CN117217885A - Bank product recommending method, device, medium and equipment - Google Patents
Bank product recommending method, device, medium and equipment Download PDFInfo
- Publication number
- CN117217885A CN117217885A CN202310989708.3A CN202310989708A CN117217885A CN 117217885 A CN117217885 A CN 117217885A CN 202310989708 A CN202310989708 A CN 202310989708A CN 117217885 A CN117217885 A CN 117217885A
- Authority
- CN
- China
- Prior art keywords
- target
- scored
- product
- clients
- client
- 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 43
- 238000012216 screening Methods 0.000 claims abstract description 7
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 238000007726 management method Methods 0.000 description 13
- 238000012797 qualification Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000007115 recruitment Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 230000007103 stamina Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application discloses a method, a device, a medium and equipment for recommending bank products, which comprise the steps of obtaining scores of a plurality of scored clients on all financial products; screening out unscored financial products according to the scores of the target clients on partial financial products; calculating the similarity between the target client and each scored client, and selecting the neighbor client with the highest similarity; predicting the scoring of the target customer on the unscored product according to the scoring of the unscored product by the neighbor customer; and sorting all the financial products according to the scores of the target clients, and recommending the financial products with the highest scores to the target clients. The application has the advantages that the information of the neighbor clients can be utilized to accurately recommend the products of the target clients lacking data, thereby meeting the demands of the clients.
Description
Technical Field
The application relates to the technical field of banks, in particular to a method, a device, a medium and equipment for recommending bank products.
Background
Banks are often pushing new financial products to meet the diversified needs of customers as financial institutions. However, banks may face problems when recommending financial products to customers.
First, the bank may lack sufficient information for the target customer, possibly due to the careful attitude of the target customer to providing personal information or the limited data collection and organization capabilities of the bank itself. The lack of information about the target customer makes it difficult for the bank to fully understand the needs of the target customer, so that the target customer cannot be accurately recommended with the appropriate financial product.
Second, banks may lack effective customer analysis tools and methods. Even if a bank has a large amount of customer information, it is difficult for the bank to accurately evaluate the customer's needs without effective tools and methods for customer analysis. If the bank lacks such tools and methods, it would result in inaccurate customer demand and risk assessment, and thus, unable to recommend proper financial products to the customer.
Disclosure of Invention
Based on this, it is necessary to provide a banking product recommendation method, apparatus, medium and device to solve the problem that a proper financial product cannot be accurately recommended to a customer.
A method of recommending a banking product, the method comprising:
obtaining scores of a plurality of scored customers for all financial products in the product list;
determining scored products and unscored products of a target customer in the product list, and obtaining the score of the target customer on the scored products;
calculating the similarity between the scoring of the target client to the scored product and the scoring of each scored client to the scored product, and determining neighbor clients similar to the target client in the plurality of scored clients according to the similarity;
predicting a score of the target customer for an unscored product based on the score of the neighbor customer for the unscored product;
and sequencing the scores of all the financial products of the target clients, and recommending the first preset number of financial products with the highest scores to the target clients as recommended products.
In one embodiment, the calculating the similarity between the target customer's score for the scored product and the score for each scored customer for the scored product includes:
calculating a scoring mean value according to all scores of target products, and subtracting the scoring mean value from the scores of target customers and scored customers to obtain a first score of the target customers and a second score of each scored customer; wherein the target product is any one of scored products;
and calculating cosine values between the first scores of all the scored products of the target clients and the second scores of all the scored products of each scored client, and taking the calculated results as the similarity.
In one embodiment, the determining, according to the similarity, a neighbor client similar to the target client among the plurality of scored clients includes:
and selecting a first second preset number of clients with highest similarity from the plurality of scored clients as neighbor clients similar to the target client.
In one embodiment, the determining, according to the similarity, a neighbor client similar to the target client among the plurality of scored clients includes:
and selecting clients with similarity larger than a preset similarity threshold from the scored clients as neighbor clients similar to the target client.
In one embodiment, the calculation of the target customer's predicted score for an unscored product is:
in the above, P q Indicating a predictive score of the target customer for the unscored product, rc indicating an average score of the target customer for all scored products, sim (c, i) indicating a similarity between the target customer and neighbor customer i, R ij Indicating the scoring of the unscored product j by neighbor client i,indicating the average score of neighbor client i for all financial products.
In one embodiment, the method further comprises:
acquiring candidate client managers associated with all recommended products;
evaluating personnel capability scores based on the base capability, business capability, and service capability of each candidate customer manager;
evaluating the business potential according to the management scale potential, the management structure and the management contract contribution of each candidate client manager;
and screening from the candidate client manager according to the personnel ability score and the operation potential to obtain a target client manager.
A bank product recommendation device, the device comprising:
the scoring acquisition module is used for acquiring scores of a plurality of scored clients on all financial products in the product list; determining scored products and unscored products of a target customer in the product list, and obtaining the score of the target customer on the scored products;
the neighbor client determining module is used for calculating the similarity between the scoring of the target client to the scored product and the scoring of each scored client to the scored product, and determining neighbor clients similar to the target client in the plurality of scored clients according to the similarity;
the prediction and recommendation module is used for predicting the scoring of the target client to the unscored product based on the scoring of the neighbor client to the unscored product; and sequencing the scores of all the financial products of the target clients, and recommending the first preset number of financial products with the highest scores to the target clients as recommended products.
In one embodiment, the neighbor client determination module is specifically configured to:
calculating a scoring mean value according to all the scoring of the target product; wherein the target product is any one of scored products;
subtracting the scoring means from the target customer's score for the target product and the scored customer's score for the target product, respectively, to obtain a first score for the target customer for the target product and a second score for each scored customer for the target product;
and calculating cosine values between the first scores of all the scored products of the target clients and the second scores of all the scored products of each scored client, and taking the calculated results as the similarity.
A computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the banking product recommendation method described above.
A banking product recommendation device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the banking product recommendation method described above.
The application provides a bank product recommending method, a device, a medium and equipment, which are used for acquiring scores of a plurality of scored clients on all financial products; screening out unscored financial products according to the scores of the target clients on partial financial products; calculating the similarity between the target client and each scored client, and selecting the neighbor client with the highest similarity; predicting the scoring of the target customer on the unscored product according to the scoring of the unscored product by the neighbor customer; and sorting all the financial products according to the scores of the target clients, and recommending the financial products with the highest scores to the target clients. The application has the advantages that the information of the neighbor clients can be utilized to accurately recommend the products of the target clients lacking data, thereby meeting the demands of the clients.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Wherein:
FIG. 1 is a flow chart of a method of recommending a banking product;
FIG. 2 is a schematic illustration of an assessment of stamina scores;
FIG. 3 is a schematic diagram of a bank product recommending apparatus;
fig. 4 is a block diagram of a construction of a banking product recommendation apparatus.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The terms first, second and the like in the description and in the claims and in the above-described figures are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
As shown in fig. 1, fig. 1 is a flow chart of a method for recommending a bank product according to an embodiment, where the method for recommending a bank product includes the following steps:
s101, scores of a plurality of scored customers for all financial products in the product list are obtained.
The financial products in the product list may be, for example, deposits, loans, funds, insurance, etc. All financial products in the product list have been scored by these scored customers with no missing values. These scores may be represented by a user-product matrix, where each row represents a scored customer, each column represents a financial product, and each element represents a score, e.g., 1 to 5 points or likes or dislikes.
Illustratively, assume that there are the following four scored customers (A, B, C, D) and the following five financial products (P1, P2, P3, P4, P5), whose scoring matrices are shown in Table 1 below:
| P1 | P2 | P3 | P4 | P5 | |
| A | 5 | 4 | 3 | 2 | 1 |
| B | 4 | 5 | 2 | 3 | 1 |
| C | 3 | 2 | 5 | 4 | 1 |
| D | 2 | 3 | 4 | 5 | 1 |
TABLE 1
This means that customer a prefers P1 and P5; b customers prefer P2 and dislike P5; c customers prefer P3 and dislike P5; d customers prefer P4 and dislike P5.
S102, determining scored products and unscored products of the target clients in the product list, and obtaining the scores of the target clients on the scored products.
Where the target customer means that they only score a part of the products in the product list and not another part of the products. It is first necessary to determine which products are scored and which are not. This may be achieved by checking for null values in the user-product matrix. Then, the score of the target customer for the scored product needs to be obtained in order to calculate their similarity to other scored customers.
Illustratively, assume that there is one target client E, who scores only P1 and P2, and does not score P3, P4, and P5. Then, his scoring matrix is shown in table 2 below:
| P1 | P2 | P3 | P4 | P5 | |
| E | 4 | 4 |
TABLE 2
This means that E customers give 4 points for both P1 and P2, and no score for P3, P4, and P5. Thus, scored products were P1 and P2, and un-scored products were P3, P4, and P5.
S103, calculating the similarity between the scoring of the target client to the scored product and the scoring of each scored client to the scored product, and determining neighbor clients similar to the target client in the plurality of scored clients according to the similarity.
From the information of tables 1 and 2, the similarity of E-customers to other scored customers can be calculated, conventionally using methods such as pearson correlation coefficients or cosine similarity.
In one embodiment, the similarity is calculated by:
(1) And calculating a score average value according to all scores of the target product, and subtracting the score average value from the scores of the target clients and the scores of the scored clients to obtain a first score of the target clients and a second score of each scored client to the target product.
Wherein the target product is any one of the scored products, that is, the same operation is performed on all the scored products. Here, the scoring vector for each customer is the vector of their scoring components for all scored products. To eliminate the difference in scoring scale, the scoring vector for each customer needs to be first centered, i.e., the average of their scores for all scored products is subtracted.
Illustratively, assuming that the target product is P1 based on the examples of tables 1 and 2 above, all its scores are 5,4,3,2,4, so its score average is (5+4+3+2+4)/5=3.6. The score for the target customer with respect to the target product and the score for the scored customer with respect to the target product are then subtracted by the score means to obtain a first score for the target customer with respect to the target product and a second score for each scored customer with respect to the target product. For example, the first score for E-client for P1 is 4-3.6=0.4; the second score for P1 for client a is 5-3.6=1.4; the second score for P1 by B client is 4-3.6=0.4; the second score for P1 by C client is 3-3.6 = -0.6; the second score for P1 by D customer is 2-3.6 = -1.6.
(2) And calculating cosine values between the first scores of all the scored products of the target clients and the second scores of all the scored products of each scored client, and taking the calculated results as similarity.
Illustratively, based on the examples of tables 1 and 2 above, the cosine values between E-client and A-client are:
similarly, the cosine values between E and B, C, D clients can be calculated, which are cos (E, B) =0.894; cos (E, C) = -0.894; cos (E, D) = -0.894.
In one particular embodiment, the neighbor client is determined by: and selecting a first second preset number of clients with highest similarity from the plurality of scored clients as neighbor clients similar to the target client.
Illustratively, assuming that the second preset number is 2, the first two clients with the highest similarity are selected from the scored clients as neighbor clients. The cosine values calculated before are arranged in order from big to small, and the first two scored clients with the highest similarity are A and B. Thus, a and B are neighbor clients of E.
In one particular embodiment, the neighbor client is determined by: and selecting clients with similarity larger than a preset similarity threshold from a plurality of scored clients as neighbor clients similar to the target client.
Illustratively, assuming a similarity threshold of 0.5, again, the customer is that the similarity of A and B is greater than the preset similarity threshold. Thus, a and B are neighbor clients of E.
S104, the scoring of the un-scored product by the target client is predicted based on the scoring of the un-scored product by the neighbor client.
In one embodiment, the calculation of the target customer's predicted score for an unscored product is as follows:
in the above, P q Indicating a predictive score of the target customer for the unscored product, rc indicating an average score of the target customer for all scored products, sim (c, i) indicating a similarity between the target customer and neighbor customer i, R ij Indicating the scoring of the unscored product j by neighbor client i,indicating the average score of neighbor client i for all financial products.
Illustratively, according to the above formula, and based on the examples of tables 1 and 2 above, a predictive score p3=3.106 for the unscored product P3 is obtained for the E-customer; obtaining a predictive score p4=3.106 for the unscored product P4 for E-customer; a predictive score p4=2.106 for the unscored product P5 is obtained for E-customer.
S105, sorting scores of all financial products of the target clients, and recommending the first preset number of financial products with the highest scores to the target clients as recommended products.
Finally, the ranking may obtain p1=p2 > p3=p4 > P5, so that if the first preset number is 2, products P1 and P2 may be recommended, and if the first preset number is 3, products P1 and P2 may be recommended, and any one of products P3 and P4 may be recommended. And so on, the description will not be repeated.
The bank product recommending method comprises the steps of obtaining scores of a plurality of scored clients on all financial products; screening out unscored financial products according to the scores of the target clients on partial financial products; calculating the similarity between the target client and each scored client, and selecting the neighbor client with the highest similarity; predicting the scoring of the target customer on the unscored product according to the scoring of the unscored product by the neighbor customer; and sorting all the financial products according to the scores of the target clients, and recommending the financial products with the highest scores to the target clients. The application has the advantages that the information of the neighbor clients can be utilized to accurately recommend the products of the target clients lacking data, thereby meeting the demands of the clients.
Further, considering that each product is equipped with a plurality of customer managers responsible for promotion, but the professional abilities of the customer managers are uneven, even if the customer needs are found and the products corresponding to the needs are found, some of the customer managers still miss the best marketing opportunity because the work is not planned or careful enough, so in a specific embodiment, the following steps are further performed:
(1) Candidate customer managers associated with all recommended products are obtained.
(2) Personnel ability scores are evaluated based on the base ability, business ability, and service ability of each candidate customer manager.
As shown in fig. 2, basic capabilities: it is mainly examined whether the client manager has the relevant qualification certificate and tool use capability so as to ensure that the client manager can conduct work in compliance and high efficiency. The method specifically comprises the following steps: personnel qualification: depending on the product scope the customer manager is involved in, it is checked whether it holds corresponding on-duty qualifications, such as financial sales qualifications, fund sales qualifications, insurance sales qualifications, private recruitment sales qualifications, etc., each of which corresponds to a certain score. Tool use capability: according to the working platform, system, software and the like used by the client manager, whether the client manager is skilled in mastering related operation methods and functions, such as a CRM system, financial planning software, data analysis software and the like, is checked, and each tool corresponds to a certain score.
Business capability: it is mainly investigated whether the customer manager has good product sales capacity and customer management capacity to ensure that it can achieve performance goals and customer satisfaction. The method specifically comprises the following steps: product sales capability: according to the type and quantity of products sold by a customer manager, whether the products can recommend proper product schemes such as public recruitment funds, private recruitment funds, net value financial accounting, insurance products and the like according to the requirements and the risk preference of the customer is checked, and each product corresponds to a certain score. Customer business capability: according to the number and quality of clients managed by a client manager, whether the clients can effectively develop new clients, improve the liveness and loyalty of the new and old clients, prevent the clients from losing and transferring, increase the permeability of complex products and the like is checked, and each index corresponds to a certain score. Performance contribution: depending on the level of performance and growth rate achieved by the customer manager, it is checked whether it can meet or exceed the intended goal, and the ranking at the same level or region, each index corresponds to a certain score.
Service capability: it is mainly examined whether the customer manager has excellent service awareness and risk control capability to ensure that it can improve customer satisfaction and reduce business risk. The method specifically comprises the following steps: NPS: according to star rating conditions given by clients on line in daily average products (such as money funds, living financing and the like) sold by client managers, whether the clients can obtain higher net recommended values (NPSs) is checked, and each rating corresponds to a certain score. Compliance/risk case: and checking whether the client manager complies with relevant laws and regulations and internal regulations and whether related problems are processed and reported in time according to compliance or risk cases related to the client manager, wherein each case corresponds to a certain deduction. Customer complaints: according to the customer complaint conditions received by the customer manager, checking whether the customer complaint conditions are avoided or reduced as much as possible, and whether the complaint problems are properly treated and solved, wherein each complaint corresponds to a certain deduction.
(3) The business potential is assessed based on the manager scale potential, the manager structure, and the manager engagement contribution of each candidate client manager.
The manager scale potential is checked whether the manager scale potential has larger development space and growth potential according to indexes such as customer total assets, total deposits, total investments and the like managed by a customer manager, and each index corresponds to a certain score.
The management structure is used for checking whether the management structure has a better client structure and a product structure according to indexes such as client types, risk preferences, product preferences and the like managed by a client manager so as to ensure that the management structure can realize diversified and differentiated operation strategies, and each index corresponds to a certain score.
The management contract contribution is to check whether the management contract contribution has higher customer loyalty and performance stability according to the service contract condition achieved by a customer manager and a customer so as to ensure that the management contract contribution can realize long-term and sustainable operation targets, and each index corresponds to a certain score.
(4) And screening the candidate client manager according to the personnel ability score and the operation potential to obtain the target client manager.
For example, the personnel ability score and the business potential score are weighted and averaged according to a certain weight to obtain a comprehensive score of each candidate client manager, and the scores are ranked from high to low.
In this way, the system recommends a more excellent customer manager to the target customer, which is beneficial for the customer to select the proper financial product.
In one embodiment, as shown in fig. 3, a bank product recommending apparatus is provided, which includes:
a score acquisition module 301, configured to acquire scores of a plurality of scored clients for all financial products in the product list; determining scored products and unscored products of the target clients in the product list, and obtaining the scores of the target clients on the scored products;
a neighbor client determining module 302, configured to calculate a similarity between the score of the target client for the scored product and the score of each scored client for the scored product, and determine neighbor clients similar to the target client among the plurality of scored clients according to the similarity;
a prediction and recommendation module 303, configured to predict a score of the target customer for the unscored product based on the scores of the neighbor customers for the unscored product; and sequencing the scores of the target clients for all the financial products, and recommending the first preset number of financial products with the highest scores to the target clients as recommended products.
In one embodiment, the neighbor client determination module 302 is specifically configured to: calculating a scoring mean value according to all the scoring of the target product; wherein the target product is any one of the scored products; subtracting the score average value from the score of the target customer with respect to the target product and the score of the scored customer with respect to the target product to obtain a first score of the target customer with respect to the target product and a second score of each scored customer with respect to the target product; and calculating cosine values between the first scores of all the scored products of the target clients and the second scores of all the scored products of each scored client, and taking the calculated results as similarity.
In one embodiment, the neighbor client determination module 302 is specifically configured to: and selecting a first second preset number of clients with highest similarity from the plurality of scored clients as neighbor clients similar to the target client.
In one embodiment, the neighbor client determination module 302 is specifically configured to: and selecting clients with similarity larger than a preset similarity threshold from a plurality of scored clients as neighbor clients similar to the target client.
In one embodiment, the calculation of the target customer's predicted score for an unscored product is:
in the above, P q Indicating a predictive score of the target customer for the unscored product, rc indicating an average score of the target customer for all scored products, sim (c, i) indicating a similarity between the target customer and neighbor customer i, R ij Indicating the scoring of the unscored product j by neighbor client i,indicating the average score of neighbor client i for all financial products.
In one embodiment, the bank product recommending means is further for: acquiring candidate client managers associated with all recommended products; evaluating personnel capability scores based on the base capability, business capability, and service capability of each candidate customer manager; evaluating the business potential according to the management scale potential, the management structure and the management contract contribution of each candidate client manager; and screening the candidate client manager according to the personnel ability score and the business potential to obtain the target client manager.
FIG. 4 illustrates an internal block diagram of a banking product recommendation device in one embodiment. As shown in fig. 4, the banking product recommendation device includes a processor, a memory, and a network interface connected through a system bus. The memory includes a nonvolatile storage medium and an internal memory. The non-volatile storage medium of the banking product recommendation device stores an operating system and may also store a computer program which, when executed by a processor, causes the processor to implement a banking product recommendation method. The internal memory may also have stored therein a computer program which, when executed by the processor, causes the processor to perform a bank product recommending method. It will be appreciated by those skilled in the art that the structure shown in fig. 4 is merely a block diagram of a portion of the structure associated with the present application and is not intended to limit the banking product recommendation device to which the present application may be applied, and that a particular banking product recommendation device may include more or fewer components than shown, or may incorporate certain components, or may have a different arrangement of components.
A computer readable storage medium storing a computer program which when executed by a processor performs the steps of: obtaining scores of a plurality of scored customers for all financial products in the product list; determining scored products and unscored products of the target clients in the product list, and obtaining the scores of the target clients on the scored products; calculating the similarity between the scoring of the target client to the scored product and the scoring of each scored client to the scored product, and determining neighbor clients similar to the target client in the plurality of scored clients according to the similarity; predicting a score of the target customer for the unscored product based on the scores of the neighbor customers for the unscored product; and sequencing the scores of the target clients for all the financial products, and recommending the first preset number of financial products with the highest scores to the target clients as recommended products.
A bank product recommending apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of when executing the computer program: obtaining scores of a plurality of scored customers for all financial products in the product list; determining scored products and unscored products of the target clients in the product list, and obtaining the scores of the target clients on the scored products; calculating the similarity between the scoring of the target client to the scored product and the scoring of each scored client to the scored product, and determining neighbor clients similar to the target client in the plurality of scored clients according to the similarity; predicting a score of the target customer for the unscored product based on the scores of the neighbor customers for the unscored product; and sequencing the scores of the target clients for all the financial products, and recommending the first preset number of financial products with the highest scores to the target clients as recommended products.
It should be noted that the above-mentioned method, apparatus, device and computer readable storage medium for recommending a bank product belong to a general inventive concept, and the contents in the embodiments of the method, apparatus, device and computer readable storage medium for recommending a bank product are applicable to each other.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored in a non-transitory computer-readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (10)
1. A method of recommending a banking product, the method comprising:
obtaining scores of a plurality of scored customers for all financial products in the product list;
determining scored products and unscored products of a target customer in the product list, and obtaining the score of the target customer on the scored products;
calculating the similarity between the scoring of the target client to the scored product and the scoring of each scored client to the scored product, and determining neighbor clients similar to the target client in the plurality of scored clients according to the similarity;
predicting a score of the target customer for an unscored product based on the score of the neighbor customer for the unscored product;
and sequencing the scores of all the financial products of the target clients, and recommending the first preset number of financial products with the highest scores to the target clients as recommended products.
2. The method of claim 1, wherein the calculating a similarity between the target customer's score for the scored product and the score for each scored customer for the scored product comprises:
calculating a scoring mean value according to all scores of target products, and subtracting the scoring mean value from the scores of target customers and scored customers to obtain a first score of the target customers and a second score of each scored customer; wherein the target product is any one of scored products;
and calculating cosine values between the first scores of all the scored products of the target clients and the second scores of all the scored products of each scored client, and taking the calculated results as the similarity.
3. The method of claim 1, wherein said determining a neighbor client of said plurality of scored clients that is similar to said target client based on said similarity comprises:
and selecting a first second preset number of clients with highest similarity from the plurality of scored clients as neighbor clients similar to the target client.
4. The method of claim 1, wherein said determining a neighbor client of said plurality of scored clients that is similar to said target client based on said similarity comprises:
and selecting clients with similarity larger than a preset similarity threshold from the scored clients as neighbor clients similar to the target client.
5. The method of claim 1, wherein the predictive score for the unscored product by the target customer is calculated by the formula:
in the above, P q Indicating a predictive score of the target customer for the unscored product, rc indicating an average score of the target customer for all scored products, sim (c, i) indicating a similarity between the target customer and neighbor customer i, R ij Indicating the scoring of the unscored product j by neighbor client i,indicating the average score of neighbor client i for all financial products.
6. The method according to claim 1, characterized in that the method further comprises:
acquiring candidate client managers associated with all recommended products;
evaluating personnel capability scores based on the base capability, business capability, and service capability of each candidate customer manager;
evaluating the business potential according to the management scale potential, the management structure and the management contract contribution of each candidate client manager;
and screening from the candidate client manager according to the personnel ability score and the operation potential to obtain a target client manager.
7. A bank product recommending apparatus, the apparatus comprising:
the scoring acquisition module is used for acquiring scores of a plurality of scored clients on all financial products in the product list; determining scored products and unscored products of a target customer in the product list, and obtaining the score of the target customer on the scored products;
the neighbor client determining module is used for calculating the similarity between the scoring of the target client to the scored product and the scoring of each scored client to the scored product, and determining neighbor clients similar to the target client in the plurality of scored clients according to the similarity;
the prediction and recommendation module is used for predicting the scoring of the target client to the unscored product based on the scoring of the neighbor client to the unscored product; and sequencing the scores of all the financial products of the target clients, and recommending the first preset number of financial products with the highest scores to the target clients as recommended products.
8. The apparatus of claim 7, wherein the neighbor client determination module is specifically configured to:
calculating a scoring mean value according to all the scoring of the target product; wherein the target product is any one of scored products;
subtracting the scoring means from the target customer's score for the target product and the scored customer's score for the target product, respectively, to obtain a first score for the target customer for the target product and a second score for each scored customer for the target product;
and calculating cosine values between the first scores of all the scored products of the target clients and the second scores of all the scored products of each scored client, and taking the calculated results as the similarity.
9. A computer readable storage medium, characterized in that a computer program is stored, which, when being executed by a processor, causes the processor to perform the steps of the method according to any of claims 1 to 6.
10. A bank product recommendation device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310989708.3A CN117217885A (en) | 2023-08-07 | 2023-08-07 | Bank product recommending method, device, medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310989708.3A CN117217885A (en) | 2023-08-07 | 2023-08-07 | Bank product recommending method, device, medium and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117217885A true CN117217885A (en) | 2023-12-12 |
Family
ID=89034232
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310989708.3A Pending CN117217885A (en) | 2023-08-07 | 2023-08-07 | Bank product recommending method, device, medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117217885A (en) |
-
2023
- 2023-08-07 CN CN202310989708.3A patent/CN117217885A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Helbok et al. | Determinants of operational risk reporting in the banking industry | |
| Ciampi | Corporate governance characteristics and default prediction modeling for small enterprises. An empirical analysis of Italian firms | |
| US8442854B2 (en) | System and method for estimating residual lifetime value of a customer base utilizing survival analysis | |
| US10325235B2 (en) | Method and system for analyzing and optimizing distribution of work from a plurality of queues | |
| Kozyr et al. | Modern approaches assessing global competitiveness | |
| Bertelli et al. | Perceiving credible commitments: How independent regulators shape elite perceptions of regulatory quality | |
| CN115358549A (en) | Method, apparatus, device, medium and program product for provider hologram creation | |
| Sandberg et al. | Financial strategy: planning and managing the corporate leverage position | |
| Siougle et al. | Linking ISO 9000 certification to firm performance and financial crisis: a matched sample longitudinal analysis | |
| Kim | Bankruptcy and institutions: Theory and empirical evidence from Korea and the United States | |
| CN116993512A (en) | Recommendation method, system, equipment and storage medium for financial products | |
| CN117217885A (en) | Bank product recommending method, device, medium and equipment | |
| Nnam et al. | Risk assessment: a fight against fraud in Nigerian organizations | |
| Hsu et al. | Product Market Competition and Analyst Coverage Decisions | |
| ARIEFIANTO et al. | The Effect of Competition and Capacity on Intermediation Cost: A Country Level Study. | |
| Apergis | The role of Covid-19 in bank profitability convergence: evidence from a sample of US banks and club clustering | |
| CN114240605A (en) | Loan calculation method and device, computer equipment and storage medium | |
| US20150095259A1 (en) | System and method for investment fund management | |
| Roje | The role of accounting determinants in predicting long term credit ratings | |
| Pratiwi et al. | Earnings Management in Companies that Missed and Beat Analyst Consensus | |
| Aini et al. | Analysis of financial performance, risk and financial distress: studies of retail companies in indonesia during the Covid-19 pandemic | |
| Krishna et al. | Prediction and Optimization of Life Insurance Prediction Based on FEA and ANN Hybrid Approach | |
| Thompson et al. | Measuring Financial Advice: aligning client elicited and revealed risk | |
| Qin et al. | Research on Innovation and Strategic Risk Management in Manufacturing Firms | |
| CN116245561A (en) | Customer repurchase prediction method, device, computer equipment and storage medium |
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 |