CN115439208A - Client dynamic pricing method based on client credit - Google Patents
Client dynamic pricing method based on client credit Download PDFInfo
- Publication number
- CN115439208A CN115439208A CN202210915325.7A CN202210915325A CN115439208A CN 115439208 A CN115439208 A CN 115439208A CN 202210915325 A CN202210915325 A CN 202210915325A CN 115439208 A CN115439208 A CN 115439208A
- Authority
- CN
- China
- Prior art keywords
- product
- customer
- information
- client
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000012216 screening Methods 0.000 claims abstract description 66
- 238000005457 optimization Methods 0.000 claims abstract description 16
- 238000013210 evaluation model Methods 0.000 claims abstract description 14
- 230000004044 response Effects 0.000 claims description 58
- 230000000694 effects Effects 0.000 claims description 32
- 238000000605 extraction Methods 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000005065 mining Methods 0.000 claims description 6
- 230000009286 beneficial effect Effects 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 230000004931 aggregating effect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000013058 risk prediction model Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G06Q30/0283—Price estimation or determination
Landscapes
- Business, Economics & Management (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a client dynamic pricing method based on client credit, which comprises the following steps: s1: acquiring a product to be priced, related user information and related product information; s2: screening out a target customer group based on the related user information and the related product information; s3: determining a risk coefficient based on historical behavior information and a credit evaluation model of each target client in the target client group; s4: constructing a target function which takes the price as a variable and corresponds to each target client; s5: solving an optimal solution of the objective function when the constraint condition is met, and taking the optimal solution of the objective function as the final pricing of the corresponding objective client; the method is used for screening a target customer group according to different products, predicting the risk of the customer by using a prediction model, simultaneously constructing a business objective function of the customer under different prices, and solving the maximization of the objective function under the limiting condition meeting a business strategy through optimization so as to calculate the pricing of the objective function with the best price of one customer.
Description
Technical Field
The invention relates to the technical field of dynamic pricing, in particular to a client dynamic pricing method based on client credit.
Background
At present, in the traditional credit card industry, the pricing of products is mostly related to market competition, own capital cost and risk cost, the conditions of each client and the overall efficiency of a bank cannot be considered to be optimal when the prices are established, a 'cutting' pricing mode is often adopted, so that some clients with high cost enjoy low price, and the clients with low cost and good quality need to accept high price for the purchase orders of the clients. With the increasing market competition severity, the bank credit card stock is in poor operation, so that customers have other better choices, and the retained customers have profits for eating the banks. The existing pricing methods in the credit card industry include the following methods:
1. referring to the same industry, the pricing is unified, and the pricing mode only considers market competition but ignores the cost of the pricing mode.
2. The method is combined with the cost addition method of a credit card mechanism, but the method can cause high pricing due to high bank asset price or high risk cost, and causes weak market promotion due to lack of market competitiveness, so that the market share can be influenced.
3. The bank conducts customer pricing in a differentiated mode, but the differentiated means is not data-driven, and on the basis of benchmark pricing, the mode is subjective and cannot timely respond to and adjust pricing strategies according to actual data through manual experience.
In the prior art, only manual judgment is carried out, or service KPI (key performance indicator) targeted discount or pricing is carried out, for example, in order to pursue credit card staging balance in the prior service KPI, the whole member is discounted in the period of time of the staging product or the whole member of part of inactive customer groups is discounted, large customer group management is divided, the single price cannot be achieved due to rough mode, only the single balance KPI can be considered, other indexes must be sacrificed when the single KPI is pursued, and the whole net profit of a bank cannot be considered and balanced. In summary, the pricing of all product lines of the credit card in the current credit card industry stays in the stage of 'manual workshop', the existing data cannot be used for refining one customer, and the optimal pricing cannot be accurately given.
Therefore, the invention provides a client dynamic pricing method based on client credit.
Disclosure of Invention
The invention provides a client dynamic pricing method based on client credit, which is used for screening clients capable of handling pricing according to different products, providing client handling and risk prediction by using a prediction model, calculating business objective functions of the clients under different prices through an elastic model generated by historical behavior data, and solving the maximization of the objective function under the limiting condition meeting business strategies through an optimization tool, thereby calculating the pricing of one client and one price with the optimal objective function.
The invention provides a client dynamic pricing method based on client credit, which comprises the following steps:
s1: acquiring a product to be priced and related user information and related product information of the product to be priced;
s2: screening out a target customer group based on the related user information and the related product information;
s3: determining credit score of each target client based on historical behavior information and a credit evaluation model of each target client in the target client group, and determining a risk coefficient based on the credit score;
s4: constructing an objective function which takes the price as a variable and corresponds to each target client based on the risk coefficient of each target client, the response data under different prices and the capital cost of the product to be priced;
s5: and solving the optimal solution of the objective function when the constraint conditions are met, and taking the optimal solution of the objective function as the final pricing of the corresponding objective client.
Preferably, in the client dynamic pricing method based on client credit, S1: the method for acquiring the product to be priced and the related user information and the related product information of the product to be priced comprises the following steps:
s101: acquiring historical transaction information of a prediction client group of the products to be priced as related user information;
s102: and acquiring the transaction amount, the staging item information and the user historical activity information of the product to be priced as related product information.
Preferably, in the client dynamic pricing method based on client credit, S2: screening out a target customer group based on the related user information and the related product information, wherein the screening comprises the following steps:
s201: determining a first user in the user historical activity information;
s202: determining a user screening condition based on the related user information and the related product information;
s203: screening a second user from the forecast customer group based on the user screening condition;
s204: and summarizing the first user and the second user to obtain a target customer group.
Preferably, in the method for dynamically pricing the client based on the client credit, S202: determining a user screening condition based on the related user information and the related product information, including:
determining historical transaction information of a corresponding prediction client group based on the related user information, constructing a historical transaction record thread of each prediction client in the prediction client group based on the historical transaction information, summarizing the historical transaction record threads of all the prediction clients to obtain a first record thread set;
establishing a transaction activity recording thread of each historical user based on the historical user activity information, summarizing the transaction activity recording threads of all the historical users, and acquiring a second recording thread set;
determining the product attribute of the product to be priced and a corresponding product attribute range based on the related product information;
extracting part of historical transaction record threads which meet the product attribute range of each product attribute from the first record thread set, and obtaining a third record thread set of each product attribute;
extracting transaction activity record threads meeting the product attribute range of each product attribute from the second record thread set, and obtaining a fourth record thread set of each product attribute;
aligning and summarizing the third recording thread set and the fourth recording thread set according to product attributes to obtain a comprehensive thread set of each product attribute, and performing commonality extraction on transaction record information corresponding to recording threads contained in the comprehensive thread set to obtain a first commonality condition;
determining a customer group corresponding to a recording thread contained in the comprehensive thread set, and determining an associated user information attribute based on a corresponding product attribute;
extracting associated user information corresponding to the associated user information attribute of each client in the client group, and performing commonality extraction on the associated user information of each client in the client group to obtain a second commonality condition;
calling out adjacent transaction threads of recording threads contained in the comprehensive thread set, determining constraint attributes based on a first commonality condition, and extracting adjacent transaction information meeting the constraint attributes from the adjacent transaction threads;
digging out the associated information between the transaction record information and the corresponding adjacent transaction information, and carrying out comprehensive analysis on the associated information contained in the comprehensive thread set to obtain a third common condition;
summarizing the first common condition, the second common condition and the third common condition to obtain a comprehensive common condition of each product attribute;
and carrying out invisible mining on the comprehensive commonalities conditions corresponding to all product attributes of the products to be priced to obtain user screening conditions.
Preferably, the customer dynamic pricing method based on customer credit performs invisible mining on comprehensive commonness conditions corresponding to all product attributes of the product to be priced to obtain user screening conditions, and includes:
summarizing the comprehensive thread sets of all product attributes to obtain a thread total set, counting the first total number of customers corresponding to the threads meeting the comprehensive commonality condition of the corresponding product attributes in the thread total set, summarizing the predicted customer group and all historical users to obtain a customer total group, and determining the second total number of customers of the customer total group;
determining the support degree of the corresponding comprehensive commonality condition based on the first customer total number and the second customer total number;
determining a commonality threshold value based on the comprehensive commonality condition, and calculating the commonality support degree of the corresponding product attribute based on the commonality threshold value and the corresponding support degree;
screening out a first thread set of which the corresponding product attribute meets the corresponding common support degree from the total thread set;
determining an associated product attribute with the product attribute having an association rule based on a product attribute association rule list, determining an association degree between the product attribute and a corresponding associated product attribute based on the association rule, and calculating an association commonality support degree based on the association degree and the commonality support degree;
screening out a second thread set of which the product attribute meets the corresponding association commonality support degree from the thread total set;
determining customer promotion degrees corresponding to the product attributes based on a third customer total number corresponding to the first thread set and a fourth customer total number corresponding to the second thread set;
judging whether the customer promotion degrees of all the product attributes meet a customer promotion degree threshold value, if so, taking the product attribute association rule list as a final association rule list;
otherwise, determining the target product attribute with the customer lifting degree not meeting the customer lifting degree threshold value, deleting the association rule with the minimum association degree of the target product attribute to obtain a latest association rule list corresponding to the target product attribute, calculating the latest association commonality support degree based on the latest association rule list, and determining a final association rule list based on the latest association rule list until the latest customer lifting degree determined based on the latest association commonality support degree meets the customer lifting degree threshold value;
based on the latest association rule contained in the final association rule list, performing association combination on the commonality condition corresponding to the product attribute with the latest association rule in the comprehensive commonality condition to obtain a user screening condition;
wherein the common conditions are as follows: the first commonality condition or the second commonality condition or the third commonality condition.
Preferably, in the client dynamic pricing method based on client credit, S3: determining credit score of each target client based on the historical behavior information and credit evaluation model of each target client in the target client group, and determining a risk coefficient based on the credit score, wherein the method comprises the following steps:
determining credit evaluation attribute feature data corresponding to each target client based on historical behavior information of each target client in the target client group;
inputting the credit evaluation attribute feature data into the credit evaluation model to obtain a credit score of a corresponding target customer;
a risk factor is determined based on the credit score.
Preferably, in the client dynamic pricing method based on client credit, S4: constructing an objective function with price as a variable corresponding to each target client based on the risk coefficient of each target client, the response data under different prices and the capital cost of the product to be priced, wherein the objective function comprises:
based on the response prediction model, obtaining response data of each target customer under different prices;
and constructing an objective function which takes the price as a variable and corresponds to each target client based on the risk coefficient and the response data of each target client and the capital cost of the product to be priced.
Preferably, the method for dynamically pricing customers based on customer credit obtains response data of each target customer at different prices based on a response prediction model, and includes:
determining response attribute characteristic data corresponding to each target client based on the historical behavior information of each target client in the target client group;
and inputting the response attribute characteristic data into a response prediction model to obtain response data of a corresponding target client.
Preferably, in the client dynamic pricing method based on client credit, S5: solving the optimal solution of the objective function when the constraint condition is met, and taking the optimal solution of the objective function as the final pricing of the corresponding client, wherein the method comprises the following steps:
determining an optimization target of the product to be priced, determining a corresponding variable role and a solving scene based on the optimization target, and determining a constraint condition corresponding to the variable role based on the solving scene;
determining a variable range corresponding to the variable role based on the constraint condition;
and determining the optimal solution of the objective function when the variable range is met, and taking the optimal solution of the objective function as the final pricing of the corresponding customer.
Preferably, the method for dynamically pricing customers based on customer credit further comprises:
providing corresponding product items to corresponding target customers based on the final pricing, and acquiring actual handling data of the corresponding product items;
adding the actual transaction data to historical behavior information of a corresponding target client to obtain latest historical behavior information;
correcting the response prediction model based on the latest historical behavior information.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of a method for dynamic pricing of customers based on customer credit according to an embodiment of the present invention;
FIG. 2 is a flowchart of a client dynamic pricing method based on client credit according to another embodiment of the present invention;
fig. 3 is a flowchart of a client dynamic pricing method based on client credit according to another embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Example 1:
the invention provides a client dynamic pricing method based on client credit, and with reference to fig. 1, the method comprises the following steps:
s1: acquiring a product to be priced and related user information and related product information of the product to be priced;
s2: screening out a target customer group based on the related user information and the related product information;
s3: determining credit score of each target client based on historical behavior information and a credit evaluation model of each target client in the target client group, and determining a risk coefficient based on the credit score;
s4: constructing an objective function which takes the price as a variable and corresponds to each target client based on the risk coefficient of each target client, the response data under different prices and the capital cost of the product to be priced;
s5: and solving the optimal solution of the objective function when the constraint conditions are met, and taking the optimal solution of the objective function as the final pricing of the corresponding objective client.
In this embodiment, the products to be priced are, for example, the bill, transaction, and special items of credit cards.
In this embodiment, the relevant user information is historical transaction information of a predicted customer group of the product to be priced, and the like, wherein the predicted customer group is an audience customer group of the preliminarily predicted product to be priced.
In this embodiment, the related product information is transaction amount, staging item information, and user historical activity information (i.e. historical response information of the historical user of the enterprise to other products of the enterprise), where the staging item information includes: information relating to cash, transaction and special installments.
In this embodiment, the target customer group is a group formed by target customers of products to be priced screened out based on the related user information and the related product information, and customers meeting the conditions for handling the products are also screened out first.
In this embodiment, the target customer is a customer included in the target customer group.
In this embodiment, the historical behavior information is information of the target customer related to the historical transaction behavior.
In this embodiment, the credit evaluation model is a preset model for evaluating the credit condition of the user in the transaction process.
In this embodiment, the credit score is a score representing the credit condition of the corresponding client evaluated based on the credit evaluation model.
In this embodiment, the risk coefficient is a coefficient that characterizes a risk condition of the staged transaction that exists for the corresponding customer, which is predicted based on the credit score.
In this embodiment, the response data is data representing the response condition of the product to be priced of the corresponding client at different prices, and is also table data represented by 0 and 1, where 1 is used if the corresponding client will handle the product, and 0 is used if the corresponding client will not handle the product, for example, table data representing whether the corresponding client will handle the product when the discount interest rates of the credit card product are 0.01, 0.02, 0.03, 0.04, and 0.05, respectively.
In this embodiment, the capital cost is the cost of the product to be priced.
In this embodiment, the objective functions are functions that use prices as variables and are used for obtaining the optimal price, and the objective functions are all related to price factors and affect the objective function values along with the change of prices.
In this embodiment, the constraints are related to a set goal, wherein the set goal relates to at least one of product profit, size, risk, revenue, and the like.
In this embodiment, solving the optimal solution of the objective function when the constraint condition is satisfied is: and finally solving through an optimization tool according to the set optimization problem, searching for the optimization of an objective function meeting the constraint conditions, and calculating the price of each corresponding client.
In this embodiment, the final pricing is a final determined interest rate discount for the corresponding customer referring to the cash, transaction, and special periods.
The beneficial effects of the above technology are: the method comprises the steps of screening clients capable of handling pricing according to different products, providing client handling and risk prediction by using a prediction model, calculating business objective functions of the clients at different prices through an elastic model generated by historical behavior data, and solving the maximization of the objective function under the limiting condition meeting business strategies through an optimization tool, so that the pricing of the optimal objective function for one client and one price is calculated.
Example 2:
on the basis of the embodiment 1, the customer dynamic pricing method based on the customer credit is that S1: acquiring a product to be priced and related user information and related product information of the product to be priced, referring to fig. 2, including:
s101: acquiring historical transaction information of a prediction client group of the products to be priced as related user information;
s102: and acquiring the transaction amount, the staging item information and the user historical activity information of the product to be priced as related product information.
In this embodiment, the forecast client group is an audience client group of the products to be priced roughly screened out in the initial stage from all clients.
In this embodiment, the historical transaction information is historical transaction behavior information of the predicted customer group.
In this embodiment, the staging item information includes item information relating to cash staging, transaction staging, and special staging.
The beneficial effects of the above technology are: by acquiring historical transaction information of a prediction client group of a product to be priced as related user information and acquiring transaction amount, staging item information and user historical activity information of the product to be priced as related product information, an information basis is provided for subsequently screening a target client group, evaluating credit scores and danger coefficients of corresponding clients and further determining final pricing.
Example 3:
on the basis of the embodiment 2, the customer dynamic pricing method based on the customer credit is as follows, S2: screening out a target customer group based on the related user information and the related product information, referring to fig. 3, including:
s201: determining a first user in the user historical activity information;
s202: determining a user screening condition based on the related user information and the related product information;
s203: screening a second user from the predicted customer population based on the user screening condition;
s204: and summarizing the first user and the second user to obtain a target customer group.
In this embodiment, the first user is a user included in the user historical activity information.
In this embodiment, the user screening condition is a client screening condition that is determined based on the relevant user information and the relevant product information and is used for screening a target client group of a product to be priced.
In this embodiment, the second user is a user screened from the predicted customer population based on the user screening condition.
In this embodiment, the target customer group is a user group obtained by aggregating all the first users and all the second users.
The beneficial effects of the above technology are: and summarizing the first user determined based on the related user information and the second user screened out based on the user screening conditions determined based on the related user information and the related product information, and determining the target group of the dynamic pricing.
Example 4:
on the basis of the embodiment 3, the customer dynamic pricing method based on the customer credit, S202: determining a user screening condition based on the related user information and the related product information, including:
determining historical transaction information of a corresponding prediction client group based on the related user information, constructing a historical transaction record thread of each prediction client in the prediction client group based on the historical transaction information, summarizing the historical transaction record threads of all the prediction clients to obtain a first record thread set;
establishing a transaction activity recording thread of each historical user based on the user historical activity information, summarizing the transaction activity recording threads of all the historical users, and acquiring a second recording thread set;
determining the product attribute of the product to be priced and the corresponding product attribute range based on the related product information;
extracting part of historical transaction record threads meeting the product attribute range of each product attribute from the first record thread set, and obtaining a third record thread set of each product attribute;
extracting transaction activity record threads meeting the product attribute range of each product attribute from the second record thread set, and obtaining a fourth record thread set of each product attribute;
aligning and summarizing the third recording thread set and the fourth recording thread set according to product attributes to obtain a comprehensive thread set of each product attribute, and performing commonality extraction on transaction record information corresponding to recording threads contained in the comprehensive thread set to obtain a first commonality condition;
determining a customer group corresponding to a recording thread contained in the comprehensive thread set, and determining an associated user information attribute based on a corresponding product attribute;
extracting associated user information corresponding to the associated user information attribute of each client in the client group, and performing commonality extraction on the associated user information of each client in the client group to obtain a second commonality condition;
calling out adjacent transaction threads of recording threads contained in the comprehensive thread set, determining constraint attributes based on a first common condition, and extracting adjacent transaction information meeting the constraint attributes from the adjacent transaction threads;
digging out the associated information between the transaction record information and the corresponding adjacent transaction information, and carrying out comprehensive analysis on the associated information contained in the comprehensive thread set to obtain a third common condition;
summarizing the first common condition, the second common condition and the third common condition to obtain a comprehensive common condition of each product attribute;
and carrying out invisible mining on the comprehensive common conditions corresponding to all product attributes of the products to be priced to obtain user screening conditions.
In this embodiment, the historical transaction record thread is a thread that records the historical transaction process of the predicted customer.
In this embodiment, the predicted customers are customers included in the group of predicted customers.
In this embodiment, the first record thread set is a thread set obtained by summarizing the historical transaction record threads of all the predicted customers.
In this embodiment, the historical user is a user included in the user historical activity information.
In this embodiment, the transaction activity recording thread is a thread for recording historical transaction processes of historical users.
In this embodiment, the second recording thread set is a thread set obtained by summarizing the transaction activity recording threads of all the historical users.
In this embodiment, the product attribute is an attribute of the product to be priced, which is determined based on the related product information, for example: transaction amount, staging type, etc., wherein the staging type includes cash staging, transaction staging, and special staging.
In this embodiment, the product attribute range is a range corresponding to the product attribute, for example: a transaction amount range, an installment number range, etc.
In this embodiment, the partial historical transaction record threads are partial threads that extract a product attribute range satisfying each product attribute from the first record thread set.
In this embodiment, the third recording thread set is a thread set obtained by aggregating the partial threads extracted from the first recording thread set and satisfying the product attribute range of each product attribute.
In this embodiment, the fourth recording thread set is a thread set obtained after the transaction activity recording threads extracted from the second recording thread set and satisfying the product attribute range of each product attribute are summarized.
In this embodiment, the first commonality condition is a condition that all the record threads included in the integrated thread set obtained after performing commonality extraction on the transaction record information corresponding to the record threads included in the integrated thread set satisfy the condition for screening users, for example, the condition for screening users is that the transaction amounts are all over 1 ten thousand yuan.
In this embodiment, the comprehensive thread set is a thread set corresponding to the product attribute, which is obtained by summarizing the third recording thread set and the fourth recording thread set corresponding to each product attribute.
In this embodiment, the customer group is a customer set formed by summarizing customers corresponding to all record threads included in the integrated thread set.
In this embodiment, the associated user information attribute is a user information attribute related to the corresponding product attribute, for example: related to the transaction amount (product attribute) is the user annual income (user information attribute).
In this embodiment, the associated user information is the user information corresponding to the associated user information attribute of the corresponding client.
In this embodiment, the second commonality condition is a condition for screening users that the associated user information of all the clients in the client group obtained after the commonality extraction is performed on the associated user information of each client in the client group is satisfied.
In this embodiment, the neighboring transaction threads are recording threads that are adjacent to the recording threads included in the integrated thread set in the original recording thread (i.e., the historical transaction recording thread and the transaction activity recording thread).
In this embodiment, the constraint attribute is an information attribute of the first commonality constraint, for example, the constraint is that the transaction amounts are all over 1 ten thousand yuan.
In this embodiment, the adjacent transaction information is the transaction information extracted from the adjacent transaction threads that satisfy the constraint attribute (i.e., the transaction amount is satisfied) and are extracted from all the adjacent transaction threads.
In this embodiment, the association information is information that has an association relationship between the transaction record information and the adjacent transaction information, for example: transaction amount, number of installments, etc.
In this embodiment, the third commonality condition is a condition for screening users that all the associated information included in the integrated thread set obtained by comprehensively analyzing the associated information included in the integrated thread set satisfies.
In this embodiment, the comprehensive commonality condition is a condition for screening users, which is obtained by summarizing the first commonality condition, the second commonality condition, and the third commonality condition for each product attribute.
In this embodiment, the user screening condition is a final screening condition for screening the user, which is obtained by invisibly mining the comprehensive commonality conditions corresponding to all product attributes of the product to be priced.
The beneficial effects of the above technology are: the method comprises the steps of establishing corresponding recording threads by historical transaction information and user historical activity information contained in related user information, enabling data information in the transaction information to be more visual, providing convenience for subsequent determination of user screening conditions, screening and extracting the recording threads based on product attribute ranges corresponding to product attributes of products to be priced, extracting the recording threads meeting the product attribute ranges of the products to be priced, facilitating subsequent common analysis based on the extracted recording threads, further determining common conditions in the historical transaction activities meeting the product attributes of the products to be priced, extracting and screening user information of clients by means of the user information attributes associated with the product attributes, performing common analysis on extraction results, extracting common conditions of audiences of the products to be priced on the user information, determining adjacent thread constraint conditions corresponding to the products to be priced based on correlation analysis of the recording threads meeting the product attributes and the corresponding adjacent transaction threads, and finally achieving the purpose that the common characteristics in the historical transaction information, the common characteristics related to the product attributes and the user information in the user information and the transaction threads and the adjacent transaction characteristics in the transaction threads are fully considered, determining the adjacent thread constraint conditions for accurate screening of the users under the conditions for accurate product screening under the conditions of the association of the user information.
Example 5:
on the basis of embodiment 4, the customer dynamic pricing method based on customer credit invisibly mines the comprehensive commonalities conditions corresponding to all product attributes of the product to be priced to obtain the user screening conditions, and includes:
summarizing the comprehensive thread sets of all product attributes to obtain a thread total set, counting the first total number of customers corresponding to the threads meeting the comprehensive commonality condition of the corresponding product attributes in the thread total set, summarizing the predicted customer group and all historical users to obtain a customer total group, and determining the second total number of customers of the customer total group;
determining the support degree of the corresponding comprehensive commonality condition based on the first customer total number and the second customer total number;
determining a commonality threshold value of the corresponding product attribute based on the comprehensive commonality condition, and calculating the commonality support degree of the corresponding product attribute based on the commonality threshold value and the corresponding support degree;
screening out a first thread set of which the corresponding product attribute meets the corresponding commonality support degree from the thread total set;
determining an associated product attribute with the product attribute having an association rule based on a product attribute association rule list, determining an association degree between the product attribute and a corresponding associated product attribute based on the association rule, and calculating an association commonality support degree based on the association degree and the commonality support degree;
screening out a second thread set of which the product attribute meets the corresponding association commonality support degree from the thread total set;
determining customer promotion degrees corresponding to the product attributes based on a third customer total number corresponding to the first thread set and a fourth customer total number corresponding to the second thread set;
judging whether the customer promotion degrees of all the product attributes meet a customer promotion degree threshold value, if so, taking the product attribute association rule list as a final association rule list;
otherwise, determining the target product attribute with the customer lifting degree not meeting the customer lifting degree threshold value, deleting the association rule with the minimum association degree of the target product attribute to obtain a latest association rule list corresponding to the target product attribute, calculating the latest association commonality support degree based on the latest association rule list, and determining a final association rule list based on the latest association rule list until the latest customer lifting degree determined based on the latest association commonality support degree meets the customer lifting degree threshold value;
based on the latest association rule contained in the final association rule list, performing association and combination on the common conditions corresponding to the product attributes with the latest association rule in the comprehensive common conditions to obtain user screening conditions;
wherein the common conditions are as follows: the first commonality condition or the second commonality condition or the third commonality condition.
In this embodiment, the thread aggregate is an aggregate obtained by aggregating the comprehensive thread aggregates of all product attributes.
In this embodiment, the first total number of customers is a total number of customers corresponding to threads that satisfy the comprehensive commonality condition of the corresponding product attribute in the thread total set.
In this embodiment, the second customer total is the total number of customers in the customer total group obtained by summarizing the predicted customer group and all historical users.
In this embodiment, based on the first total number of customers and the second total number of customers, the support degree of the corresponding comprehensive commonality condition is determined, that is:
and taking the ratio of the first customer total number and the second customer total number as the support degree of the corresponding comprehensive commonality condition.
In this embodiment, the commonality threshold of the corresponding product attribute is determined based on the comprehensive commonality condition, which is: and the threshold values which are jointly met by the corresponding product attributes are extracted from the comprehensive commonality conditions of the corresponding product attributes.
In this embodiment, the commonality support degree of the corresponding product attribute is calculated based on the commonality threshold and the corresponding support degree, that is: and taking the product of the commonality threshold and the commonality support degree of the corresponding product attribute as the commonality support degree of the corresponding product attribute.
In this embodiment, the first thread set is a set formed by threads that have been screened from the total thread set and whose corresponding product attributes satisfy the corresponding support degree of commonality.
In this embodiment, the associated product attribute is other product attributes having association rules with the product attribute determined based on the product attribute association rule list.
In this embodiment, the product attribute association rule list is a list including association rules among product attributes.
In this embodiment, the association degree is a numerical value representing the association degree between the product attributes having the corresponding association rule, which is determined based on the association rule.
In this embodiment, calculating the association commonality support based on the association degree and the commonality support includes:
wherein d is the associated common support degree of the corresponding product attributes, n is the total number of the associated product attributes having the association rule with the corresponding product attributes, z is the common support degree of the corresponding product attributes, i is the ith associated product attribute having the association rule with the corresponding product attributes, and g i The association degree between the ith associated product attribute and the corresponding product attribute of which the association rule exists with the corresponding product attribute is defined;
for example, n is 3, the association degrees between the ith associated product attribute and the corresponding product attribute of the association rule existing with the corresponding product attribute are 0.6, 0.2 and 0.9 in turn, z is 0.05, and d is 0.16625.
In this embodiment, the second thread set is a set formed by threads of which the product attributes screened from the thread total set satisfy the corresponding association commonality support.
In this embodiment, the third total number of clients is the total number of clients corresponding to the threads included in the first thread set.
In this embodiment, the fourth total number of clients is the total number of clients corresponding to the threads included in the second thread set.
In this embodiment, determining the customer promotion degree of the corresponding product attribute based on the third customer total number corresponding to the first thread set and the fourth customer total number corresponding to the second thread set includes:
in the formula, t is the customer promotion degree corresponding to the product attribute, lg is a logarithmic function with the base of 10, a is the third customer total corresponding to the first thread set, and b is the fourth customer total corresponding to the second thread set;
for example, a is 200, b is 100, and t is 0.176.
In this embodiment, the customer promotion threshold is the minimum customer promotion corresponding to the latest association rule list as the final association rule list.
In this embodiment, it is determined whether the customer promotion degrees of all product attributes satisfy the customer promotion degree threshold, that is: and when the customer lifting degree is not less than the customer lifting degree threshold value, judging that the customer lifting degree corresponding to the product attribute meets the customer lifting degree threshold value, otherwise, judging that the customer lifting degree corresponding to the product attribute does not meet the customer lifting degree threshold value.
In this embodiment, the target product attribute is an attribute when the customer promotion degree does not satisfy the customer promotion degree threshold.
In this embodiment, the final association rule list is a product attribute association rule list corresponding to the case where the customer promotion degree satisfies the customer promotion degree threshold.
In this embodiment, the latest association rule list is an association rule list that is newly obtained after deleting an association rule with the minimum association degree with the target product attribute in the current association rule list.
In this embodiment, the latest association commonality support is the latest association commonality support calculated based on the latest association rule list.
In this embodiment, the latest customer promotion degree is the latest customer promotion degree determined based on the latest association commonality support degree.
In this embodiment, the latest association rule is an association rule included in the latest association rule list.
In this embodiment, the commonalities conditions corresponding to the product attributes having the latest association rule in the comprehensive commonalities conditions are associated and merged to obtain user screening conditions, that is:
for example: the latest association rule exists in the two comprehensive common conditions that the annual income of the customer is not less than 10 ten thousand yuan and the transaction amount is not less than 1 ten thousand yuan, so that the latest association rule is combined into the user screening condition that the annual income of the customer is not less than 10 ten thousand yuan and the transaction amount is not less than 1 ten thousand yuan.
The beneficial effects of the above technology are: the method comprises the steps of calculating support degrees corresponding to different comprehensive conditions based on the total number of customers meeting different comprehensive common conditions and the total number of customers in all samples, calculating common support degrees based on the common threshold and the support degrees of each comprehensive condition, calculating associated common support degrees based on the determined association degrees between product attributes, and screening the existing association rules among the product attributes based on the customer promotion degrees based on the total number of customers meeting the common support degrees and the total number of customers meeting the associated common support degrees, thereby determining an association rule list with good effect on the final customer promotion degrees, providing an important basis for accurately determining the user screening conditions with good customer promotion degrees subsequently, avoiding the influence of the subsequently determined user screening conditions on the customer screening effect based on the excessive association constraints among the product attributes, and ensuring the effectiveness and the screening effect of the determined user screening conditions.
Example 6:
on the basis of the embodiment 1, the customer credit-based dynamic customer pricing method comprises the following steps of S3: determining a credit score of each target client based on the historical behavior information and the credit evaluation model of each target client in the target client group, and determining a risk coefficient based on the credit score, wherein the method comprises the following steps:
determining credit evaluation attribute characteristic data corresponding to each target client based on the historical behavior information of each target client in the target client group;
inputting the credit evaluation attribute feature data into the credit evaluation model to obtain a credit score of a corresponding target customer;
a risk factor is determined based on the credit score.
In this embodiment, the credit evaluation attribute feature data is data that affects the user credit score extracted from the historical behavior information of the target client.
In this embodiment, the credit evaluation model is a preset model for evaluating the credit condition of the user in the transaction process.
In this embodiment, a risk coefficient is determined based on the credit score, that is:
the credit score is input into a risk prediction model (namely, a model for predicting the risk coefficient of the user in the transaction process) to obtain the risk coefficient.
The beneficial effects of the above technology are: credit evaluation attribute feature data influencing the credit score of the user are extracted from the historical behavior information of each target client in the target client group, the score of the credit condition of the target client in the historical transaction process is evaluated by combining a credit evaluation model, the risk coefficient is further determined, and a data basis is provided for achieving targeted dynamic pricing based on client credit subsequently.
Example 7:
on the basis of the embodiment 1, the customer dynamic pricing method based on the customer credit is as follows, S4: constructing an objective function with price as a variable corresponding to each target client based on the risk coefficient of each target client, the response data under different prices and the capital cost of the product to be priced, wherein the objective function comprises:
based on the response prediction model, obtaining response data of each target customer at different prices;
and constructing an objective function which takes the price as a variable and corresponds to each target client based on the risk coefficient and the response data of each target client and the capital cost of the product to be priced.
In this embodiment, the response prediction model is a model for predicting the response condition of the user to the product to be priced at different prices.
In this embodiment, the response data is data representing a response situation of the user to the product to be priced at different prices, which is determined after the historical transaction information of the target customer is input to the response prediction model.
In this embodiment, the objective functions are functions that use prices as variables and are used for obtaining the optimal price, and the objective functions are all related to price factors and affect the objective function values along with the change of prices.
The beneficial effects of the above technology are: the risk coefficient of each target client, response data under different prices, capital cost of products to be priced and other factors are comprehensively considered, the target function corresponding to the target client is constructed, and a dynamic pricing implementation mode is provided for determining final pricing by solving the optimal solution of the target function in the follow-up process.
Example 8:
on the basis of embodiment 7, the method for dynamically pricing customers based on customer credit, based on a response prediction model, obtains response data of each target customer at different prices, and includes:
determining response attribute characteristic data corresponding to each target client based on the historical behavior information of each target client in the target client group;
and inputting the response attribute feature data into a response prediction model to obtain response data corresponding to the target client.
In this embodiment, the response attribute feature data is data extracted from the historical behavior information of the target customer and used for determining the response condition of the user when the price of the product to be priced is different.
The beneficial effects of the above technology are: response attribute feature data used for determining response conditions of users when the users treat pricing products with different prices are extracted from historical behavior information of each target client in a target client group, scores of the credit conditions of the target clients in the historical transaction process are evaluated by combining a response prediction model, and then risk coefficients are determined, and a data basis is provided for achieving targeted dynamic pricing based on client credit subsequently.
Example 9:
on the basis of the embodiment 1, in the client dynamic pricing method based on the client credit, S5: solving an optimal solution of the objective function when the constraint conditions are met, and taking the optimal solution of the objective function as the final pricing of the corresponding client, wherein the method comprises the following steps:
determining an optimization target of the product to be priced, determining a corresponding variable role and a solving scene based on the optimization target, and determining a constraint condition corresponding to the variable role based on the solving scene;
determining a variable range corresponding to the variable role based on the constraint condition;
and determining the optimal solution of the objective function when the variable range is met, and taking the optimal solution of the objective function as the final pricing of the corresponding customer.
In this embodiment, the optimization objective includes at least one of: product profit, scale, risk, revenue, etc.
In this embodiment, the variable role is, for example, a target variable, a limit variable, and the like.
In this embodiment, the solution scenario is an unlimited condition, a limited condition traversal, and the like.
In this embodiment, the constraint condition corresponding to the variable role is a constraint condition for limiting the variable, for example, the profit of the product is limited to be not less than 0.1 ten thousand yuan.
In this embodiment, the variable range corresponding to the variable role is the variable range of the constraint variable, for example, the profit of the product is not less than 0.1 ten thousand yuan.
In this embodiment, the optimal solution of the objective function is the optimal solution of the corresponding objective function when the variable range is satisfied.
The beneficial effects of the above technology are: variable roles, the limiting ranges of different variables and solving scenes are determined based on the optimization target of the product to be priced, the optimal pricing of the corresponding target client when the optimization target is met is further determined, and the pricing of one client and one price when the optimization target is met is realized.
Example 10:
on the basis of embodiment 7, the dynamic client pricing method based on client credit further includes:
providing corresponding product items to corresponding target customers based on the final pricing, and acquiring actual handling data of the corresponding product items;
adding the actual transaction data to historical behavior information of a corresponding target client to obtain latest historical behavior information;
correcting the response prediction model based on the latest historical behavior information.
In this embodiment, the product item is a credit card product item generated after determining the price of the product to be priced based on the final pricing.
In this embodiment, the actual transaction data is data representing a condition that the target client transacts the corresponding product item.
In this embodiment, the latest historical behavior information is the latest historical behavior information obtained after adding the transaction record information extracted from the actual transaction data to the historical behavior information of the corresponding target client.
In this embodiment, correcting the response prediction model based on the latest historical behavior information is: and correcting the weight of the response condition of the user under different prices determined by the influence contained in the response prediction model based on the data used for determining the response condition of the user under different prices of the product to be priced and the product attribute of the product to be priced in the latest historical behavior information, thereby realizing the correction and update of the response prediction model.
The beneficial effects of the above technology are: by tracking the actual response condition of the target user to the product item generated based on the final pricing, the response prediction model can be continuously optimized and corrected, so that the prediction result of the response prediction model is more accurate, and the dynamic pricing effect is further improved.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A method for dynamic pricing of customers based on customer credit, comprising:
s1: acquiring a product to be priced and related user information and related product information of the product to be priced;
s2: screening out a target customer group based on the related user information and the related product information;
s3: determining the credit score of each target client based on the historical behavior information and the credit evaluation model of each target client in the target client group, and determining a risk coefficient based on the credit score;
s4: constructing an objective function which takes the price as a variable and corresponds to each target client based on the risk coefficient of each target client, the response data under different prices and the capital cost of the product to be priced;
s5: and solving the optimal solution of the target function when the constraint conditions are met, and taking the optimal solution of the target function as the final pricing of the corresponding target client.
2. The method for dynamic pricing of customers based on customer credit as claimed in claim 1, wherein S1: the method for acquiring the product to be priced and the related user information and the related product information of the product to be priced comprises the following steps:
s101: acquiring historical transaction information of a prediction client group of the products to be priced as related user information;
s102: and acquiring the transaction amount, the staging item information and the user historical activity information of the product to be priced as related product information.
3. The method for dynamic customer pricing based on customer credit of claim 2, wherein S2: screening out a target customer group based on the related user information and the related product information, wherein the screening comprises the following steps:
s201: determining a first user in the user historical activity information;
s202: determining a user screening condition based on the related user information and the related product information;
s203: screening a second user from the forecast customer group based on the user screening condition;
s204: and summarizing the first user and the second user to obtain a target customer group.
4. The method for dynamic pricing of customers based on customer credit as claimed in claim 3, wherein S202: determining a user screening condition based on the related user information and the related product information, including:
determining historical transaction information of a corresponding prediction client group based on the related user information, constructing a historical transaction record thread of each prediction client in the prediction client group based on the historical transaction information, summarizing the historical transaction record threads of all the prediction clients to obtain a first record thread set;
establishing a transaction activity recording thread of each historical user based on the historical user activity information, summarizing the transaction activity recording threads of all the historical users, and acquiring a second recording thread set;
determining the product attribute of the product to be priced and a corresponding product attribute range based on the related product information;
extracting part of historical transaction record threads which meet the product attribute range of each product attribute from the first record thread set, and obtaining a third record thread set of each product attribute;
extracting transaction activity record threads meeting the product attribute range of each product attribute from the second record thread set, and obtaining a fourth record thread set of each product attribute;
aligning and summarizing the third recording thread set and the fourth recording thread set according to product attributes to obtain a comprehensive thread set of each product attribute, and performing commonality extraction on transaction record information corresponding to recording threads contained in the comprehensive thread set to obtain a first commonality condition;
determining a customer group corresponding to a recording thread contained in the comprehensive thread set, and determining an associated user information attribute based on a corresponding product attribute;
extracting associated user information corresponding to the associated user information attribute of each client in the client group, and performing commonality extraction on the associated user information of each client in the client group to obtain a second commonality condition;
calling out adjacent transaction threads of recording threads contained in the comprehensive thread set, determining constraint attributes based on a first commonality condition, and extracting adjacent transaction information meeting the constraint attributes from the adjacent transaction threads;
digging out the associated information between the transaction record information and the corresponding adjacent transaction information, and carrying out comprehensive analysis on the associated information contained in the comprehensive thread set to obtain a third common condition;
summarizing the first common condition, the second common condition and the third common condition to obtain a comprehensive common condition of each product attribute;
and carrying out invisible mining on the comprehensive common conditions corresponding to all product attributes of the products to be priced to obtain user screening conditions.
5. The customer dynamic pricing method based on customer credit as claimed in claim 4, wherein the step of invisibly mining the comprehensive commonalities corresponding to all product attributes of the product to be priced to obtain the user screening condition comprises:
summarizing the comprehensive thread sets of all product attributes to obtain a thread total set, counting the first total number of customers corresponding to the threads meeting the comprehensive commonality condition of the corresponding product attributes in the thread total set, summarizing the predicted customer group and all historical users to obtain a customer total group, and determining the second total number of customers of the customer total group;
determining the support degree of the corresponding comprehensive commonality condition based on the first total number of customers and the second total number of customers;
determining a commonality threshold value based on the comprehensive commonality condition, and calculating the commonality support degree of the corresponding product attribute based on the commonality threshold value and the corresponding support degree;
screening out a first thread set of which the corresponding product attribute meets the corresponding commonality support degree from the thread total set;
determining a related product attribute with a related rule with the product attribute based on a product attribute related rule list, determining a degree of association between the product attribute and the corresponding related product attribute based on the related rule, and calculating a degree of association commonality support based on the degree of association and the degree of commonality support;
screening out a second thread set of which the product attribute meets the corresponding association commonality support degree from the total thread set;
determining customer promotion degrees corresponding to the product attributes based on a third customer total number corresponding to the first thread set and a fourth customer total number corresponding to the second thread set;
judging whether the customer promotion degrees of all the product attributes meet a customer promotion degree threshold value, if so, taking the product attribute association rule list as a final association rule list;
otherwise, determining the target product attribute with the customer lifting degree not meeting the customer lifting degree threshold value, deleting the association rule with the minimum association degree of the target product attribute to obtain a latest association rule list corresponding to the target product attribute, calculating the latest association commonality support degree based on the latest association rule list, and determining a final association rule list based on the latest association rule list until the latest customer lifting degree determined based on the latest association commonality support degree meets the customer lifting degree threshold value;
based on the latest association rule contained in the final association rule list, performing association combination on the commonality condition corresponding to the product attribute with the latest association rule in the comprehensive commonality condition to obtain a user screening condition;
wherein the common conditions are as follows: the first commonality condition or the second commonality condition or the third commonality condition.
6. The method for dynamic customer pricing based on customer credit of claim 1, wherein S3: determining credit score of each target client based on the historical behavior information and credit evaluation model of each target client in the target client group, and determining a risk coefficient based on the credit score, wherein the method comprises the following steps:
determining credit evaluation attribute characteristic data corresponding to each target client based on the historical behavior information of each target client in the target client group;
inputting the credit evaluation attribute feature data into the credit evaluation model to obtain a credit score of a corresponding target customer;
a risk factor is determined based on the credit score.
7. The method for dynamic pricing of customers based on customer credit as claimed in claim 1, wherein S4: constructing an objective function with price as a variable corresponding to each target client based on the risk coefficient of each target client, the response data under different prices and the capital cost of the product to be priced, wherein the objective function comprises:
based on the response prediction model, obtaining response data of each target customer under different prices;
and constructing an objective function which takes the price as a variable and corresponds to each target client based on the risk coefficient and the response data of each target client and the capital cost of the product to be priced.
8. The method of claim 7, wherein obtaining response data of each target customer at different prices based on the response prediction model comprises:
determining response attribute characteristic data corresponding to each target client based on historical behavior information of each target client in the target client group;
and inputting the response attribute characteristic data into a response prediction model to obtain response data of a corresponding target client.
9. The method for dynamic pricing of customers based on customer credit as claimed in claim 1, wherein S5: solving the optimal solution of the objective function when the constraint condition is met, and taking the optimal solution of the objective function as the final pricing of the corresponding client, wherein the method comprises the following steps:
determining an optimization target of the product to be priced, determining a corresponding variable role and a solving scene based on the optimization target, and determining constraint conditions of the corresponding variable role based on the solving scene;
determining a variable range corresponding to the variable role based on the constraint condition;
and determining the optimal solution of the target function when the variable range is met, and taking the optimal solution of the target function as the final pricing of the corresponding client.
10. The method of claim 7, further comprising:
providing corresponding product items to corresponding target customers based on the final pricing, and acquiring actual handling data of the corresponding product items;
adding the actual transaction data to historical behavior information of a corresponding target client to obtain latest historical behavior information;
correcting the response prediction model based on the latest historical behavior information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210915325.7A CN115439208A (en) | 2022-08-01 | 2022-08-01 | Client dynamic pricing method based on client credit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210915325.7A CN115439208A (en) | 2022-08-01 | 2022-08-01 | Client dynamic pricing method based on client credit |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115439208A true CN115439208A (en) | 2022-12-06 |
Family
ID=84241775
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210915325.7A Pending CN115439208A (en) | 2022-08-01 | 2022-08-01 | Client dynamic pricing method based on client credit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115439208A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB0422482D0 (en) * | 2003-10-17 | 2004-11-10 | Makor Issues & Rights Ltd | System and method for profit maximization in retail industry |
| US20110071857A1 (en) * | 2009-09-23 | 2011-03-24 | Sap Ag | System and Method for Management of Financial Products Portfolio Using Centralized Price and Performance Optimization Tool |
| CN108629698A (en) * | 2018-05-09 | 2018-10-09 | 深圳壹账通智能科技有限公司 | A kind of pricing method of insurance products, device, terminal device and storage medium |
| CN108898498A (en) * | 2018-05-31 | 2018-11-27 | 北京朋友保科技有限公司 | A kind of client's screening technique and system |
| CN110363652A (en) * | 2019-06-27 | 2019-10-22 | 上海淇毓信息科技有限公司 | A kind of financial product pricing method, device and electronic equipment based on Price Sensitive model |
| CN111582908A (en) * | 2020-04-09 | 2020-08-25 | 上海淇毓信息科技有限公司 | Pricing method and device based on interest rate sensitivity curve and electronic equipment |
| CN111815429A (en) * | 2020-06-02 | 2020-10-23 | 福建省农村信用社联合社 | Interest rate adjusting system based on client contribution degree and FTP pricing |
-
2022
- 2022-08-01 CN CN202210915325.7A patent/CN115439208A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB0422482D0 (en) * | 2003-10-17 | 2004-11-10 | Makor Issues & Rights Ltd | System and method for profit maximization in retail industry |
| US20110071857A1 (en) * | 2009-09-23 | 2011-03-24 | Sap Ag | System and Method for Management of Financial Products Portfolio Using Centralized Price and Performance Optimization Tool |
| CN108629698A (en) * | 2018-05-09 | 2018-10-09 | 深圳壹账通智能科技有限公司 | A kind of pricing method of insurance products, device, terminal device and storage medium |
| CN108898498A (en) * | 2018-05-31 | 2018-11-27 | 北京朋友保科技有限公司 | A kind of client's screening technique and system |
| CN110363652A (en) * | 2019-06-27 | 2019-10-22 | 上海淇毓信息科技有限公司 | A kind of financial product pricing method, device and electronic equipment based on Price Sensitive model |
| CN111582908A (en) * | 2020-04-09 | 2020-08-25 | 上海淇毓信息科技有限公司 | Pricing method and device based on interest rate sensitivity curve and electronic equipment |
| CN111815429A (en) * | 2020-06-02 | 2020-10-23 | 福建省农村信用社联合社 | Interest rate adjusting system based on client contribution degree and FTP pricing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2003530649A (en) | Personalized investment advisory system and method embodied on a network | |
| MXPA01008623A (en) | Methods and systems for efficiently sampling portfolios for optimal underwriting. | |
| EP1264242A1 (en) | Methods and systems for automated inferred valuation of credit scoring | |
| US20140344143A1 (en) | System and method for managing related accounts | |
| CN112801529A (en) | Financial data analysis method and device, electronic device and medium | |
| CN112613972A (en) | Credit risk-based medium and small micro-enterprise credit decision method | |
| CN113674040A (en) | Vehicle quotation method, computer device and computer-readable storage medium | |
| Koont | The digital banking revolution: Effects on competition and stability | |
| Wang et al. | The relationship between corporate social responsibility and firm performance: An application of quantile regression | |
| Wang et al. | Uncertainty, GVC participation and the export of Chinese firms | |
| Carluccio et al. | Private firms, corporate investment and the WACC: evidence from France | |
| CN110930259A (en) | Creditor right recommendation method and system based on mixed strategy | |
| CN115439208A (en) | Client dynamic pricing method based on client credit | |
| Laporta et al. | Unionization and profitability in the Canadian manufacturing sector | |
| CN114943582A (en) | Information recommendation method and system and recommendation server | |
| CN115034685A (en) | Customer value evaluation method, customer value evaluation device and computer-readable storage medium | |
| Nicita | Who benefits from export-led growth? Evidence from Madagascar's textile and apparel industry | |
| US20140180964A1 (en) | Method for displaying current disparate ratio for enterprise value using difference between market value for enterprise and basic analysis | |
| CN114693428A (en) | Data determination method and device, computer readable storage medium and electronic equipment | |
| KR20090075557A (en) | A mind decision support system using a type classification and outcome assessment of funds | |
| Wang et al. | Financial advisor's covert discrimination against long-term clients | |
| CN113313572B (en) | Model identification method based on accumulation fund point-credit customer | |
| CN117236996B (en) | User behavior prediction method and system based on big data analysis | |
| Kirkos et al. | Applying data mining methodologies for auditor selection | |
| Kalmár et al. | Bank controlling with a marketing attitude–applied statistics in the service of controlling |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221206 |
|
| RJ01 | Rejection of invention patent application after publication |