CN116228371A - Recommendation method and device for financial products, storage medium and electronic equipment - Google Patents
Recommendation method and device for financial products, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN116228371A CN116228371A CN202310266575.7A CN202310266575A CN116228371A CN 116228371 A CN116228371 A CN 116228371A CN 202310266575 A CN202310266575 A CN 202310266575A CN 116228371 A CN116228371 A CN 116228371A
- Authority
- CN
- China
- Prior art keywords
- target
- group
- interest
- client
- interest feature
- 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 58
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 238000012216 screening Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 abstract description 8
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000004590 computer program Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005304 joining Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a recommendation method and device of financial products, a storage medium and electronic equipment. Relates to the field of artificial intelligence, and the method comprises the following steps: acquiring consumption record sets of all clients in a target database, and dividing all the clients into a plurality of client groups based on the consumption record sets; acquiring target interest characteristic information and target consumption records of a current client, and determining a target client group to which the current client belongs according to the target consumption records of the current client; calculating the interest feature similarity of each target client in the current client and the target client group based on the target interest feature information to obtain a group of interest feature similarity; determining a target interest feature set of the current client based on a set of interest feature similarities; and determining target financial products according to the target interest feature group and the target customer group, and recommending the target financial products to the current customers. By the method and the device, the problem of low success rate of recommending financial products in the related technology is solved.
Description
Technical Field
The application relates to the field of artificial intelligence, in particular to a recommendation method and device of financial products, a storage medium and electronic equipment.
Background
In the related art, each financial institution continuously adds new users to find credit cards, and recommending credit cards to users is an important task for business personnel. However, the service personnel basically recommend products in a mode of inquiring clients, social software release related information and the like, and the recommendation success rate is low.
Aiming at the problem of low success rate of recommending financial products in the related technology, no effective solution is proposed at present.
Disclosure of Invention
The main objective of the present application is to provide a method, an apparatus, a storage medium and an electronic device for recommending financial products, so as to solve the problem of low success rate of recommending financial products in related technologies.
In order to achieve the above object, according to one aspect of the present application, there is provided a recommendation method of a financial product. The method comprises the following steps: acquiring consumption record sets of all clients in a target database, and dividing all the clients into a plurality of client groups based on the consumption record sets; acquiring target interest characteristic information and target consumption records of a current client, and determining a target client group to which the current client belongs according to the target consumption records of the current client; calculating the interest feature similarity of each target client in the current client and the target client group based on the target interest feature information to obtain a group of interest feature similarity; determining a target interest feature group of the current client based on a set of interest feature similarities, wherein the target interest feature group is an interest feature group in a target client group; and determining target financial products according to the target interest feature group and the target customer group, and recommending the target financial products to the current customers.
Optionally, dividing all clients into a plurality of client groups based on the set of consumption records includes: determining the number of consumption times in a preset time period in a consumption record of each customer; judging whether the consumption times are larger than or equal to the first preset consumption times, and dividing the clients into a first client group under the condition that the consumption times are smaller than the first preset consumption times; judging whether the consumption times are larger than or equal to second preset consumption times or not under the condition that the consumption times are larger than or equal to first preset consumption times, wherein the second preset consumption times are larger than or equal to the first preset consumption times; dividing the clients into a second client group under the condition that the consumption times are smaller than the second preset consumption times; and dividing the clients into a third client group under the condition that the consumption times are larger than or equal to the second preset consumption times.
Optionally, before calculating the feature of interest similarity of the current client to each target client in the target client group based on the target feature of interest information, the method further comprises: and receiving a questionnaire result of each target client in the target client group, and acquiring interest characteristic information of each target client based on the questionnaire result.
Optionally, calculating the interest feature similarity of the current client to each target client in the target client group based on the target interest feature information includes: determining a plurality of interest features in the target interest feature information to obtain a first interest feature set, and determining a plurality of interest features in the interest feature information of each target client to obtain a second interest feature set; determining the number of the interesting features in the intersection of the first interesting feature set and the second interesting feature set to obtain the first interesting feature number; determining the number of the interesting features in the union set of the first interesting feature set and the second interesting feature set to obtain the second interesting feature number; and calculating the ratio of the number of the first interest features to the number of the second interest features to obtain the similarity of the interest features of the current client and the target client.
Optionally, determining the target set of interest features for the current customer based on the set of interest feature similarities comprises: determining a plurality of interest feature groups in the target client group, and determining a group of target feature clients contained in each interest feature group; calculating the sum of the similarity of the current client and the interest characteristics of all target characteristic clients in each interest characteristic group to obtain a similarity accumulated value of each interest characteristic group; calculating the sum of the interest feature similarity of the current client and all clients in the target client group to obtain the total interest feature similarity accumulated value of the target client group; calculating the ratio of the similarity accumulated value of each interest feature group to the total interest feature similarity accumulated value to obtain a group of target probabilities of the current clients belonging to each interest feature group; and determining the maximum target probability value in the group of target probabilities, and determining the interest feature group corresponding to the maximum target probability value as the target interest feature group.
Optionally, before determining the interest feature group corresponding to the maximum target probability value as the target interest feature group, the method further includes: calculating the sum of all target probability values in a group of target probabilities to obtain a total probability value; judging whether the total probability value is larger than or equal to a preset probability value; under the condition that the total probability value is smaller than a preset probability value, a new interest feature group is established, and the new interest feature group is determined to be a target interest feature group; and under the condition that the total probability value is greater than or equal to the preset probability value, executing the step of determining the interest feature group corresponding to the maximum target probability value as the target interest feature group.
Optionally, determining the target financial product from the target set of interest features and the target customer group comprises: determining a type of financial products corresponding to the target interest feature group; and determining the consumption frequency range of the target customer group, and screening target financial products from a class of financial products based on the consumption frequency range.
In order to achieve the above object, according to another aspect of the present application, there is provided a recommendation device for a financial product. The device comprises: a first acquisition unit configured to acquire a consumption record set of all clients in a target database, and divide all clients into a plurality of client groups based on the consumption record set; the second acquisition unit is used for acquiring target interest characteristic information and target consumption records of the current client and determining a target client group to which the current client belongs according to the target consumption records of the current client; the calculating unit is used for calculating the interest feature similarity of each target client in the current client and the target client group based on the target interest feature information to obtain a group of interest feature similarity; a first determining unit, configured to determine a target interest feature group of the current client based on the set of interest feature similarities, where the target interest feature group is an interest feature group in the target client group; and the second determining unit is used for determining a target financial product according to the target interest feature group and the target client group and recommending the target financial product to the current client.
Through the application, the following steps are adopted: acquiring consumption record sets of all clients in a target database, and dividing all the clients into a plurality of client groups based on the consumption record sets; acquiring target interest characteristic information and target consumption records of a current client, and determining a target client group to which the current client belongs according to the target consumption records of the current client; calculating the interest feature similarity of each target client in the current client and the target client group based on the target interest feature information to obtain a group of interest feature similarity; determining a target interest feature group of the current client based on a set of interest feature similarities, wherein the target interest feature group is an interest feature group in a target client group; and determining target financial products according to the target interest feature group and the target customer group, and recommending the target financial products to the current customers, thereby solving the problem of low success rate of recommending the financial products in the related technology. The interest feature similarity is calculated between the current client and clients of different interest feature groups, the interest feature group to which the current client belongs is determined, and financial products are recommended to the current client based on the target interest feature group to which the current client belongs and the target client group, so that the effect of improving the product recommendation success rate is achieved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, illustrate and explain the application and are not to be construed as limiting the application. In the drawings:
FIG. 1 is a flow chart of a recommendation method for a financial product provided according to an embodiment of the present application;
FIG. 2 is a flowchart of a method for calculating feature of interest similarity provided according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a recommendation device for financial products provided according to an embodiment of the present application;
fig. 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application.
Detailed Description
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the present application described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for presentation, analyzed data, etc.) related to the present disclosure are information and data authorized by the user or sufficiently authorized by each party.
The present invention will be described with reference to preferred implementation steps, and fig. 1 is a flowchart of a recommendation method for a financial product according to an embodiment of the present application, as shown in fig. 1, and the method includes the following steps:
Step S101, a consumption record set of all clients in the target database is obtained, and all clients are divided into a plurality of client groups based on the consumption record set.
Specifically, the target database may be a database of a financial institution, from which consumption records of customers are derived, and all customers are classified into three types of customer groups of "frequent consumption", "normal consumption", and "low frequency consumption" according to the consumption records.
Step S102, obtaining target interest characteristic information and target consumption records of the current client, and determining a target client group to which the current client belongs according to the target consumption records of the current client.
Specifically, the interest feature information may be information obtained according to a questionnaire, the design of the questionnaire may be designed for the type of financial products such as credit cards to be recommended, feature extraction is performed for unique selling points of the credit cards, for example, when constellation credit cards, car loving credit cards and ancient architecture credit cards need to be recommended, questions in the questionnaire may be set as "whether the constellation is interested", "whether there is a car", "whether the ancient architecture is interested", and the like, so that relevant questionnaire surveys are performed in the business handling of the user to obtain the interest feature information. And acquiring target interest characteristic information from a questionnaire fed back by the current client, acquiring target consumption records of the current client, and determining which type of target client group in frequent consumption, normal consumption and low-frequency consumption the current client belongs to based on the consumption times in a preset time period in the target consumption records.
Step S103, calculating the interest feature similarity of each target client in the current client and the target client group based on the target interest feature information to obtain a group of interest feature similarity.
Specifically, the interest feature similarity is calculated through the intersection of the interest feature in the target interest feature information of the current client and the interest feature of the target client and the number of the interest features in the union, so that a group of interest feature similarity between the current client and each target client in the target client group is obtained.
Step S104, determining a target interest feature group of the current client based on a group of interest feature similarities, wherein the target interest feature group is an interest feature group in a target client group.
Specifically, the probability that the current client belongs to each interest feature group is calculated according to a group of interest feature similarity, and the interest feature group with the highest probability is determined as the target interest feature group.
Step S105, determining target financial products according to the target interest feature group and the target customer group, and recommending the target financial products to the current customers.
Specifically, determining the product recommendation group of the current customer after determining the target customer group and the target interest feature group of the current customer, for example, the generated product recommendation group may include: the method comprises the steps of frequent consumption, constellation interest groups, frequent consumption, historic building interest, frequent consumption, vehicle presence groups, normal consumption, constellation interest groups, normal consumption, historic building interest, normal consumption, vehicle presence groups, low-frequency consumption, constellation interest groups, low-frequency consumption, historic building interest, low-frequency consumption, vehicle presence groups and the like, recommending the product recommendation groups of different labels by adopting different product recommendation technologies, and selecting target financial products corresponding to the product recommendation groups to recommend the product recommendation groups so as to improve the success rate of product recommendation.
According to the recommendation method of the financial products, consumption record sets of all clients in a target database are obtained, and all the clients are divided into a plurality of client groups based on the consumption record sets; acquiring target interest characteristic information and target consumption records of a current client, and determining a target client group to which the current client belongs according to the target consumption records of the current client; calculating the interest feature similarity of each target client in the current client and the target client group based on the target interest feature information to obtain a group of interest feature similarity; determining a target interest feature group of the current client based on a set of interest feature similarities, wherein the target interest feature group is an interest feature group in a target client group; and determining target financial products according to the target interest feature group and the target customer group, and recommending the target financial products to the current customers, thereby solving the problem of low success rate of recommending the financial products in the related technology. The interest feature similarity is calculated between the current client and clients of different interest feature groups, the interest feature group to which the current client belongs is determined, and financial products are recommended to the current client based on the target interest feature group to which the current client belongs and the target client group, so that the effect of improving the product recommendation success rate is achieved.
Before recommending the product, the target customer group to which the current customer belongs needs to be determined first, and optionally, in the recommendation method of the financial product provided in the embodiment of the present application, dividing all customers into a plurality of customer groups based on the consumption record set includes: determining the number of consumption times in a preset time period in a consumption record of each customer; judging whether the consumption times are larger than or equal to the first preset consumption times, and dividing the clients into a first client group under the condition that the consumption times are smaller than the first preset consumption times; judging whether the consumption times are larger than or equal to second preset consumption times or not under the condition that the consumption times are larger than or equal to first preset consumption times, wherein the second preset consumption times are larger than or equal to the first preset consumption times; dividing the clients into a second client group under the condition that the consumption times are smaller than the second preset consumption times; and dividing the clients into a third client group under the condition that the consumption times are larger than or equal to the second preset consumption times.
Specifically, the preset time period may be one month, the consumption times refer to the times of purchasing products by the customers at the financial institution, the first preset consumption times may be ten times, the second preset consumption times may be twenty times, if the consumption times in one month of the current customer's consumption records are less than ten times, the target customer group to which the current customer belongs is low-frequency consumption, if the consumption times in one month of the current customer's consumption records are greater than or equal to ten times and less than or equal to twenty times, the target customer group to which the current customer belongs is normal consumption, and if the consumption times in one month of the current customer's consumption records are greater than or equal to twenty times, the target customer group to which the current customer belongs is high-frequency consumption. Initial data for determining a product recommendation group of a current customer is obtained by determining a target customer group to which the current customer belongs.
Optionally, in the recommendation method of a financial product provided in the embodiment of the present application, before calculating the similarity of the interest feature of each target client in the current client and the target client group based on the interest feature information, the method further includes: and receiving a questionnaire result of each target client in the target client group, and acquiring interest characteristic information of each target client based on the questionnaire result.
Specifically, the interest characteristic information of the target client is generally obtained by means of a questionnaire, and the interest characteristic information of the target client is obtained according to the questionnaire result filled by the target client. For example, the questionnaire may be designed as a question of "whether or not there is a vehicle", "whether or not to like a ancient building", "whether or not to like a constellation", etc., so as to obtain a specific interest feature of the target user. And obtaining the interest characteristic information of the target client, so as to divide different interest characteristic groups for the target client.
Optionally, fig. 2 is a flowchart of a method for calculating the similarity of interest features of a current client and each target client in a target client group after determining the interest feature group of the target client, as shown in fig. 2, in the method for recommending a financial product provided in the embodiment of the present application, calculating the similarity of interest features of the current client and each target client in the target client group based on the target interest feature information includes: step S201, determining a plurality of interest features in the target interest feature information to obtain a first interest feature set, and determining a plurality of interest features in the interest feature information of each target client to obtain a second interest feature set; step S202, determining the number of the interesting features in the intersection of the first interesting feature set and the second interesting feature set to obtain the first interesting feature number; step S203, determining the number of the interesting features in the union of the first interesting feature set and the second interesting feature set to obtain the second interesting feature number; and step S204, calculating the ratio of the first interest feature number to the second interest feature number to obtain the interest feature similarity of the current client and the target client.
Specifically, the target interest feature information refers to interest feature information of a current client, for example, a target client group of the current client is low-frequency consumption, and each interest feature group included in the low-frequency consumption is determined, for example, an interest feature group like a car, an interest feature group like an ancient building, an interest feature group like a constellation, and the like. Current customer interest characteristics include enjoying ancient architecture. Loving sports, etc. The first set of interest features includes two interest features like ancient architecture and loving sports, target customer a likes constellation and car, and target customer B likes ancient architecture and travel. And calculating the similarity of the interest features of each target client and the current client through the Jaccard similarity coefficient, for example, the number of the first interest features of the target client A and the current client is 0, the number of the second interest features is 4, the similarity of the interest features of the target client A and the current client is 0 divided by 4 and equal to 0, and similarly, the similarity of the interest features of the target client B and the current client is 1 divided by 3 and equal to 0.3. And determining the target interest feature group to which the current client belongs by calculating the interest feature similarity of the current client and each target client in the target client group.
It should be noted that, the calculation method of the jaccard similarity coefficient is that, assuming that there are n clients currently, the client set is represented as u= { U 1 ,…,u i ,…,u n Current clients each have an interest feature, defining the interest feature of client u1 as I u1 Will client u 2 Is defined as I u2 The similarity of interest features between two clients can be obtained by using the Jaccard similarity formula:
I(u1,u2)∈[0,1]
after calculating the similarity of the interest features of each target client in the target client group and the current client, calculating the probability that the current client belongs to each interest feature group, and optionally, in the recommendation method of the financial product provided by the embodiment of the application, determining the target interest feature group of the current client based on a group of interest feature similarities includes: determining a plurality of interest feature groups in the target client group, and determining a group of target feature clients contained in each interest feature group; calculating the sum of the similarity of the current client and the interest characteristics of all target characteristic clients in each interest characteristic group to obtain a similarity accumulated value of each interest characteristic group; calculating the sum of the interest feature similarity of the current client and all clients in the target client group to obtain the total interest feature similarity accumulated value of the target client group; calculating the ratio of the similarity accumulated value of each interest feature group to the total interest feature similarity accumulated value to obtain a group of target probabilities of the current clients belonging to each interest feature group; and determining the maximum target probability value in the group of target probabilities, and determining the interest feature group corresponding to the maximum target probability value as the target interest feature group.
Specifically, the plurality of feature of interest groups is expressed as g= { G 1 ,…,g a ,…,g A }. Determining whether the current client can join the corresponding interest feature group by calculating the interest feature similarity among the clients, and for the current client u 1 It is unknown which desired feature set can be added to, and there are two cases for the current customer, the first case is customer u 1 Will be added to an existing feature of interest group, e.g. feature of interest group g 1 、g a Etc. because this interest feature set is the same as the interest feature of the current client, the second case is the current client u 1 A new interest feature group is formed, because the interest features of other clients that have joined the interest feature group are different from those of the current client, the probability of the current client joining the existing interest feature group or forming a new interest feature group is:
wherein P (u) 1 Alpha) represents whenA set of target probabilities that the front client belongs to the respective feature of interest set,
representing the current client u 1 A total interest feature similarity accumulated value with target client clients in all target client groups,
the accumulated value of the similarity representing the current client u1 and all target clients in the interest feature group ga, alpha is the parameter of the algorithm, which determines the degree of dispersion of the interest feature group formation. And (3) calculating the probability that the current client belongs to each interest feature group, so that the interest feature group with the highest probability is screened out as a target interest feature group.
Optionally, in the recommendation method of a financial product provided in the embodiment of the present application, before determining the interest feature group corresponding to the maximum target probability value as the target interest feature group, the method further includes: calculating the sum of all target probability values in a group of target probabilities to obtain a total probability value; judging whether the total probability value is larger than or equal to a preset probability value; under the condition that the total probability value is smaller than a preset probability value, a new interest feature group is established, and the new interest feature group is determined to be a target interest feature group; and under the condition that the total probability value is greater than or equal to the preset probability value, executing the step of determining the interest feature group corresponding to the maximum target probability value as the target interest feature group.
Specifically, the preset probability value may be 0.5, and when the sum of probabilities that the current client belongs to each existing interest feature group, that is, the total probability value is less than 0.5, it is indicated that the current client does not belong to any existing interest feature group, the target interest feature group is a new interest feature group. And determining the target interest feature group of the current client as a new feature group when the total probability value is smaller than the preset probability value, so that the target interest feature group is ensured to be divided more accurately.
Optionally, in the recommendation method of financial products provided in the embodiment of the present application, determining the target financial product according to the target interest feature group and the target customer group includes: determining a type of financial products corresponding to the target interest feature group; and determining the consumption frequency range of the target customer group, and screening target financial products from a class of financial products based on the consumption frequency range.
For example, if the target interest feature group is a favorite feature group of a constellation, the financial products related to the constellation are determined from a plurality of financial products, one type of financial products can be credit cards with different amounts and associated with the constellation, then the final recommended target financial products are determined based on the consumption frequency range of the target customer group, for example, the target customer group is low-frequency consumption, and the credit card with smaller amount is taken as the target financial product from the credit cards with associated constellation, and the target financial product is matched with the current customer by screening the target financial product from the one type of financial products, so that the success rate of product recommendation is improved.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
The embodiment of the application also provides a recommending device for the financial product, and the recommending device for the financial product can be used for executing the recommending method for the financial product. The following describes a recommendation device for financial products provided in the embodiments of the present application.
Fig. 3 is a schematic diagram of a recommendation device for financial products according to an embodiment of the present application. As shown in fig. 3, the apparatus includes:
a first obtaining unit 10, configured to obtain a consumption record set of all clients in a target database, and divide all clients into a plurality of client groups based on the consumption record set;
a second obtaining unit 20, configured to obtain target interest feature information and a target consumption record of a current client, and determine a target client group to which the current client belongs according to the target consumption record of the current client;
a calculating unit 30, configured to calculate, based on the target interest feature information, interest feature similarities of the current client and each target client in the target client group, so as to obtain a set of interest feature similarities;
a first determining unit 40, configured to determine a target interest feature group of the current client based on the set of interest feature similarities, where the target interest feature group is an interest feature group in the target client group;
A second determining unit 50, configured to determine a target financial product according to the target interest feature group and the target customer group, and recommend the target financial product to the current customer.
According to the recommendation device for the financial products, provided by the embodiment of the application, consumption record sets of all clients in a target database are acquired through the first acquisition unit 10, and all clients are divided into a plurality of client groups based on the consumption record sets; a second obtaining unit 20, configured to obtain target interest feature information and a target consumption record of a current client, and determine a target client group to which the current client belongs according to the target consumption record of the current client; a calculating unit 30, configured to calculate, based on the target interest feature information, interest feature similarities of the current client and each target client in the target client group, to obtain a set of interest feature similarities; a first determining unit 40 that determines a target interest feature group of the current client based on the set of interest feature similarities, wherein the target interest feature group is an interest feature group in the target client group; the second determining unit 50 determines a target financial product according to the target interest feature group and the target customer group, and recommends the target financial product to the current customer, thereby solving the problem of low success rate of recommending financial products in the related art.
Optionally, in the recommendation device for a financial product provided in the embodiment of the present application, the first obtaining unit 10 includes: the first determining module is used for determining the consumption times in a preset time period in the consumption record of each customer; the first judging module is used for judging whether the consumption times are larger than or equal to a first preset consumption times, and dividing the clients into a first client group under the condition that the consumption times are smaller than the first preset consumption times; the second judging module is used for judging whether the consumption times are larger than or equal to second preset consumption times or not under the condition that the consumption times are larger than or equal to first preset consumption times, wherein the second preset consumption times are larger than or equal to the first preset consumption times; the first dividing module is used for dividing the clients into a second client group under the condition that the consumption times are smaller than the second preset consumption times; the second dividing module is used for dividing the clients into a third client group under the condition that the consumption times are larger than or equal to the second preset consumption times.
Optionally, in the recommendation device for a financial product provided in the embodiment of the present application, the device further includes: and the receiving unit is used for receiving the questionnaire result of each target client in the target client group and acquiring the interest characteristic information of each target client based on the questionnaire result.
Optionally, in the recommendation device for a financial product provided in the embodiment of the present application, the calculating unit 30 includes: the second determining module is used for determining a plurality of interest features in the target interest feature information to obtain a first interest feature set, and determining a plurality of interest features in the interest feature information of each target client to obtain a second interest feature set; the third determining module is used for determining the number of the interesting features in the intersection of the first interesting feature set and the second interesting feature set to obtain the first interesting feature number; a fourth determining module, configured to determine the number of interesting features in the union of the first interesting feature set and the second interesting feature set, to obtain the second number of interesting features; the first calculation module is used for calculating the ratio of the first interest feature number to the second interest feature number to obtain the interest feature similarity of the current client and the target client.
Alternatively, in the recommendation device for financial products provided in the embodiment of the present application, the first determining unit 40 includes: a fifth determining module, configured to determine a plurality of interest feature groups in the target client group, and determine a group of target feature clients included in each interest feature group; the second calculation module is used for calculating the sum of the interest feature similarities of the current client and all target feature clients in each interest feature group to obtain a similarity accumulated value of each interest feature group; the third calculation module is used for calculating the sum of the interest feature similarities of the current clients and all clients in the target client group to obtain a total interest feature similarity accumulated value of the target client group; the fourth calculation module is used for calculating the ratio of the similarity accumulated value of each interest feature group to the total interest feature similarity accumulated value to obtain a group of target probabilities that the current client belongs to each interest feature group; and the sixth determining module is used for determining the maximum target probability value in the group of target probabilities and determining the interest feature group corresponding to the maximum target probability value as the target interest feature group.
Optionally, in the recommendation device for a financial product provided in the embodiment of the present application, the device further includes: the probability value calculation unit is used for calculating the sum of all target probability values in a group of target probabilities to obtain a total probability value; the judging unit is used for judging whether the total probability value is larger than or equal to a preset probability value; the establishing unit is used for establishing a new interest feature group and determining the new interest feature group as a target interest feature group under the condition that the total probability value is smaller than a preset probability value; and the execution unit is used for executing the step of determining the interest feature group corresponding to the maximum target probability value as the target interest feature group under the condition that the total probability value is larger than or equal to the preset probability value.
Optionally, in the recommendation device for a financial product provided in the embodiment of the present application, the second determining unit 50 includes: a seventh determining module, configured to determine a type of financial product corresponding to the target interest feature set; and the eighth determining module is used for determining the consumption frequency range of the target customer group and screening target financial products from the financial products based on the consumption frequency range.
The recommendation device for financial products includes a processor and a memory, the first acquiring unit 10, the second acquiring unit 20, the calculating unit 30, the first determining unit 40, the second determining unit 50, and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one, and the success rate of product recommendation is improved by adjusting kernel parameters.
The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.
An embodiment of the present invention provides a computer-readable storage medium having a program stored thereon, which when executed by a processor, implements a recommendation method for a financial product.
The embodiment of the invention provides a processor, which is used for running a program, wherein the program runs to execute a recommendation method of financial products.
Fig. 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application. As shown in fig. 4, the device 401 includes a processor, a memory, and a program stored on the memory and executable on the processor, and the processor implements the following steps when executing the program: a recommendation method of financial products. The device herein may be a server, PC, PAD, cell phone, etc.
The present application also provides a computer program product adapted to perform, when executed on a data processing device, a program initialized with the method steps of: a recommendation method of financial products.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Claims (10)
1. A recommendation method for a financial product, comprising:
acquiring consumption record sets of all clients in a target database, and dividing all the clients into a plurality of client groups based on the consumption record sets;
acquiring target interest characteristic information and target consumption records of a current client, and determining a target client group to which the current client belongs according to the target consumption records of the current client;
Calculating the interest feature similarity of each target client in the current client and the target client group based on the target interest feature information to obtain a group of interest feature similarity;
determining a target interest feature set of the current customer based on the set of interest feature similarities, wherein the target interest feature set is an interest feature set in the target customer group;
and determining a target financial product according to the target interest feature group and the target customer group, and recommending the target financial product to the current customer.
2. The method of claim 1, wherein dividing all customers into a plurality of customer groups based on the set of consumption records comprises:
determining the number of consumption times in a preset time period in a consumption record of each customer;
judging whether the consumption times are larger than or equal to a first preset consumption times, and dividing the clients into a first client group under the condition that the consumption times are smaller than the first preset consumption times;
judging whether the consumption times are larger than or equal to second preset consumption times or not under the condition that the consumption times are larger than or equal to the first preset consumption times, wherein the second preset consumption times are larger than or equal to the first preset consumption times;
Dividing the customers into a second customer group if the number of consumption times is less than the second preset number of consumption times;
and dividing the clients into a third client group under the condition that the consumption times are larger than or equal to the second preset consumption times.
3. The method of claim 1, wherein prior to calculating the similarity of interest features for the current customer to each target customer in the target customer group based on the target interest feature information, the method further comprises:
and receiving a questionnaire result of each target client in the target client group, and acquiring interest characteristic information of each target client based on the questionnaire result.
4. The method of claim 1, wherein calculating the feature of interest similarity of the current customer to each target customer in the target customer group based on the target feature of interest information comprises:
determining a plurality of interest features in the target interest feature information to obtain a first interest feature set, and determining a plurality of interest features in the interest feature information of each target client to obtain a second interest feature set;
determining the number of the interesting features in the intersection of the first interesting feature set and the second interesting feature set to obtain a first interesting feature number;
Determining the number of the interesting features in the union set of the first interesting feature set and the second interesting feature set to obtain a second interesting feature number;
and calculating the ratio of the number of the first interest features to the number of the second interest features to obtain the similarity of the interest features of the current client and the target client.
5. The method of claim 1, wherein determining the target set of interest features for the current customer based on the set of interest feature similarities comprises:
determining a plurality of interest feature groups in the target client group, and determining a group of target feature clients contained in each interest feature group;
calculating the sum of the interest feature similarity of the current client and all target feature clients in each interest feature group to obtain a similarity accumulated value of each interest feature group;
calculating the sum of the interest feature similarity of the current client and all clients in the target client group to obtain a total interest feature similarity accumulated value of the target client group;
calculating the ratio of the similarity accumulated value of each interest feature group to the total interest feature similarity accumulated value to obtain a group of target probabilities of the current clients belonging to each interest feature group;
And determining the maximum target probability value in the set of target probabilities, and determining the interest feature set corresponding to the maximum target probability value as the target interest feature set.
6. The method of claim 5, wherein prior to determining the set of features of interest corresponding to the maximum target probability value as the set of target features of interest, the method further comprises:
calculating the sum of all target probability values in the group of target probabilities to obtain a total probability value;
judging whether the total probability value is larger than or equal to a preset probability value;
under the condition that the total probability value is smaller than the preset probability value, a new interest feature group is established, and the new interest feature group is determined to be the target interest feature group;
and under the condition that the total probability value is greater than or equal to the preset probability value, executing the step of determining the interest feature group corresponding to the maximum target probability value as the target interest feature group.
7. The method of claim 1, wherein determining a target financial product from the target set of interest features and the target customer group comprises:
determining a type of financial products corresponding to the target interest feature group;
And determining the consumption frequency range of the target customer group, and screening the target financial products from the financial products based on the consumption frequency range.
8. A recommendation device for a financial product, comprising:
a first acquisition unit configured to acquire a consumption record set of all clients in a target database, and divide all clients into a plurality of client groups based on the consumption record set;
the second acquisition unit is used for acquiring target interest characteristic information and target consumption records of the current client and determining a target client group to which the current client belongs according to the target consumption records of the current client;
the calculating unit is used for calculating the interest feature similarity of each target client in the current client and the target client group based on the target interest feature information to obtain a group of interest feature similarity;
a first determining unit, configured to determine a target interest feature group of the current client based on the set of interest feature similarities, where the target interest feature group is an interest feature group in the target client group;
and the second determining unit is used for determining a target financial product according to the target interest feature group and the target client group and recommending the target financial product to the current client.
9. A non-volatile storage medium, characterized in that the non-volatile storage medium comprises a stored program, wherein the program, when run, controls a device in which the non-volatile storage medium is located to perform the recommendation method of a financial product according to any one of claims 1 to 7.
10. An electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of recommending financial products of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310266575.7A CN116228371A (en) | 2023-03-13 | 2023-03-13 | Recommendation method and device for financial products, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310266575.7A CN116228371A (en) | 2023-03-13 | 2023-03-13 | Recommendation method and device for financial products, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116228371A true CN116228371A (en) | 2023-06-06 |
Family
ID=86569470
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310266575.7A Pending CN116228371A (en) | 2023-03-13 | 2023-03-13 | Recommendation method and device for financial products, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116228371A (en) |
-
2023
- 2023-03-13 CN CN202310266575.7A patent/CN116228371A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106570718B (en) | Information delivery method and delivery system | |
| CA3045736A1 (en) | Digital banking platform and architecture | |
| US20150278350A1 (en) | Recommendation System With Dual Collaborative Filter Usage Matrix | |
| CN111882426A (en) | Business risk classifier training method, device, equipment and storage medium | |
| CN116542747A (en) | Product recommendation method and device, storage medium and electronic equipment | |
| Fletcher et al. | Are Netflix and Spotify subscribers more likely to pay for online news? Comparative analysis of data from six countries | |
| CN113656699A (en) | User feature vector determination method, related device and medium | |
| CN116450951A (en) | Service recommendation method and device, storage medium and electronic equipment | |
| CN116739665A (en) | Information delivery method and device, electronic equipment and storage medium | |
| CN116596576B (en) | Target recommendation method and device | |
| CN112330373A (en) | User behavior analysis method and device and computer readable storage medium | |
| CN111708945A (en) | Product recommendation method and device, electronic equipment and computer storage medium | |
| CN111881274A (en) | Method, device and processor for determining answer of question | |
| CN116228371A (en) | Recommendation method and device for financial products, storage medium and electronic equipment | |
| CN110020118B (en) | Method and device for calculating similarity between users | |
| CN116186119A (en) | User behavior analysis method, device, equipment and storage medium | |
| Cheryshenko et al. | Integration of big data in the decision-making process in the real estate sector | |
| CN113448876B (en) | Service testing method, device, computer equipment and storage medium | |
| CN116228370A (en) | Product recommendation method and device and electronic equipment | |
| CN117372132B (en) | User credit score generation method, device, computer equipment and storage medium | |
| Hardjono et al. | Implementation of Data Mining for Churn Prediction in Music Streaming Company Using 2020 Dataset | |
| CN117093775A (en) | Project recommendation method and device, processor and electronic equipment | |
| CN111753179B (en) | Data extraction method and device | |
| CN118212009A (en) | Client benefit distribution method, device, electronic equipment and computer program product | |
| CN116680591A (en) | Client information clustering method and device and electronic equipment |
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 |