputting the sample data to an initial model;
and the model training unit is used for training based on the output result of the initial model according to a predetermined target benefit evaluation function to obtain the pricing parameter self-adaptive adjustment model.
Further, the rate of return determination module 420 further includes:
the pricing mode determining unit is used for determining the pricing mode of the user according to user input data before acquiring historical pricing list data and determining at least one group of sample data according to the historical pricing list data;
and the target benefit evaluation function determining unit is used for searching a target benefit evaluation function matched with the pricing mode from a pre-established mapping table according to the mapping relation between the pricing mode and the benefit evaluation function.
Further, the benefit evaluation function includes a first benefit evaluation function, a second benefit evaluation function, and a third benefit evaluation function.
Further, the first benefit assessment function is associated with the economic capital target overall rate of return; the second benefit assessment function is associated with a pricing overall pass rate; the third benefit assessment function is associated with an economic capital target overall rate of return and a pricing overall rate of passage.
Further, the pricing parameter adaptive adjustment model also comprises an overall economic profit margin constraint condition; the constraint condition is used to determine the economic capital target rate of return when the pricing parameter adaptive adjustment model is conditioned to meet an overall economic profitability constraint.
Further, the training algorithm of the pricing parameter adaptive adjustment model is a genetic algorithm.
Further, the rate of return determination module 420 further includes:
and the parameter adjusting unit is used for updating the initial regional target economic capital overall rate of return in the pricing parameter adaptive adjustment model according to the regional target economic capital overall rate of return input by the user.
The pricing request response device provided by the embodiment of the application can execute the pricing request response method provided by any embodiment of the application, and has corresponding functional modules and beneficial effects of the execution method.
EXAMPLE five
Fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present disclosure, and as shown in fig. 5, the electronic device includes a processor 510, a memory 520, an input device 530, and an output device 540.
The number of the processors 510 in the device may be one or more, and one processor 510 is taken as an example in fig. 5; the processor 510, the memory 520, the input device 530 and the output device 540 of the apparatus may be connected by a bus or other means, as exemplified by the bus connection in fig. 5.
Wherein the input device 530 is used for receiving a pricing request of a customer.
And the output device 540 is used for outputting the pricing result.
The memory 520 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data region may store data created according to the use of the terminal, etc. (pricing results, sample data, pricing parameter adaptive adjustment model, economic capital target return rate, pricing additional information, calculation results of pricing request, etc. as in the above embodiments). Further, the memory 520 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 520 may further include memory located remotely from processor 510, which may be connected to devices through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 530 may be used to receive input numeric or character information and generate key signal inputs related to customer settings and function control of the apparatus. The output device 540 may include a display device such as a display screen.
EXAMPLE six
A sixth embodiment of the present application further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a method for responding to pricing requests, the method comprising:
receiving a pricing request of a client, and determining the category of the client according to the pricing request;
inputting the category of the customer into a pricing parameter adaptive adjustment model according to the category of the customer to obtain an economic capital target return rate output by the pricing parameter adaptive adjustment model; the pricing parameter self-adaptive adjustment model is obtained by training according to sample data of the category of a client;
and determining a calculation result of the pricing request by adopting a preset pricing method according to the economic capital target return rate and the pricing additional information.
From the above description of the embodiments, it is obvious for those skilled in the art that the present application can be implemented by software and necessary general hardware, and certainly can be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods described in the embodiments of the present application.
It should be noted that, in the embodiment of the apparatus for responding to a pricing request, the included units and modules are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only used for distinguishing one functional unit from another, and are not used for limiting the protection scope of the application.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present application and the technical principles employed. It will be understood by those skilled in the art that the present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the application. Therefore, although the present application has been described in more detail with reference to the above embodiments, the present application is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the appended claims.
Claims (15)
1. A method for responding to a pricing request, comprising:
receiving a pricing request of a client, and determining the category of the client according to the pricing request;
inputting the category of the customer into a pricing parameter adaptive adjustment model according to the category of the customer to obtain an economic capital target return rate output by the pricing parameter adaptive adjustment model; the pricing parameter self-adaptive adjustment model is obtained by training according to sample data of the category of a client;
and determining a calculation result of the pricing request by adopting a preset pricing method according to the economic capital target return rate and the pricing additional information.
2. The method according to claim 1, wherein if the pricing request is a loan pricing request, the determining the calculation result of the pricing request is to determine a loan interest rate of the loan;
alternatively, the first and second electrodes may be,
and if the pricing request is a deposit pricing request, determining the deposit interest rate of the deposit according to the calculation result of the pricing request.
3. The method of claim 1, wherein the category of the customer is determined according to the following:
according to the client identification in the pricing request, acquiring personal information of the client from a service database; and acquiring product information of the product from the service database according to the product identifier in the pricing request;
and inputting the personal information and the product information into a preset customer classification model to obtain the category of the customer.
4. The method of claim 3, wherein the customer classification model classifies the customers from four dimensions, customer size, customer territory, customer credit rating, and product category.
5. The method of claim 1, wherein the training process of the pricing parameter adaptive adjustment model comprises:
obtaining historical pricing list data, and determining at least one group of sample data according to the historical pricing list data; wherein the historical pricing bill data comprises an executed interest rate of each pricing and a category of the customer;
inputting the sample data to an initial model;
and training based on the output result of the initial model according to a predetermined target benefit evaluation function to obtain the pricing parameter self-adaptive adjustment model.
6. The method of claim 5, wherein prior to obtaining historical pricing schedule data and determining at least one set of sample data from the historical pricing schedule data, the method further comprises:
determining a pricing mode of the user according to user input data;
and searching a target benefit evaluation function matched with the pricing mode from a pre-established mapping table according to the mapping relation between the pricing mode and the benefit evaluation function.
7. The method of claim 5, wherein the pricing parameter adaptive adjustment model further comprises an overall economic profit margin constraint;
the constraint condition is used to determine the economic capital target rate of return when the pricing parameter adaptive adjustment model is conditioned to meet an overall economic profitability constraint.
8. The method according to claim 5, wherein the training algorithm of the pricing parameter adaptive adjustment model is a genetic algorithm.
9. The method of claim 5, further comprising:
and updating the initial regional target economic capital overall rate of return in the pricing parameter adaptive adjustment model according to the regional target economic capital overall rate of return input by the user.
10. The method of claim 6, wherein the benefit evaluation function comprises a first benefit evaluation function, a second benefit evaluation function, and a third benefit evaluation function.
11. The method of claim 10, wherein the first benefit assessment function is associated with the economic capital target overall rate of return; the second benefit assessment function is associated with a pricing overall pass rate; the third benefit assessment function is associated with an economic capital target overall rate of return and a pricing overall rate of passage.
12. The method of claim 1, wherein the pre-set pricing method is a cost-additive pricing method.
13. An apparatus for responding to a pricing request, comprising:
the client category determining module is used for receiving a pricing request of a client and determining the category of the client according to the pricing request;
the return rate determining module is used for inputting the category of the customer into a pricing parameter adaptive adjustment model according to the category of the customer to obtain an economic capital target return rate output by the pricing parameter adaptive adjustment model; the pricing parameter self-adaptive adjustment model is obtained by training according to sample data of the category of a client;
and the pricing result determining module is used for determining the calculation result of the pricing request by adopting a preset pricing method according to the economic capital target return rate and the pricing additional information.
14. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method of responding to pricing requests according to any of claims 1-12.
15. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a method of responding to a pricing request according to any of claims 1-12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110347748.9A CN112950287A (en) | 2021-03-31 | 2021-03-31 | Pricing request response method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110347748.9A CN112950287A (en) | 2021-03-31 | 2021-03-31 | Pricing request response method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112950287A true CN112950287A (en) | 2021-06-11 |
Family
ID=76231379
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110347748.9A Pending CN112950287A (en) | 2021-03-31 | 2021-03-31 | Pricing request response method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112950287A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113724069A (en) * | 2021-08-31 | 2021-11-30 | 平安科技（深圳）有限公司 | Pricing method and device based on deep learning, electronic equipment and storage medium |
-
2021
- 2021-03-31 CN CN202110347748.9A patent/CN112950287A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113724069A (en) * | 2021-08-31 | 2021-11-30 | 平安科技（深圳）有限公司 | Pricing method and device based on deep learning, electronic equipment and storage medium |
| CN113724069B (en) * | 2021-08-31 | 2024-02-13 | 平安科技（深圳）有限公司 | Deep learning-based pricing method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020143341A1 (en) | Blockchain architecture-based warehouse receipt pledge financing assessment method and device | |
| CN101138004A (en) | Stock portfolio selecting device, stock portfolio selecting method, and stock portfolio selecting program | |
| Jiang et al. | Influencing factors for predicting financial performance based on genetic algorithms | |
| CN110675029A (en) | Dynamic management and control method and device for commercial tenant, server and readable storage medium | |
| Sklavos et al. | The liquidity of energy stocks | |
| US20240054461A1 (en) | Systems and methods for routing electronic transactions using predicted authorization approval | |
| WO2020057659A1 (en) | A computer implemented method for compiling a portfolio of assets | |
| Gourieroux et al. | Value at risk | |
| Boguslauskas et al. | The selection of financial ratios as independent variables for credit risk assessment | |
| US20230419323A1 (en) | Systems and methods for routing electronic transactions using network simulation and forecasting | |
| Pinto et al. | Strategic participation in competitive electricity markets: Internal versus sectorial data analysis | |
| Oricchio et al. | SME funding: the role of shadow banking and alternative funding options | |
| Bach et al. | Selection of variables for credit risk data mining models: preliminary research | |
| CN114782169A (en) | Customer attrition rate early warning method and device | |
| CN112950287A (en) | Pricing request response method, device, equipment and storage medium | |
| Mokhova et al. | A survey of external and internal factors influencing the cost of equity: The case of Czech companies | |
| Liu et al. | A multi-agent simulation of investment choice in the P2P lending market with bankruptcy risk | |
| Alfonso-Sánchez et al. | Optimizing credit limit adjustments under adversarial goals using reinforcement learning | |
| CA3081254C (en) | Data conversion and distribution systems | |
| CN115221212A (en) | Fund investment data management system and method | |
| Sorkhi et al. | Measuring short-term risk of initial public offering of equity securities: a hybrid Bayesian and Data-Envelopment-Analysis-based approach | |
| Wang et al. | Does the Relative Importance of the Push and Pull Factors of Foreign Capital Flows Vary Across Quantiles? | |
| Hin et al. | Computation of the implied discount rate and volatility for an overdefined system using stochastic optimization | |
| Guillou et al. | Markup Heterogeneity, export StatuS and tHe eStabliSHMent of tHe euro | |
| Cleophas et al. | Modeling strategic customers using simulations-with examples from airline revenue management |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |