Credit card recommendation method and device, electronic equipment and computer readable storage medium

Abstract

The invention discloses a credit card recommendation method and device, electronic equipment and a computer readable storage medium. The method comprises the following steps: acquiring multi-dimensional customer data of debit card stock customers through a first business channel of a financial institution; credit card customer group information is obtained through a second business channel of the financial institution, the credit card customer group information comprises credit card customer group classification information and a credit card recommendation strategy corresponding to each credit card customer group, and the first business channel and the second business channel are different business channels of the financial institution; determining a credit card customer group to which the debit card stock customer belongs according to the credit card customer group classification information and the multi-dimensional customer data; and obtaining a credit card recommendation strategy corresponding to the credit card customer group, and recommending a credit card to the corresponding debit card stock customer according to the credit card recommendation strategy corresponding to the credit card customer group.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a credit card recommendation method, device, electronic device and computer-readable storage medium. Background Art

[0002] With the rapid development of financial technology, retail banking is facing unprecedented challenges and opportunities. As one of the important products of retail banks, credit card customer development and management have become the key to improving banks' competitiveness. However, traditional credit card customer development methods often rely on extensive marketing activities and simple customer classification, which makes it difficult to accurately identify and meet customers' personalized needs.

[0003] In the existing technology, banks and other financial institutions usually use the following methods to increase credit card customer penetration:

[0004] (1) Traditional marketing methods: such as telephone marketing, SMS marketing, email marketing, etc., which promote credit card products to potential customers by casting a wide net. This method is inefficient and easily causes disgust and resistance from customers.

[0005] (2) Data analysis and marketing: Some banks have begun to use big data technology to conduct customer analysis, but this is often limited to simple data screening and classification, lacking in-depth customer profiling and personalized recommendations.

[0006] (3) Single product promotion: Banks often only promote credit card products within a single product line to a certain type of customer, and lack a collaborative sales mechanism across business channels. Summary of the invention

[0007] In view of the defects existing in the credit card sales mechanism in the prior art and to at least solve some of the technical problems therein, the embodiments of the present application provide a credit card recommendation method, device, electronic device and computer-readable storage medium.

[0008] The present application embodiment adopts the following technical solutions:

[0009] In a first aspect, an embodiment of the present application provides a credit card recommendation method, the method comprising:

[0010] Obtain multi-dimensional customer data of existing debit card customers through the primary business channels of financial institutions;

[0011] obtaining credit card customer group information through a second business channel of a financial institution, wherein the credit card customer group information includes credit card customer group classification information and a credit card recommendation strategy corresponding to each credit card customer group, wherein the first business channel and the second business channel are different business channels of the financial institution;

[0012] Determining the credit card customer group to which the existing debit card customer belongs based on the credit card customer group classification information and the multi-dimensional customer data;

[0013] The credit card recommendation strategy corresponding to the credit card customer group is obtained, so as to make credit card recommendations to corresponding existing debit card customers according to the credit card recommendation strategy corresponding to the credit card customer group.

[0014] In a second aspect, an embodiment of the present application further provides a credit card recommendation device, the device comprising:

[0015] A first acquisition unit, configured to acquire multi-dimensional customer data of existing debit card customers through a first business channel of a financial institution;

[0016] A second acquisition unit is used to acquire credit card customer group information through a second business channel of a financial institution, wherein the credit card customer group information includes credit card customer group classification information and a credit card recommendation strategy corresponding to each credit card customer group, and the first business channel and the second business channel are different business channels of the financial institution;

[0017] A customer classification unit, configured to determine the credit card customer group to which the existing debit card customer belongs based on the credit card customer group classification information and the multi-dimensional customer data;

[0018] The credit card recommendation unit is used to obtain the credit card recommendation strategy corresponding to the credit card customer group, so as to make credit card recommendations to corresponding debit card existing customers according to the credit card recommendation strategy corresponding to the credit card customer group.

[0019] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0020] a processor; and a memory arranged to store computer executable instructions which, when executed, cause the processor to perform a credit card recommendation method.

[0021] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium, which stores one or more programs, and when the one or more programs are executed by an electronic device including multiple application programs, the electronic device performs a credit card recommendation method.

[0022] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0023] The embodiment of the present application obtains multi-dimensional customer data of existing debit card customers through the first business channel of the financial institution and obtains credit card customer group information through the second business channel of the financial institution, and finely classifies the existing debit card customers according to the credit card customer group classification information and the multi-dimensional customer data, so as to make credit card recommendations to the existing debit card customers of the corresponding credit card customer group according to the credit card recommendation strategy corresponding to each credit card customer group.

[0024] The embodiment of the present application uses existing debit card customers as the objects of credit card recommendation, which can not only broaden the potential customer base of credit cards, but also realize cross-product line collaborative sales of debit card products and credit card products, improve the comprehensive contribution of customers, and finely classify existing debit card customers through multi-dimensional data and credit card customer classification information, which can improve the classification accuracy of customers. According to the fine classification results of customers, targeted credit card recommendations can be made, and the matching degree between credit card products and customer needs can be improved. The embodiment of the present application can improve the penetration rate, satisfaction and loyalty of credit card customers, and provide strong support for the sustainable development of the retail business of financial institutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0026] Figure 1 A flowchart of a credit card recommendation method in an embodiment of the present application;

[0027] Figure 2 A schematic diagram of a process for classifying existing debit card customers into credit card customer groups in an embodiment of the present application;

[0028] Figure 3 This is a structural schematic diagram of a credit card recommendation device in an embodiment of the present application;

[0029] Figure 4 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0031] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0032] The traditional credit card recommendation mechanism has at least the following disadvantages in increasing credit card customer penetration:

[0033] (1) The cross-selling of traditional credit card recommendation mechanisms is often limited to a single product line and lacks a collaborative sales mechanism across business channels, resulting in poor cross-selling effects and low overall customer contribution.

[0034] (2) Customer segmentation is not accurate enough. Traditional solutions often classify customers based on simple customer attributes. They lack the mining and analysis of in-depth information such as customer financial behavior, consumption habits, and risk preferences. As a result, customer segmentation is not accurate enough and it is difficult to meet customers' personalized needs.

[0035] (3) Low product matching. Due to inaccurate customer segmentation, banks and other financial institutions often lack specificity when recommending credit card products, resulting in a low matching degree between products and customer needs, making it difficult to stimulate customers' desire to buy.

[0036] (4) Traditional marketing methods are inefficient and easily cause customers to feel disgusted and resist, while simple data analysis and marketing make it difficult to achieve precise marketing and personalized recommendations.

[0037] It can be seen that the traditional credit card recommendation mechanism is often based on relatively extensive customer classification and marketing strategies, which makes it difficult to effectively identify and meet customers' personalized needs, resulting in slow growth in credit card business and poor customer experience.

[0038] In view of the above problems, the embodiments of the present application aim to solve the problems of credit card customer expansion and refined management in the retail business of financial institutions. Specifically, the embodiments of the present application aim to improve the penetration rate, satisfaction and loyalty of credit card customers through accurate customer segmentation, data analysis, product matching and personalized marketing plans.

[0039] The present application embodiment provides a credit card recommendation method, such as Figure 1 As shown, a flow chart of a credit card recommendation method in an embodiment of the present application is provided, and the method at least includes the following steps S110 to S140:

[0040] Step S110, obtaining multi-dimensional customer data of existing debit card customers through the first business channel of the financial institution.

[0041] The execution subject of the credit card recommendation method of the embodiment of the present application is a computing device. When making a credit card recommendation, the computing device should obtain the recommended object of the credit card. In financial institutions such as banks, debit card business and credit card business belong to different business channels (or business lines). The traditional solution is to obtain the target customer group of credit cards through the credit card business channel and recommend credit card products to the target customer group. Therefore, the cross-selling of the traditional credit card recommendation mechanism is often limited to the credit card product line, and cannot achieve the cross-product line channel collaborative sales of the debit card product line and the credit card product line, resulting in low overall customer contribution.

[0042] Based on this, the embodiment of the present application is to obtain existing debit card customers through the first business channel of the financial institution, and use the existing debit card customers as the target customer group for the credit card. In practical applications, the existing debit card customers in recent years can be used as the target customer group for the credit card. Among them, the first business channel is a channel for managing debit card business.

[0043] It is understandable that the above computing device can be hardware or software. When the computing device is hardware, it can be a distributed cluster consisting of multiple servers or terminal devices, or a single server or a single terminal device. When the computing device is embodied as software, it can be installed in the hardware devices listed above. The computing device can also be multiple software or software modules used to provide distributed services, or it can be implemented as a single software or software module, which is not specifically limited here.

[0044] Step S120, obtaining credit card customer group information through the second business channel of the financial institution, the credit card customer group information including credit card customer group classification information and credit card recommendation strategies corresponding to each credit card customer group, the first business channel and the second business channel are different business channels of the financial institution.

[0045] The second business channel of the embodiment of the present application is a channel for managing credit card business. The first business channel and the second business channel are different business channels of the financial institution. There is a communication barrier between the two business channels, and it is difficult for the second business channel to directly obtain customer data from the first business channel. Therefore, the embodiment of the present application uses the computing equipment of the financial institution to obtain multi-dimensional customer data of existing debit card customers from the first business channel, obtains credit card customer group information from the second business channel, and integrates the data of the first business channel and the second business channel through the computing equipment to achieve data sharing and strategy coordination.

[0046] The credit card customer group information of the embodiment of the present application includes credit card customer group classification information and a credit card recommendation strategy corresponding to each credit card customer group. The credit card customer group classification information is used to classify existing debit card customers, and the credit card recommendation strategy is used to recommend credit cards to existing debit card customers.

[0047] It is understandable that the embodiments of the present application do not limit the execution order of the above-mentioned steps S110 and S120. In other embodiments of the present application, step S120 may be executed first, and then step S110; or step S110 and step S120 may be executed at the same time.

[0048] Step S130, determining the credit card customer group to which the existing debit card customers belong based on the credit card customer group classification information and the multi-dimensional customer data.

[0049] Step S140, obtaining the credit card recommendation strategy corresponding to the credit card customer group, so as to make credit card recommendations to corresponding existing debit card customers according to the credit card recommendation strategy corresponding to the credit card customer group.

[0050] like Figure 1 It can be seen from the credit card recommendation method shown that the embodiment of the present application obtains multi-dimensional customer data of existing debit card customers through the first business channel of the financial institution and obtains credit card customer group information through the second business channel of the financial institution, and finely classifies the existing debit card customers according to the credit card customer group classification information and the multi-dimensional customer data, so as to make credit card recommendations to the existing debit card customers of the corresponding credit card customer group according to the credit card recommendation strategy corresponding to each credit card customer group.

[0051] The embodiment of the present application uses existing debit card customers as the objects of credit card recommendation, which can not only broaden the potential customer base of credit cards, but also realize cross-product line collaborative sales of debit card products and credit card products, thereby improving the overall contribution of customers. In addition, the existing debit card customers are finely classified through multi-dimensional data and credit card customer classification information, which can improve the classification accuracy of customers. According to the fine classification results of customers, credit card recommendations can be made in a targeted manner, thereby improving the matching degree between credit card products and customer needs. The embodiment of the present application can improve the penetration rate, satisfaction and loyalty of credit card customers, and provide strong support for the sustainable development of the retail business of financial institutions.

[0052] In some embodiments of the present application, the multi-dimensional customer data includes at least personal attribute data, asset attribute data, risk attribute data, consumption attribute data and product attribute data, wherein:

[0053] Personal attribute data mainly includes basic customer information such as customer code, gender, age, education, address, marital status, and position;

[0054] Asset attribute data mainly includes customer asset information such as personal income status, customer deposit amount, whether the customer has a house or a car, total investment, total liabilities, etc.

[0055] Risk attribute data mainly include whether the customer has overdue payments and the number of overdue payments, whether there is cash-out behavior, the number of times the customer has been urged to repay, etc.

[0056] Consumption attribute data mainly includes customer consumption preferences, installment status, cash withdrawal status, bank business status, whether to bind third-party payment services (third-party payment services include Alipay services, WeChat services, etc.), credit card usage frequency, debit card and credit card consumption habits, etc.;

[0057] Product attribute data includes information such as credit card limit, number of additional credit card cards, credit card level, credit card type, type of personal loan held, account opening date, etc.

[0058] The customer data of the embodiment of the present application includes not only traditional personal attribute data and asset attribute data, but also multiple dimensions such as consumption attribute data, risk attribute data and product attribute data, so it is possible to more accurately identify customer characteristics and needs.

[0059] In some embodiments of the present application, the credit card customer group classification information includes credit card marketing target portrait information for coarse classification and types of credit card customer groups for fine classification, classification characteristics of each credit card customer group and classification priority of each credit card customer group.

[0060] Among them, the credit card marketing target portrait information is a rough classification of existing debit card customers based on their credit card marketing potential, and the credit card marketing target portrait information includes customer authorization information for credit card marketing, credit card holding information and age statistics information with credit card marketing potential.

[0061] When configuring the credit card customer classification information through the second business channel, the embodiment of the present application obtains multi-dimensional customer data of existing credit card customers through the second business channel. By performing data analysis on the multi-dimensional customer data of existing credit card customers, it is found that customers who hold credit cards and have a certain repayment ability have specific age distribution characteristics (for example, the age of credit card holders is mainly 22-50 years old). Therefore, when configuring the credit card marketing target portrait information, age is used as a customer characteristic.

[0062] The customer authorization information of credit card marketing is related to the customer experience. For example, if the cross-selling customer information provided by the first business channel is not authorized by the customer, then when the financial institution reaches out to the customer for credit card, it may cause customer disgust or resistance, affecting the user experience. Therefore, this embodiment uses the customer authorization information of credit card marketing as another customer feature of the credit card marketing target portrait information. In addition, this mechanism can also significantly shorten the approval time, improve the approval efficiency, and reduce the customer waiting time.

[0063] When an existing debit card customer already holds a credit card of this financial institution, the need for the existing debit card customer to hold other credit cards of this financial institution is relatively low. Therefore, this embodiment uses credit card holding information as the third customer feature of the credit card marketing target portrait information.

[0064] Through the three customer characteristics of the credit card marketing target profile information, target debit card existing customers with credit card marketing potential can be screened out from the debit card existing customers. Through the types of credit card customer groups, the classification characteristics of each credit card customer group, and the classification priority of each credit card customer group, the target debit card existing customers can be further subdivided to improve the classification accuracy of credit card customer groups.

[0065] Among them, the credit card customer groups include, in descending order of classification priority, the agency customer group, the personal loan customer group, the AUM customer group and the potential customer group. The embodiment of the present application obtains the classification characteristics of each credit card customer group through the following steps:

[0066] Acquire multi-dimensional customer data of existing credit card customers through the second business channel;

[0067] Determine the reference customer group for loan issuance, the reference customer group for individual loans, the reference customer group for AUM and the reference customer group for potential that have asset potential and repayment potential based on the multi-dimensional customer data of the existing credit card customers;

[0068] By setting an algorithm (such as a quantile screening algorithm), customer characteristics statistics are conducted on the reference customer group for agency payment, the reference customer group for personal loans, the AUM reference customer group and the potential reference customer group. Based on the customer characteristic statistical results, the agency payment amount characteristics corresponding to the reference customer group for agency payment, the loan and overdue characteristics of the financial structure corresponding to the personal loan reference customer group within the first time window, the monthly and daily average AUM characteristics of the AUM reference customer group within the second time window, and the third-party payment service quantity characteristics, financial product holding quantity characteristics and debit card activity characteristics of the potential reference customer group are determined.

[0069] Therefore, the payment amount characteristics corresponding to the payment reference customer group are used as the payment amount characteristics of the payment customer group, the loan and overdue characteristics of the financial structure corresponding to the personal loan reference customer group in the first time window are used as the loan and overdue characteristics of the financial structure of the personal loan customer group in the first time window, the monthly average daily AUM characteristics of the AUM reference customer group in the second time window are used as the monthly average daily AUM characteristics of the AUM customer group in the second time window, and the third-party payment service quantity characteristics, financial product holding quantity characteristics and debit card activity characteristics of the potential reference customer group are used as the third-party payment service quantity characteristics, financial product holding quantity characteristics and debit card activity characteristics of the potential customer group.

[0070] Among them, when this embodiment determines the reference customer group for agency payment, personal loan reference customer group, AUM reference customer group and potential reference customer group with asset potential and repayment potential based on the multi-dimensional customer data of the existing credit card customers, it can first screen out high-quality customers with asset potential and repayment potential based on the multi-dimensional customer data of the existing credit card customers, divide the high-quality customers into customer groups, and obtain sample data of the reference customer group for agency payment, personal loan reference customer group, AUM reference customer group and potential reference customer group.

[0071] For example, from the perspective of personal attributes, the employer and position of existing credit card customers can reflect the asset and liability situation to a certain extent. For example, customers working in state-owned enterprises and private enterprises have relatively high assets and repayment capabilities, and are high-quality customers, and can be used as sample data for customer characteristic statistics; from the perspective of loan attributes, customers who hold multiple loan products and have zero overdue payments have strong repayment capabilities and are high-quality customers, and can also be used as sample data for customer characteristic statistics; from the perspective of AUM distribution, customers whose average daily AUM in the past six months is greater than the set limit value (for example, greater than 40,000 yuan) have strong repayment capabilities and are high-quality customers.

[0072] In this way, by classifying the above-mentioned high-quality customers, sample data of each reference customer group can be obtained. By performing customer characteristic statistics on the sample data, the customer characteristics of each reference customer group can be obtained, and the customer characteristics of each reference customer group can be used as the classification characteristics of the classification customer group of existing debit card customers.

[0073] When configuring the classification priority of each credit card customer group, you can refer to the overdue risk to configure the classification priority of the credit card customer group. For example, considering that the agency customer group has a relatively low risk and the potential customer group has a relatively high risk, the agency customer group is configured as the highest classification priority and the potential customer group is configured as the lowest classification priority.

[0074] It is understandable that when configuring the classification priority of credit card customers in the embodiment of the present application, those skilled in the art can flexibly configure it according to their needs.

[0075] In some embodiments of the present application, determining the credit card customer group to which the existing debit card customer belongs according to the credit card customer group classification information and the multi-dimensional customer data in the above step S130 specifically includes:

[0076] Roughly classify the existing debit card customers according to the credit card marketing target portrait information and the multi-dimensional customer data to obtain target existing debit card customers with credit card marketing potential;

[0077] The target debit card existing customers are subclassified according to the types of the credit card customer groups, the classification characteristics of each credit card customer group, the classification priority of each credit card customer group and the multi-dimensional customer data to obtain the credit card customer group to which the target debit card existing customers belong.

[0078] In some possible implementations of this embodiment, the existing debit card customers are roughly classified according to the credit card marketing target portrait information and the multi-dimensional customer data to obtain target existing debit card customers with credit card marketing potential, specifically including:

[0079] Obtaining customer authorization information for credit card marketing of existing debit card customers based on a pre-established risk pre-credit whitelist;

[0080] Acquire the credit card holding information and age information of the existing debit card customers according to the multi-dimensional customer data;

[0081] Matching the customer authorization information, credit card holding information and age information of the existing debit card customer for credit card marketing with the credit card marketing target profile information, and determining whether the existing debit card customer has credit card marketing potential based on the information matching result;

[0082] When it is determined that the existing debit card customer has credit card marketing potential, the existing debit card customer is used as a target existing debit card customer.

[0083] Specifically, the pre-established risk pre-credit whitelist is queried based on the customer code, and whether the existing debit card customer belongs to the risk pre-credit whitelist customer is determined based on the query result; the age information of the existing debit card customer is obtained based on the personal attribute data, and the credit card holding information of the existing debit card customer is obtained based on the product attribute data. When the existing debit card customer belongs to the risk pre-credit whitelist customer, the credit card holding information shows that the customer does not hold a credit card, and the age information corresponds to the age statistical information, the existing debit card customer is determined to be a target existing debit card customer with credit card marketing potential; otherwise, the existing debit card customer is determined to have no credit card marketing potential, and no credit card recommendation is given to the customer.

[0084] In some other possible implementations of this embodiment, the target existing debit card customers are sub-classified according to the types of the credit card customer groups, the classification characteristics of each credit card customer group, the classification priority of each credit card customer group, and the multi-dimensional customer data to obtain the credit card customer group to which the target existing debit card customer belongs, specifically including:

[0085] The classification feature matching order is determined according to the classification priority of each credit card customer group, and the credit card customer group with a high classification priority has a high classification feature matching order;

[0086] The multi-dimensional customer data and the classification features of the corresponding credit card customer groups are matched according to the classification feature matching order, and the credit card customer group to which the target debit card stock customer belongs is determined according to the matching result; the specific matching classification process is as follows:

[0087] Obtaining a matching result between the multi-dimensional customer data and the classification characteristics of the current credit card customer group;

[0088] The target debit card existing customers that match the classification characteristics of the current credit card customer group are classified into the current credit card customer group, and the remaining other target debit card existing customers are matched with the classification characteristics of the next level credit card customer group according to the classification characteristic matching order until the classification of the final credit card customer group is completed.

[0089] by Figure 2 Taking the scenario shown in the figure as an example, Figure 2 In the scenario shown, the credit card customer groups include the agency customer group, the personal loan customer group, the AUM customer group and the potential customer group in descending order of classification priority, among which:

[0090] The classification characteristics of the agency payment customer group include agency payment amount characteristics, for example, the agency payment amount is greater than 5,000 yuan;

[0091] The classification characteristics of the individual loan customer group include the loan and overdue characteristics of the financial structure in the first time window, such as having a loan record and no overdue record in the past year;

[0092] The classification characteristics of the AUM (Asset Under Management) customer group include the monthly average daily AUM characteristics in the second time window, for example, the monthly average daily AUM value in the past six months is greater than 40,000 yuan;

[0093] The classification characteristics of the potential customer group include at least one of the number of authorized third-party payment services, the number of financial products held, and the active debit card characteristics. For example, the number of third-party payment services is greater than 2, the number of financial products held is greater than 2, and the number of debit card transactions in the past year analyzed through MCC (Merchant Category Code) is greater than 6 times.

[0094] It should be understood that each credit card customer group can be further divided into multiple sub-customer groups. Taking the agency customer group as an example, the agency customer group can be divided into sub-customer groups based on the amount level of the agency amount and the agency enterprise information (enterprise scale, enterprise region, enterprise nature); in actual application, by analyzing the quality of agency enterprises and regional concentration, the priority pilot areas can be identified. For example, with 200 people (or other orders of magnitude of people) as the median enterprise size, sub-customer groups of the agency customer group can be formulated according to first-tier cities, second-tier cities and other cities, so as to explore differentiated cross-selling based on the actual size of the agency enterprises and improve credit card penetration.

[0095] Taking personal loan customers as an example, we analyze the customer preference for large installment products through the loan information they hold. We score each customer's response preference in each channel based on historical responsiveness and behavioral feedback, divide the personal loan customer base into sub-groups based on the scores, and match credit card services to the corresponding sub-groups.

[0096] Taking potential customers as an example, potential customers are further divided into high-binding sub-customer groups (existing debit card customers authorize binding to multiple third-party payment services), multi-product sub-customer groups (existing debit card customers hold multiple financial products, and the profits of financial products include consumer loan products, home mortgage products, wealth management products and agency products) and highly active sub-customer groups (debit card transactions are more frequent).

[0097] like Figure 2As shown, debit card stock customers are obtained as credit card recommendation targets through the first business channel of the financial institution, and the debit card stock customers are roughly classified based on the credit card marketing target portrait information, and the target debit card stock customers with credit card marketing potential are screened out from the debit card stock customers through the rough classification; when the target debit card stock customers are finely classified, the debit card stock customers with agency payment amount greater than 5,000 yuan are first screened out from the target debit card stock customers according to the agency payment amount characteristics and added to the agency payment customer group, and then according to the loan and overdue characteristics of the financial structure in the first time window, the debit card stock customers with overdue payment in the past year are screened out from the remaining target debit card stock customers. Debit card stock customers with loan records and no overdue records are selected and added to the personal loan customer group; then, based on the monthly average daily AUM characteristics in the second time window, debit card stock customers with a monthly average daily AUM value of more than 40,000 yuan in the past six months are selected from the remaining target debit card stock customers and added to the AUM customer group; finally, based on the number of authorized third-party payment services, the number of financial products held, and the active debit card characteristics, debit card stock customers with more than 2 third-party payment services or more than 2 financial products held or more than 6 debit card transactions in the past year are selected from the remaining target debit card stock customers and added to the potential customer group. Among them, the same debit card stock customers are not included in the agency customer group, personal loan customer group, AUM customer group, and potential customer group, that is, each debit card stock customer is divided into at most one of the credit card customer groups, and a debit card stock customer will not be in different credit card customer groups at the same time.

[0098] The embodiment of the present application analyzes the customer needs corresponding to each credit card customer group in advance, so as to formulate a credit card matching strategy for the corresponding credit card customer group according to the customer needs, for example:

[0099] For the payroll customer base, various types of credit cards are configured with discount coupons that can be bound to salary card repayments, exclusive mall discount coupons, etc.; for the personal loan customer base, credit card products suitable for overdraft consumption are configured; for the AUM customer base, credit card products with high-value benefit services, such as medical beauty benefits, fitness benefits, etc.; for potential customers holding multiple products, credit card products with fund subscription discounts and insurance policy renewal discounts are configured; for more active potential customers, credit card products with scenario consumption benefits, scenario consumption benefits include video memberships, dining discount coupons, game recharge coupons, etc. For other potential customer groups, ordinary credit card products can be configured, such as instant discounts for third-party payment services.

[0100] In addition, personalized credit card marketing strategies can be formulated for each credit card customer group. For example, customized consumption promotion benefits and e-vouchers with set credit limits for the agency customer group, customized installment preferential benefits and e-vouchers with set credit limits for the personal loan customer group, customized high-value benefits and e-vouchers with set credit limits for the AUM customer group, and customized consumption promotion benefits, installment preferential benefits and e-vouchers with set credit limits for potential customer groups.

[0101] This embodiment can increase the added value and attractiveness of credit card products through customized credit card matching strategies and personalized credit card marketing plans, which is conducive to improving the penetration rate of credit cards and enhancing loyalty.

[0102] It can be seen from the above embodiments of the present application that the credit card recommendation method of the embodiments of the present application has at least the following advantages:

[0103] First, the embodiments of the present application not only focus on data analysis and marketing strategy formulation of a single business channel, but also emphasize data integration and marketing strategy coordination across business channels. The embodiments of the present application break the barriers between business channels in the traditional marketing model, and by integrating data resources from different business channels, form a comprehensive customer portrait and marketing strategy across business channels, thereby realizing a multi-channel, all-round credit card recommendation mechanism.

[0104] Second, the embodiment of the present application extracts multi-dimensional data such as personal attribute data, asset attribute data, risk attribute data, consumption attribute data, product attribute data, etc. of existing debit card customers, and uses data analysis technology to accurately segment existing debit card customers. The customer classification method of the embodiment of the present application not only takes into account the basic information of the customer, but also combines multiple aspects such as the customer's financial behavior and consumption habits, so as to more accurately identify potential high-quality credit card customer groups, form a more accurate customer portrait, and provide strong support for the subsequent formulation of marketing strategies.

[0105] Third, the embodiments of the present application can increase the added value and attractiveness of credit card products through customized credit card matching strategies and personalized credit card marketing plans, which is conducive to improving the penetration rate of credit cards, enhancing loyalty, and more effectively allocating marketing resources and reducing operating costs. At the same time, the implementation of the risk pre-credit mechanism also helps to reduce credit risks and improve business security. In addition, through precise customer segmentation and personalized marketing strategies, it is possible to better tap potential customer groups and expand market share.

[0106] The present application also provides a credit card recommendation device, such as Figure 3As shown, a schematic diagram of the structure of a credit card recommendation device in an embodiment of the present application is provided. The credit card recommendation device 300 includes: a first acquisition unit 310, a second acquisition unit 320, a customer classification unit 330 and a credit card recommendation unit 340, wherein:

[0107] The first acquisition unit 310 is used to acquire multi-dimensional customer data of existing debit card customers through a first business channel of a financial institution;

[0108] A second acquisition unit 320 is used to acquire credit card customer group information through a second business channel of a financial institution, wherein the credit card customer group information includes credit card customer group classification information and a credit card recommendation strategy corresponding to each credit card customer group, wherein the first business channel and the second business channel are different business channels of the financial institution;

[0109] A customer classification unit 330, configured to determine the credit card customer group to which the existing debit card customer belongs based on the credit card customer group classification information and the multi-dimensional customer data;

[0110] The credit card recommendation unit 340 is used to obtain the credit card recommendation strategy corresponding to the credit card customer group, so as to make credit card recommendations to corresponding existing debit card customers according to the credit card recommendation strategy corresponding to the credit card customer group.

[0111] In some embodiments of the present application, the credit card customer group classification information includes credit card marketing target portrait information for coarse classification and types of credit card customer groups for fine classification, classification characteristics of each credit card customer group and classification priority of each credit card customer group; the multi-dimensional customer data includes at least personal attribute data, asset attribute data, risk attribute data, consumption attribute data and product attribute data.

[0112] In some embodiments of the present application, the customer classification unit 330 includes a coarse classification module and a detailed classification module;

[0113] A rough classification module, used to roughly classify the existing debit card customers according to the credit card marketing target portrait information and the multi-dimensional customer data, and obtain target existing debit card customers with credit card marketing potential;

[0114] The sub-classification module is used to sub-classify the target debit card existing customers according to the types of the credit card customer groups, the classification characteristics of each credit card customer group, the classification priority of each credit card customer group and the multi-dimensional customer data, and obtain the credit card customer group to which the target debit card existing customers belong.

[0115] In some embodiments of the present application, the credit card marketing object portrait information includes customer authorization information for credit card marketing, credit card holding information and age statistics information of customers with credit card marketing potential. The coarse classification module is specifically used to obtain the customer authorization information for credit card marketing of the debit card stock customers according to a pre-established risk pre-credit whitelist; obtain the credit card holding information and age information of the debit card stock customers according to the multi-dimensional customer data; match the customer authorization information, credit card holding information and age information of the debit card stock customers for credit card marketing with the credit card marketing object portrait information, and determine whether the debit card stock customer has credit card marketing potential based on the information matching result; when it is determined that the debit card stock customer has credit card marketing potential, use the debit card stock customer as the target debit card stock customer.

[0116] In some embodiments of the present application, the detailed classification module is specifically used to determine the classification feature matching order according to the classification priority of each credit card customer group; match the multi-dimensional customer data and the classification features of the corresponding credit card customer group according to the classification feature matching order, and determine the credit card customer group to which the target debit card existing customers belong based on the matching results.

[0117] In some embodiments of the present application, the detailed classification module is specifically used to obtain the matching results of the multi-dimensional customer data and the classification characteristics of the current credit card customer group; classify the target debit card stock customers who match the classification characteristics of the current credit card customer group into the current credit card customer group, and match the remaining other target debit card stock customers with the classification characteristics of the next level credit card customer group according to the classification characteristic matching order, until the classification of the final credit card customer group is completed.

[0118] In some embodiments of the present application, the credit card customer group includes, in descending order of classification priority, an agency customer group, a personal loan customer group, an AUM customer group, and a potential customer group, wherein:

[0119] The classification characteristics of the agency payment customer group include agency payment amount characteristics;

[0120] The classification characteristics of the individual loan customer group include loan and overdue characteristics of the financial structure within the first time window;

[0121] The classification characteristics of the AUM customer group include monthly and daily average AUM characteristics within the second time window;

[0122] The classification characteristics of the potential customer group include at least one of the number of authorized third-party payment services, the number of financial products held, and the active debit card characteristics.

[0123] It can be understood that the above-mentioned credit card recommendation device can implement each step of the credit card recommendation method provided in the above-mentioned embodiment, and the relevant explanations about the credit card recommendation method are applicable to the credit card recommendation device and will not be repeated here.

[0124] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 4 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0125] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0126] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0127] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a credit card recommendation device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0128] Obtain multi-dimensional customer data of existing debit card customers through the primary business channels of financial institutions;

[0129] obtaining credit card customer group information through a second business channel of a financial institution, wherein the credit card customer group information includes credit card customer group classification information and a credit card recommendation strategy corresponding to each credit card customer group, wherein the first business channel and the second business channel are different business channels of the financial institution;

[0130] Determining the credit card customer group to which the existing debit card customer belongs based on the credit card customer group classification information and the multi-dimensional customer data;

[0131] The credit card recommendation strategy corresponding to the credit card customer group is obtained, so as to make credit card recommendations to corresponding existing debit card customers according to the credit card recommendation strategy corresponding to the credit card customer group.

[0132] The above application Figure 1 The method performed by the credit card recommendation device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by a hardware integrated logic circuit in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above credit card recommendation method in combination with its hardware.

[0133] The electronic device may also perform Figure 1 A method for executing a credit card recommendation device in Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0134] The present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to execute Figure 1The method performed by the credit card recommendation device in the illustrated embodiment is specifically used to perform:

[0135] Obtain multi-dimensional customer data of existing debit card customers through the primary business channels of financial institutions;

[0136] obtaining credit card customer group information through a second business channel of a financial institution, wherein the credit card customer group information includes credit card customer group classification information and a credit card recommendation strategy corresponding to each credit card customer group, wherein the first business channel and the second business channel are different business channels of the financial institution;

[0137] Determining the credit card customer group to which the existing debit card customer belongs based on the credit card customer group classification information and the multi-dimensional customer data;

[0138] The credit card recommendation strategy corresponding to the credit card customer group is obtained, so as to make credit card recommendations to corresponding existing debit card customers according to the credit card recommendation strategy corresponding to the credit card customer group.

[0139] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0140] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0141] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0142] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0143] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0144] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0145] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media 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 disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0146] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0147] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0148] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A credit card recommendation method, characterized in that: The credit card recommendation method comprises: Obtain multi-dimensional customer data of existing debit card customers through the primary business channels of financial institutions; obtaining credit card customer group information through a second business channel of a financial institution, wherein the credit card customer group information includes credit card customer group classification information and a credit card recommendation strategy corresponding to each credit card customer group, wherein the first business channel and the second business channel are different business channels of the financial institution; Determining the credit card customer group to which the existing debit card customer belongs based on the credit card customer group classification information and the multi-dimensional customer data; The credit card recommendation strategy corresponding to the credit card customer group is obtained, so as to make credit card recommendations to corresponding existing debit card customers according to the credit card recommendation strategy corresponding to the credit card customer group.

2. The credit card recommendation method according to claim 1, characterized in that: The credit card customer group classification information includes credit card marketing target profile information for coarse classification and types of credit card customer groups for fine classification, classification characteristics of each credit card customer group and classification priority of each credit card customer group; The multi-dimensional customer data includes at least personal attribute data, asset attribute data, risk attribute data, consumption attribute data and product attribute data.

3. The credit card recommendation method according to claim 2, characterized in that: The step of determining the credit card customer group to which the existing debit card customer belongs based on the credit card customer group classification information and the multi-dimensional customer data includes: Roughly classify the existing debit card customers according to the credit card marketing target portrait information and the multi-dimensional customer data to obtain target existing debit card customers with credit card marketing potential; The target debit card existing customers are subclassified according to the types of the credit card customer groups, the classification characteristics of each credit card customer group, the classification priority of each credit card customer group and the multi-dimensional customer data to obtain the credit card customer group to which the target debit card existing customers belong.

4. The credit card recommendation method according to claim 2, characterized in that: The credit card marketing target profile information includes customer authorization information for credit card marketing, credit card holding information, and age statistics information of customers with credit card marketing potential. The method of roughly classifying the existing debit card customers according to the credit card marketing target profile information and the multi-dimensional customer data to obtain target existing debit card customers with credit card marketing potential includes: Obtaining customer authorization information for credit card marketing of existing debit card customers based on a pre-established risk pre-credit whitelist; Acquire the credit card holding information and age information of the existing debit card customers according to the multi-dimensional customer data; Matching the customer authorization information, credit card holding information and age information of the existing debit card customer for credit card marketing with the credit card marketing target profile information, and determining whether the existing debit card customer has credit card marketing potential based on the information matching result; When it is determined that the existing debit card customer has credit card marketing potential, the existing debit card customer is used as a target existing debit card customer.

5. The credit card recommendation method according to claim 3, characterized in that: The sub-classifying the target existing debit card customers according to the type of the credit card customer group, the classification characteristics of each credit card customer group, the classification priority of each credit card customer group, and the multi-dimensional customer data to obtain the credit card customer group to which the target existing debit card customer belongs includes: Determine the classification feature matching order based on the classification priority of each credit card customer group; The multi-dimensional customer data and the classification features of the corresponding credit card customer groups are matched according to the classification feature matching order, and the credit card customer group to which the target debit card existing customer belongs is determined according to the matching result.

6. The credit card recommendation method according to claim 5, characterized in that: The step of matching the multi-dimensional customer data with the classification features of the corresponding credit card customer group according to the classification feature matching order, and determining the credit card customer group to which the target debit card existing customer belongs according to the matching result, comprises: Obtaining a matching result between the multi-dimensional customer data and the classification characteristics of the current credit card customer group; The target debit card existing customers that match the classification characteristics of the current credit card customer group are classified into the current credit card customer group, and the remaining other target debit card existing customers are matched with the classification characteristics of the next level credit card customer group according to the classification characteristic matching order until the classification of the final credit card customer group is completed.

7. The credit card recommendation method according to claim 2, characterized in that: The credit card customer groups include, in descending order of classification priority, agency customer groups, personal loan customer groups, AUM customer groups and potential customer groups, among which: The classification characteristics of the agency payment customer group include agency payment amount characteristics; The classification characteristics of the individual loan customer group include loan and overdue characteristics of the financial structure within the first time window; The classification characteristics of the AUM customer group include monthly and daily average AUM characteristics within the second time window; The classification characteristics of the potential customer group include at least one of the number of authorized third-party payment services, the number of financial products held, and the active debit card characteristics.

8. A credit card recommendation device, characterized in that: The credit card recommendation device comprises: A first acquisition unit, configured to acquire multi-dimensional customer data of existing debit card customers through a first business channel of a financial institution; A second acquisition unit is used to acquire credit card customer group information through a second business channel of a financial institution, wherein the credit card customer group information includes credit card customer group classification information and a credit card recommendation strategy corresponding to each credit card customer group, and the first business channel and the second business channel are different business channels of the financial institution; A customer classification unit, configured to determine the credit card customer group to which the existing debit card customer belongs based on the credit card customer group classification information and the multi-dimensional customer data; The credit card recommendation unit is used to obtain the credit card recommendation strategy corresponding to the credit card customer group, so as to make credit card recommendations to corresponding debit card existing customers according to the credit card recommendation strategy corresponding to the credit card customer group.

9. An electronic device, comprising: processor; as well as A memory arranged to store computer executable instructions, which when executed cause the processor to perform the credit card recommendation method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, causes the electronic device to execute the credit card recommendation method according to any one of claims 1 to 7.

Images