Customer group determination method and device, electronic equipment and program product

Abstract

The invention discloses a customer group determination method and device, electronic equipment and a program product, relates to the field of artificial intelligence and is applied to the field of financial science and technology, and the method comprises the steps: collecting transaction data of a plurality of customers in a financial institution, and extracting various types of index information from the transaction data, the plurality of customers at least use any service in the plurality of services, and the age of the customers is within a preset range; determining dependence degree scores of the plurality of clients on the financial institution according to the plurality of types of index information; clustering the plurality of clients according to the dependence degree score and the multi-class index information to obtain a first clustering result; and determining customer group information corresponding to each customer in the plurality of customers according to the first clustering result. Through application of the method and the device, the problem that the classification result is inaccurate due to the fact that the customers are classified only according to a single transaction index when the customer group information corresponding to the customers is determined by a financial institution in the related technology is solved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence and is applied to the field of financial technology. Specifically, it relates to a customer group identification method, device, electronic device, and program product. Background Technology

[0002] In the fields of customer relationship management and market analysis, financial institutions have long used various methods to assess customer behavior patterns, classify customers, and identify corresponding customer groups to optimize service strategies and resource allocation. Currently, when determining customer group information, financial institutions often rely solely on a single transaction indicator for customer classification. Due to the diversity of transaction behaviors and the differences in customer preferences, a single indicator often fails to fully reflect the true value of a customer and the degree of dependence the customer has on the financial institution. If financial institutions classify customers solely based on transaction amount, the value of the former may be underestimated, while the value of the latter may be overestimated, leading to biased service strategies and impacting the financial institution's market competitiveness and customer satisfaction.

[0003] In view of this, no effective solution has yet been proposed to address the problem that financial institutions classify customers based on a single transaction indicator when determining customer group information in related technologies, resulting in inaccurate classification results. Summary of the Invention

[0004] The main objective of this application is to provide a customer group identification method, apparatus, electronic device, and program product to solve the problem in related technologies where financial institutions classify customers based on only a single transaction indicator when identifying customer group information, resulting in inaccurate classification results.

[0005] To achieve the above objectives, according to one aspect of this application, a method for determining a financial institution's service strategy is provided. The method includes: collecting transaction data from multiple customers of the financial institution and extracting multiple types of indicator information from the transaction data, wherein the multiple customers are customers who use at least one of multiple services and whose age falls within a preset range; determining a dependence score of the multiple customers on the financial institution based on the multiple types of indicator information; clustering the multiple customers based on the dependence score and the multiple types of indicator information to obtain a first clustering result; and determining customer group information corresponding to each customer among the multiple customers based on the first clustering result.

[0006] Furthermore, the multiple services include at least: a first service, a second service, a third service, a fourth service, and a fifth service. The first service represents current deposit services, the second service represents bank card payment services, the third service represents time deposit services, the fourth service represents asset management services, and the fifth service represents credit services. Multiple types of indicator information are extracted from the transaction data, including: indicator information for each service within the multiple services based on transaction time, transaction frequency, and transaction amount indicators. These multiple types of indicator information include at least: the most recent transaction time, service duration, balance information, and financial institution revenue information for each service. The indicator information for the first service also includes at least: transaction amount and transaction frequency; the indicator information for the second service also includes at least: transaction amount, number of transactions, number of active card uses, number of active cards, number of inactive cards, and credit limit information; the indicator information for the third service also includes at least: the number of service holders; the indicator information for the fourth service also includes at least: the number of applications, the type of service held, and the number of service holders; and the indicator information for the fifth service also includes at least: the number of repayments and the number of service holders.

[0007] Furthermore, based on multiple types of indicator information, the dependence scores of multiple customers on financial institutions are determined, including: for each customer among the multiple customers, standardizing each indicator included in each category of indicators corresponding to each service in the multiple types of indicator information to obtain the indicator score for each category of indicators corresponding to each service, wherein the value of each indicator score belongs to an integer value within a preset numerical range; determining the indicator score for each category of indicators corresponding to each service based on the indicator scores for each category of indicators corresponding to each service and the preset weight information of each indicator, and multiplying the indicator scores for each category of indicators corresponding to each service to obtain the indicator score for each service; determining the target weight information of the indicator score for each service based on the degree of influence of each service on the dependence score; and determining the dependence scores of multiple customers on financial institutions based on the indicator scores for each service and the target weight information of the indicator scores for each service.

[0008] Furthermore, multiple customers are clustered based on dependence scores and multiple indicator information to obtain a first clustering result, including: clustering multiple customers based on their dependence scores on financial institutions to obtain a second clustering result, wherein the second clustering result includes at least a first type of customer and a second type of customer, with the first type of customer indicating a higher dependence on financial institutions than the second type of customer; determining the customer distribution information for each service based on the indicator scores for each service corresponding to each customer; and clustering the first type of customer and the second type of customer based on financial institution revenue information and the customer distribution information for each service respectively to obtain the first clustering result.

[0009] Furthermore, based on the indicator scores of each service corresponding to each customer, the customer distribution information for each service is determined, including: for each of the multiple services, determining the average indicator score of each service based on the indicator scores of each service corresponding to each customer; classifying the multiple customers based on the average indicator scores of each service to obtain the classification results corresponding to each service, wherein the classification results corresponding to each service include at least a third type of customer and a fourth type of customer, and for any service, the indicator score of the third type of customer corresponding to the service is greater than the average indicator score of the service, and the indicator score of the fourth type of customer corresponding to the service is less than or equal to the average indicator score of the service; determining the proportion of the number of third type customers and the proportion of the number of fourth type customers in each service based on the classification results corresponding to each service to obtain the customer distribution information for each service.

[0010] Furthermore, multiple customers are clustered based on their dependence scores on financial institutions to obtain a second clustering result. This includes: summing the dependence scores of multiple customers on financial institutions to obtain a total dependence score; determining the average dependence score based on the number of customers and the total dependence score of multiple customers; and dividing the multiple customers into a first category and a second category based on the average dependence score to obtain the second clustering result.

[0011] Furthermore, based on the financial institution's revenue information and the customer distribution information of each service, the first type of customers and the second type of customers are clustered respectively to obtain the first clustering result, including: determining the average revenue information of each customer based on the financial institution's revenue information of multiple services corresponding to each customer in the multi-category indicator information; determining the customer proportion information of each customer in the customer group to which each customer belongs in the classification result based on the customer distribution information of each service for the classification result; and clustering the first type of customers and the second type of customers respectively based on the average revenue information of each customer and the customer proportion information corresponding to each customer to obtain the first clustering result.

[0012] To achieve the above objectives, according to another aspect of this application, a device for determining the service strategy of a financial institution is provided. The device includes: a data collection unit for collecting transaction data from multiple customers of a financial institution and extracting multiple types of indicator information from the transaction data, wherein the multiple customers are customers who use at least one of multiple services and whose age falls within a preset range; a calculation unit for determining the dependence level score of the multiple customers on the financial institution based on the multiple types of indicator information; a clustering unit for clustering the multiple customers based on the dependence level score and the multiple types of indicator information to obtain a first clustering result; and a determination unit for determining the customer group information corresponding to each customer among the multiple customers based on the first clustering result.

[0013] Furthermore, the multiple services include at least: a first service, a second service, a third service, a fourth service, and a fifth service. The first service represents current deposit services, the second service represents bank card payment services, the third service represents time deposit services, the fourth service represents asset management services, and the fifth service represents credit services. The collection unit includes an extraction subunit, used to extract indicator information for each service from the transaction data based on transaction time indicators, transaction frequency indicators, and transaction amount indicators, to obtain multiple types of indicator information. Among them, the multiple types of indicator information include at least: the most recent transaction time, service duration, balance information, and financial institution revenue information for each service. The indicator information for the first service also includes at least: transaction amount and transaction frequency. The indicator information for the second service also includes at least: transaction amount, number of consumptions, number of active card uses, number of active cards, number of inactive cards, and credit limit information. The indicator information for the third service also includes at least: the number of service holders. The indicator information for the fourth service also includes at least: the number of applications, the type of service held, and the number of service holders. The indicator information for the fifth service also includes at least: the number of repayments and the number of service holders.

[0014] Further, the calculation unit includes: a processing subunit, used to standardize each indicator included in each category of indicators corresponding to each service in the multi-category indicator information for each customer among multiple customers, to obtain the indicator score of each category of indicators corresponding to each service, wherein the value of each indicator score belongs to an integer value within a preset numerical range; a first calculation subunit, used to determine the indicator score of each category of indicators corresponding to each service based on the indicator score of each category of indicators corresponding to each service and the preset weight information of each indicator, and to perform a product operation on the indicator scores of each category of indicators corresponding to each service to obtain the indicator score of each service; a determination subunit, used to determine the target weight information of the indicator score of each service based on the degree of influence of each service on the dependence score; and a second calculation subunit, used to determine the dependence score of multiple customers on the financial institution based on the indicator score of each service and the target weight information of the indicator score of each service.

[0015] Furthermore, the clustering unit includes: a first clustering subunit, used to cluster multiple customers based on their dependence scores on financial institutions to obtain a second clustering result, wherein the second clustering result includes at least a first type of customer and a second type of customer, with the first type of customer having a higher dependence on financial institutions than the second type of customer; a third calculation subunit, used to determine the customer distribution information for each service based on the indicator scores for each service corresponding to each customer; and a second clustering subunit, used to cluster the first type of customer and the second type of customer respectively based on the financial institution's revenue information and the customer distribution information for each service to obtain the first clustering result.

[0016] Furthermore, the third calculation subunit includes: a first calculation module, used to determine the average indicator score of each service based on the indicator score of each service corresponding to each customer; a classification module, used to classify multiple customers based on the average indicator score of each service to obtain the classification result corresponding to each service, wherein the classification result corresponding to each service includes at least a third type of customer and a fourth type of customer, and for any service, the indicator score of the service corresponding to the third type of customer is greater than the average indicator score of the service, and the indicator score of the service corresponding to the fourth type of customer is less than or equal to the average indicator score of the service; and a second calculation module, used to determine the proportion of the number of third type of customers and the proportion of the number of fourth type of customers in each service based on the classification result corresponding to each service to obtain the customer distribution information of each service.

[0017] Furthermore, the first clustering subunit includes: a third calculation module, used to sum the dependence scores of multiple customers on financial institutions to obtain a total dependence score; a fourth calculation module, used to determine the average dependence score based on the number of customers and the total dependence score of multiple customers; and a division module, used to divide multiple customers into a first type of customer and a second type of customer based on the average dependence score to obtain a second clustering result.

[0018] Furthermore, the second clustering subunit includes: a fifth calculation module, used to determine the average revenue information of each customer based on the financial institution revenue information of multiple services corresponding to each customer in the multi-category indicator information; a determination module, used to determine the customer proportion information of each customer in the customer group to which each customer belongs in the classification results based on the customer distribution information of each service; and a clustering module, used to cluster the first type of customers and the second type of customers respectively based on the average revenue information of each customer and the customer proportion information corresponding to each customer, to obtain the first clustering result.

[0019] To achieve the above objectives, according to one aspect of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements any of the above-mentioned methods for determining financial institution service strategies, and when executed by a processor, implements the steps of the methods for determining financial institution service strategies in various embodiments of this application.

[0020] To achieve the above objectives, according to one aspect of this application, a computer-readable storage medium is provided, comprising stored computer instructions, wherein the method for determining any of the above-mentioned financial institution service strategies is implemented when the computer instructions are executed by a processor.

[0021] To achieve the above objectives, according to one aspect of this application, an electronic device is provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement any of the above-described methods for determining financial institution service strategies.

[0022] In this embodiment, transaction data from multiple customers of a financial institution is collected, and multiple types of indicator information are extracted from the transaction data. These multiple customers are those who use at least one of multiple services and whose age falls within a preset range. The dependence rating of each customer on the financial institution is determined based on the multiple indicator information. The multiple customers are then clustered based on the dependence rating and the multiple indicator information to obtain a first clustering result. Based on the first clustering result, the customer group information corresponding to each customer is determined. This solves the technical problem that when financial institutions determine customer group information, classifying customers solely based on a single transaction indicator leads to inaccurate classification results.

[0023] By collecting transaction data from multiple customers within financial institutions and extracting various indicators including the most recent transaction time, transaction frequency, and transaction amount, a comprehensive quantification of customers' multidimensional behavioral characteristics can be achieved, thus enabling the construction of a comprehensive dependency scoring system. Simultaneously, by combining dependency scoring with multiple indicator information for cluster analysis, the customer group is subdivided into several primary clusters with different behavioral patterns. This achieves multi-level and multi-angle precise customer classification, further improving the accuracy of customer classification and optimizing the financial institution's customer management strategies. These steps overcome the limitations of related technologies that rely solely on a single transaction indicator for classification, ensuring the comprehensiveness and effectiveness of financial institutions in identifying customer segment information. Attached Figure Description

[0024] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0025] Figure 1 This is a hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for determining service strategies of financial institutions, according to Embodiment 1 of this application.

[0026] Figure 2 This is a flowchart of an optional financial institution service strategy determination method provided in Embodiment 1 of this application;

[0027] Figure 3This is a schematic diagram of an optional process for calculating a customer’s dependence score on a financial institution, provided in Embodiment 1 of this application.

[0028] Figure 4 This is a schematic diagram of a device for determining a financial institution's service strategy according to Embodiment 2 of this application;

[0029] Figure 5 This is a schematic diagram of an electronic device for determining a financial institution's service strategy according to Embodiment 3 of this application. Detailed Implementation

[0030] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0031] It should be noted that the processing method, apparatus, storage medium, and electronic device specified in this application can be used in the fintech field to improve the accuracy of financial institution service strategies in the process of providing customers with accurate financial institution service strategies. It can also be used in any field other than fintech. The application fields of the processing method, apparatus, storage medium, and electronic device specified in this application are not limited.

[0032] It should be noted that the information collected in this application (including but not limited to user device information, user personal information, collected data, used data, generated data, processed data, etc.) and the data (including but not limited to data used for analysis, stored data, displayed data, collected information, used information, generated information, processed information, etc.) are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse. For example, this system has interfaces with relevant users or organizations, providing users with corresponding operation entry points for users to choose to agree to or refuse automated decision results; if the user chooses to refuse, the process proceeds to the expert decision-making stage.

[0033] Example 1

[0034] According to an embodiment of this application, a method embodiment for determining a financial institution's service strategy is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0035] The method embodiment provided in Embodiment 1 of this application can be executed in a mobile terminal, computer terminal or similar computing device. Figure 1 This is a hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for determining service strategies of financial institutions, according to Embodiment 1 of this application. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0036] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0037] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method for determining financial institution service strategies in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned method for determining financial institution service strategies. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0038] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0039] The display can be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0040] Under the aforementioned operating environment, this application provides the following: Figure 2 The method for determining the service strategy of financial institutions is shown. Figure 2 This is a flowchart of an optional financial institution service strategy determination method provided in Embodiment 1 of this application.

[0041] Step S201: Collect transaction data of multiple customers in financial institutions and extract multiple types of indicator information from the transaction data. Among them, multiple customers are customers who use at least one of the multiple services and whose age is within a preset range.

[0042] In this embodiment 1, transaction data of multiple customers are obtained from financial institutions. These customers must meet two conditions: first, the customer has used at least one of the five core personal financial services provided by the bank, including flexible deposit of funds, payment and settlement, fixed deposit of funds, asset management and credit services; second, the customer's age is within a pre-set range.

[0043] From the collected customer transaction data, three main categories of indicators are analyzed and extracted: time since the last transaction (Recency), transaction frequency within a recent specific time period (Frequency), and total transaction amount within that time period (Monetary). These indicators form the basis of the RFM (Recency, Frequency, Monetary) model, used to subsequently assess customers' dependence on banking services. This step ensures the representativeness and validity of the analysis sample, focusing on active customer groups to more accurately identify and classify customer dependence levels.

[0044] In one optional embodiment, based on historical customer transaction data accumulated in the bank's data warehouse, transaction data from the most recent year for 200,000 customers are randomly selected for analysis of individual customer dependence within commercial banks. Sampled customers have at least one transaction in one of five categories of personal financial services: flexible fund storage services, payment and settlement services, fixed fund storage services, asset management services, and credit services, and are aged between 18 and 55 (i.e., the aforementioned preset range). The RFM dependence score for each service is calculated, and cluster analysis is performed on the individual customers to determine the financial institution's service strategy for each customer category.

[0045] Step S202: Determine the degree of dependence of multiple customers on financial institutions based on multiple types of indicator information.

[0046] In this embodiment 1, after extracting various indicator information from the financial institution's customer transaction data, these indicators are quantified. Based on the indicator score for each indicator, a customer's indicator score for different services is calculated, resulting in an individual customer's service dependence score. Finally, the indicator scores for different services are weighted and summed to obtain the customer's overall dependence score on the financial institution, i.e., the overall individual customer dependence score. This process quantifies customer dependence, enabling financial institutions to identify the level of customer dependence based on the score and subsequently formulate corresponding service strategies.

[0047] Step S203: Cluster multiple customers based on dependency scores and multi-category indicator information to obtain the first clustering result.

[0048] In this embodiment 1, based on the calculated dependency scores and combined with multiple indicator information, a data clustering algorithm is used to analyze multiple customers of the financial institution. The goal of clustering is to automatically group customers into different categories based on similar dependency scores and indicator characteristics. This process achieves objective classification of customer groups according to the closeness of their connection with the bank by identifying patterns and trends in the scores and indicator information. The clustering results, i.e., the first clustering results, reveal the differences in dependency levels among different customer groups, with each cluster representing a group of customers with similar dependency levels and behavioral patterns. Through this analysis, financial institutions can gain a deeper understanding of the structure of their customer groups and develop specific service strategies for each cluster to optimize customer relationships and improve customer satisfaction.

[0049] Step S204: Determine the customer group information corresponding to each customer among multiple customers based on the first clustering result.

[0050] In this embodiment 1, after performing cluster analysis on customer data, the customer group is divided into several subsets with similar behavioral characteristics, forming the first clustering result. Subsequently, based on the first clustering result, the common attributes of each cluster are analyzed, and corresponding customer group information is defined, including dependency rating levels, financial service preference information, etc. After determining the customer group information for each cluster, by comparing each customer's dependency rating and transaction behavior data, they are categorized into the most matching customer group, thereby determining the specific customer group information to which each customer belongs. This process ensures the accuracy of customer classification, providing financial institutions with a strategic foundation for customer management and service optimization.

[0051] Optionally, in the method for determining the financial institution service strategy provided in Embodiment 1 of this application, the multiple services include at least: a first service, a second service, a third service, a fourth service, and a fifth service. The first service represents a current deposit service, the second service represents a bank card payment service, the third service represents a time deposit service, the fourth service represents an asset management service, and the fifth service represents a credit service. Multiple types of indicator information are extracted from the transaction data, including: extracting indicator information for each service from the transaction data based on transaction time indicators, transaction frequency indicators, and transaction amount indicators to obtain multiple types of indicator information. Among them, the multiple types of indicator information include at least: the most recent transaction time, service duration, balance information, and financial institution revenue information for each service. The indicator information for the first service also includes at least: transaction amount and transaction frequency. The indicator information for the second service also includes at least: transaction amount, number of consumptions, number of active card usages, number of active cards, number of inactive cards, and credit limit information. The indicator information for the third service also includes at least: the number of service holders. The indicator information for the fourth service also includes at least: the number of applications, the type of service held, and the number of service held. The indicator information for the fifth service also includes at least: the number of repayments and the number of service holders.

[0052] In this Implementation Example 1, to construct a comprehensive evaluation system reflecting the degree of dependence of individual customers on financial institutions, service categories are first defined, clearly distinguishing the services provided by institutions into two main categories: transactional services and non-transactional services. Transactional services, due to their involvement in frequent financial transactions, are evaluated based on the frequency and depth of interaction between customers and banks. The first service, namely demand deposit services, is closely related to customers' daily cash flow and focuses on the liquidity management of customer funds. The second service, namely bank card payment services, focuses on customers' payment and settlement habits, including card activation frequency and transaction activity.

[0053] Then, for non-trading services, which are not characterized by immediate transactions but rather focus on long-term fund management or financial service experience, the third to fifth services are defined, representing time deposit services, asset management services, and credit services, respectively. The third service focuses on customers' preferences for long-term fund storage; the fourth service focuses on customers' participation in asset management, including product subscriptions and holdings; and the fifth service measures customers' activity and repayment performance in credit services.

[0054] Secondly, for each service, multiple indicators directly related to customer dependence were selected. These indicators cover various dimensions such as recent transaction behavior, transaction frequency, and transaction amount to comprehensively reflect the customer's service usage characteristics. Finally, through quantitative analysis of these indicators, a service-level dependence scoring system was established. The scoring for transactional services emphasizes the proximity, frequency, and amount of recent customer transactions, while the scoring for non-transactional services focuses more on the duration, type, and quantity of service held, as well as the long-term value these services bring to the bank.

[0055] Finally, for each service category, specific metrics closely related to customer transaction behavior are sifted from historical transaction data. This process ensures the relevance and effectiveness of the evaluation metrics. These metrics include at least three categories: transaction time metrics, transaction frequency metrics, and transaction amount metrics. Transaction time metrics focus on transaction time characteristics, including but not limited to the time interval since the last transaction and the duration of a specific service. These metrics reveal the timeliness and continuity of customer interaction with the bank. Transaction frequency metrics then focus on transaction frequency characteristics, measuring customer activity and identifying frequent, loyal customers by counting the number of transactions within a specific time period. Finally, transaction amount metrics focus on transaction amount characteristics, including customer transaction amounts and financial institution revenue information, such as the revenue a customer generates for the bank through a particular service. This step aims to quantify the customer's value contribution to the bank.

[0056] In one alternative embodiment, the RFM model is improved by utilizing the basic principles of the RFM model and combining it with the characteristics of financial institution services for individual customers. The resulting service level dependency measurement index can be shown in Table 1 below.

[0057] Table 1

[0058]

[0059] Table 1 selects five personal financial services, including two transactional services (flexible fund storage and payment settlement) and three non-transactional services (fixed fund storage, asset management, and credit). Based on the characteristics and data of each service, key indicators R (proximity), F (frequency), and M (limit) are constructed. In the proximity indicator R, the proximity indicator for flexible fund storage adds service duration to reflect the length of time the customer has established a relationship with the bank; payment settlement adds the time since card activation, i.e., the time interval from when the customer activated their bank card to the present; fixed fund storage uses the time since the last purchase to represent the duration of the fixed deposit service, and also uses the time until maturity to expand the proximity indicator; generally, the longer the maturity date of fixed fund storage, the higher the customer's dependence; asset management and credit services also add service holding time indicators. In frequency indicator F, based on the characteristics of bank card services, the number of active card uses, transaction frequency, number of active cards, and number of inactive cards are selected to comprehensively reflect the degree of customer reliance on payment and settlement services. Fixed-term deposit services are non-transactional services, so the frequency indicator is reflected through the number of services held. Asset management services reflect the number of services held by customers and their transaction activity through indicators such as the number of financial product subscriptions, the types and quantities of services held. Credit services reflect the number of services held by customers through the number of repayments and the number of services held. In credit limit indicator M, in addition to the basic transaction amount indicator, two supplementary indicators are added: average monthly balance and the revenue generated by the customer for the financial institution through this service.

[0060] The quantitative indicators of service level dependence (i.e., the various types of indicator information mentioned above) have the following characteristics: First, the quantitative indicators have been expanded according to different service characteristics. For example, the proximity indicator of fixed-term deposit services is expanded by using the time until maturity date. Second, the dependence measurement indicators also have different focuses according to the differences between transactional and non-transactional services. For example, frequency indicators are emphasized for transactional services, such as the number of transactions, card activations, and consumption, while non-transactional services are more focused on the types and quantities of services held.

[0061] Through the above steps, the technical effect of refining customer dependence evaluation indicators has been achieved, ensuring the comprehensiveness and accuracy of subsequent dependence scoring, providing financial institutions with more accurate customer segmentation, and further improving customer satisfaction through in-depth analysis of customer transaction behavior.

[0062] Optionally, in the method for determining the service strategy of a financial institution provided in Embodiment 1 of this application, determining the dependence score of multiple customers on the financial institution based on multiple types of indicator information includes: for each customer among the multiple customers, standardizing each indicator included in each type of indicator corresponding to each service in the multiple types of indicator information to obtain the indicator score of each type of indicator corresponding to each service, wherein the value of each indicator score belongs to an integer value within a preset numerical range; determining the indicator score of each type of indicator corresponding to each service based on the indicator score of each type of indicator corresponding to each service and the preset weight information of each indicator, and multiplying the indicator scores of each type of indicator corresponding to each service to obtain the indicator score of each service; determining the target weight information of the indicator score of each service based on the degree of influence of each service on the dependence score; and determining the dependence score of multiple customers on the financial institution based on the indicator score of each service and the target weight information of the indicator score of each service.

[0063] In this embodiment 1, to quantify the dependence of individual customers on financial institutions and construct an effective scoring system, firstly, the various indicator information involved in each customer's services is standardized. This process ensures the comparability between different indicators and the numerical stability during calculation. Standardization converts the value of each indicator into an integer score within a preset range, allowing direct comparison and combination of the scores. For example, to further improve the precision of financial institutions' management of customer dependence, a five-eighths-level scoring method can be used to quantify the extracted various indicator information. This method includes dividing indicators such as the time since the last transaction, service duration, number of transactions, transaction amount, and financial institution revenue information into five levels based on their numerical distribution. Each level corresponds to a score value, thereby transforming time, frequency, and amount characteristics into comparable numerical scores, enhancing the objectivity and operability of the scoring system.

[0064] Next, based on the business importance of each indicator within each service, a preset weight is assigned to each indicator. A weighted average is then used to calculate the indicator score for each category. This step strengthens the influence of key indicators in the scoring, reflecting their contribution to customer reliance. Secondly, the indicator scores for each category are multiplied to generate a comprehensive indicator score for each service. This multiplication operation comprehensively reflects customer behavioral characteristics across three core dimensions: time, frequency, and amount, thus providing a more comprehensive perspective for subsequent reliance assessment.

[0065] Finally, the impact of each service on the dependence score was determined, and target weight information was assigned to the comprehensive index score of each service. These weights represent the relative importance of different services to the overall dependence score, ensuring the comprehensiveness and accuracy of the scoring system. Based on the comprehensive index score and target weight information of each service, the scores of all services were weighted and summed to calculate the total dependence score of each customer on the financial institution.

[0066] In one alternative embodiment, Figure 3 This is a schematic diagram of an optional process for calculating a customer's dependence score on a financial institution, provided in Embodiment 1 of this application. Figure 3 As shown, for flexible fund storage services, transaction time-related indicators (such as those related to the time since the last transaction P1 and the service duration P2) are determined based on standardized scores. Figure 3 The first type of indicator in the index) is used to score the indicator, and the trading frequency indicator (such as the standardized score of the number of transactions P3) is used to determine the trading frequency indicator. Figure 3 The second category of indicators) is scored based on standardized scores for transaction amount P4, average monthly balance P5, and financial institution revenue P6 to determine transaction amount-related indicators (such as...). Figure 3 The third category of indicators in the system is used to score the flexible fund storage service. The score is calculated based on the scores of the transaction time, transaction frequency, and transaction amount indicators.

[0067] For payment and settlement services, the standardized scores for transaction time indicators (P7: time since last transaction, P8: time since card activation) are used to determine the scores for transaction frequency indicators (P9: number of active card uses, P10: number of transactions, P11: number of active cards, and P12: number of inactive cards) are used to determine the scores for transaction amount indicators (P13: overdraft balance, P14: transaction amount, P15: average monthly credit limit utilization rate, and P16: financial institution revenue) are used to determine the scores for payment and settlement services. The overall score for payment and settlement services is calculated based on these scores.

[0068] For fixed-term deposit services, the standardized scores for transaction time indicators (P17: time since last purchase, P18) and transaction frequency indicators (P19: number of service holdings) are used to determine the standardized scores for transaction amount indicators. The standardized scores for average monthly balance (P20: average monthly balance, P21: revenue) are used to determine the standardized scores for transaction amount indicators. The final score for the fixed-term deposit service is calculated based on these scores.

[0069] For asset management services, the standardized scores for transaction time indicators are determined based on the time since the last purchase (P22) and the number of services held (P23). The standardized scores for transaction frequency indicators are determined based on the number of subscriptions (P24), the types of services held (P25), and the number of services held (P26). The standardized scores for transaction amount indicators are determined based on the standardized scores for average monthly balance (P27) and financial institution revenue (P28). The overall asset management service score is then calculated based on these three scores.

[0070] For credit services, the standardized scores for transaction time indicators are determined based on the remaining loan term (P29) and service duration (P30); the standardized scores for transaction frequency indicators are determined based on the number of repayments (P31) and the number of services held (P32); and the standardized scores for transaction amount indicators are determined based on the loan balance (P33) and financial institution revenue (P34). The overall credit service score is then calculated based on these scores.

[0071] Based on the indicator scores for flexible fund storage services, payment and settlement services, fixed fund storage services, asset management services, and credit services, as well as the weight information corresponding to each service, the dependence score of each customer on the financial institution is calculated.

[0072] Based on the quantitative indicators of individual customer dependence on the five representative categories of personal financial services mentioned above, a Personal Customer Dependence Assessment Model (PCLM) is constructed. Utilizing the R proximity, F frequency, and M amount indicators for each service, a five-level scoring system is used to obtain the indicator scores for each category. These scores are then multiplied to obtain the service-level dependence score. Depending on the impact of different services on customer dependence, expert consultation and weighting methods or feature importance analysis can be used to determine the corresponding weight information for each service, thereby calculating the individual customer dependence score. This model includes two levels of customer dependence evaluation: customer level and service level. In practical applications, it provides both customer-level dependence scores for financial institutions and dependence scores for relatively independent core personal financial services, meeting the management needs of different services. The calculation formula for the Personal Customer Dependence Assessment Model (PCLM) is shown in Formula 1.

[0073] (1)

[0074] in, Rate the level of customer dependence on each service. The weights for each service are (i represents five service categories: flexible fund storage service, payment and settlement service, fixed fund storage service, asset management service, and credit service, i=1 / 2 / 3 / 4 / 5). , , The scoring system is based on customer service level indicators such as proximity, frequency, and amount; the product of these three factors forms the score. . In accordance with The five-tier scoring function, which ranks scores from highest to lowest, allows for the generation of corresponding scores based on the indicators of each service. , , The rating, among which, The degree of dependence is quantified by indicators (j represents each indicator, j=1 / 2 / 3…34). for For standardized scoring, Different categories of indicators (proximity R, frequency F, amount M) The corresponding weights.

[0075] Through the above steps, the vague concept of customer dependence can be transformed into a clear and measurable numerical indicator, achieving the technical effect of quantifying customer dependence and identifying key service influencing factors. Financial institutions can effectively segment their customer groups based on this scoring system, thus providing them with an effective tool for quantifying customer dependence, facilitating the implementation of differentiated customer relationship management strategies, thereby optimizing customer experience and increasing customer dependence.

[0076] Optionally, in the method for determining the service strategy of a financial institution provided in Embodiment 1 of this application, multiple customers are clustered based on dependence scores and multiple types of indicator information to obtain a first clustering result, including: clustering multiple customers based on their dependence scores on financial institutions to obtain a second clustering result, wherein the second clustering result includes at least a first type of customer and a second type of customer, and the first type of customer has a higher dependence on financial institutions than the second type of customer; determining the customer distribution information of each service based on the indicator scores of each service corresponding to each customer; and clustering the first type of customer and the second type of customer based on the financial institution's revenue information and the customer distribution information of each service respectively to obtain the first clustering result.

[0077] In this Example 1, to deepen the financial institution's understanding of its customer base and optimize its customer relationship management strategy, firstly, cluster analysis is performed on all the financial institution's customers based on previously calculated dependency scores. This process aims to identify customer groups with significant differences in dependency levels. By employing an appropriate clustering algorithm, a second clustering result is obtained based on the similarity and differences in dependency scores. This result distinguishes at least two customer categories: a first category with high dependency and a second category with low dependency. This division directly reflects the degree of customer stickiness to the financial institution.

[0078] Next, focusing on the performance indicators for each service, the customer distribution information for each service was calculated. This step provided specific analytical results regarding the attractiveness of different services and customer preferences, offering data support for service improvement and personalization. Secondly, combining the revenue information obtained by financial institutions from various services with the previously analyzed customer distribution for each service, the first and second customer categories were clustered again, generating the first clustering result.

[0079] Finally, by analyzing the results of the first clustering, financial institutions can accurately identify different customer groups (e.g., highly dependent customer groups, and potential churn customers requiring special attention), providing a basis for developing differentiated service strategies. Through these steps, the technical effects of refined customer segmentation, enhanced customer relationship management, and improved service efficiency are achieved. Financial institutions can then take more targeted measures based on customers' dependence on services to improve customer satisfaction.

[0080] Optionally, in the method for determining the service strategy of a financial institution provided in Embodiment 1 of this application, the customer distribution information of each service is determined based on the indicator score of each service corresponding to each customer, including: for each of multiple services, determining the average indicator score of each service based on the indicator score of each service corresponding to each customer; classifying multiple customers based on the average indicator score of each service to obtain the classification result corresponding to each service, wherein the classification result corresponding to each service includes at least a third type of customer and a fourth type of customer, and for any service, the indicator score of the service corresponding to a third type of customer is greater than the average indicator score of the service, and the indicator score of the service corresponding to a fourth type of customer is less than or equal to the average indicator score of the service; determining the proportion of the number of third type customers and the proportion of the number of fourth type customers in each service based on the classification result corresponding to each service to obtain the customer distribution information of each service.

[0081] In this Example 1, to deepen financial institutions' understanding of customer performance across various services and achieve service-based customer segmentation, firstly, for each of the five representative personal financial services, an average service indicator score was calculated based on each customer's service indicator rating. Then, using the average indicator score for each service as a boundary, customer groups were categorized, generating a classification result for each service. This result includes at least two customer categories: one category consists of customers exhibiting above-average dependence and engagement in the service (the third category); the other category consists of customers below or equal to the average level (the fourth category). Through this classification, financial institutions can clearly distinguish between active and loyal customers and relatively inactive or less dependent customers in a particular service, providing a basis for service customization and resource optimization.

[0082] Secondly, based on the classification results for each service, the proportion of customers in the third and fourth categories was calculated. This statistical analysis reveals the distribution characteristics of customer dependence and engagement at the service level, helping financial institutions identify services with a high proportion of highly dependent customers and services requiring enhanced customer stickiness. Finally, the proportions of the two customer categories in each service were aggregated to form a complete customer distribution information matrix. This matrix visually demonstrates the ability of different services to attract and retain customers, as well as the distribution pattern of customer groups across these five service categories. Through these steps, the technical effect of refined customer segmentation and service evaluation is achieved. Financial institutions can adjust their service strategies based on customer distribution information to improve service quality and enhance customer dependence.

[0083] Through the above steps, the technical effect of finely identifying the distribution of customer dependence under different services is achieved, enabling financial institutions to adjust and optimize customer relationship management strategies based on the specific performance of each service, and further realize a deep understanding of customer groups at the service level and precise service configuration.

[0084] Optionally, in the method for determining the service strategy of a financial institution provided in Embodiment 1 of this application, multiple customers are clustered based on their dependence scores on the financial institution to obtain a second clustering result. This includes: summing the dependence scores of multiple customers on the financial institution to obtain a total dependence score; determining an average dependence score based on the number of customers and the total dependence score of the multiple customers; and dividing the multiple customers into a first category of customers and a second category of customers based on the average dependence score to obtain the second clustering result.

[0085] In this embodiment 1, to systematically identify the overall dependence of customers on financial institutions and to perform preliminary customer group classification accordingly, firstly, a summation operation is performed to add up the dependence scores of all customers, resulting in a total dependence score. Then, the total dependence score is divided by the number of customers to calculate the average dependence score. This average score provides a benchmark for subsequent customer classification, enabling financial institutions to assess whether the dependence of individual customers is higher or lower than the average level based on this standard.

[0086] Secondly, based on the calculated average dependency score, the customer group is divided into two categories: one category consists of customers with a dependency level higher than the average, defined as Category I customers; the other category consists of customers with a dependency level equal to or lower than the average, classified as Category II customers. This classification process is essentially a quantitative grading of customer dependency levels, which helps financial institutions identify core and marginal customers, laying the foundation for developing differentiated customer service strategies.

[0087] Finally, the compositional characteristics and proportions of the first and second customer groups are summarized and analyzed to generate a second clustering result. This result not only includes customer classification information but also reflects the overall dependence intensity distribution of the customer groups. Through the above steps, the technical effect of refined customer segmentation based on dependence level scoring is achieved. Financial institutions can use this to identify high-dependency customer groups, optimize resource allocation, improve attention and service quality for core customers, and simultaneously adopt appropriate service strategies for low-dependency customer groups, thereby improving customer satisfaction.

[0088] Optionally, in the method for determining the service strategy of a financial institution provided in Embodiment 1 of this application, the first type of customers and the second type of customers are clustered according to the financial institution's revenue information and the customer distribution information of each service to obtain a first clustering result. This includes: determining the average revenue information of each customer based on the financial institution's revenue information of multiple services corresponding to each customer in the multi-category indicator information; determining the customer proportion information of each customer in the customer group to which each customer belongs in the classification result based on the customer distribution information of each service for the classification result; and clustering the first type of customers and the second type of customers according to the average revenue information of each customer and the customer proportion information corresponding to each customer to obtain a first clustering result.

[0089] In this Example 1, to comprehensively assess the overall value of individual customers to financial institutions and, based on this, to conduct in-depth segmentation of the customer base, firstly, based on the revenue records of each customer using multiple services from various indicator information, statistical methods are used to calculate the average revenue information for each customer to the financial institution. This step aims to quantify the revenue brought to the financial institution by each customer, providing an important reference for subsequent customer value assessment.

[0090] Then, for each service's classification results—specifically, the third and fourth customer categories based on indicator scores—customer distribution information was analyzed to determine the proportion of each category within that service classification. Next, considering both the average revenue of each customer and their proportion within different service classifications, further cluster analysis was conducted on the first category (customers with above-average dependence) and the second category (customers with equal or below-average dependence).

[0091] In one optional embodiment, since a customer's dependence level is not directly proportional to their revenue contribution to the bank (for example, a highly dependent customer may not necessarily generate high revenue for the commercial bank), financial institutions can classify individual customers into four customer groups based on their dependence level scores on the customer's revenue contribution to the financial institution. These groups are: Group 1, with a high dependence score (i.e., the aforementioned Group 1 customers), high revenue contribution (the customer's revenue contribution is greater than the average revenue information of multiple customers), and a low proportion of customers (the aforementioned customer proportion information is less than or equal to a preset threshold); Group 2, with a high dependence score, low revenue contribution (the customer's revenue contribution is less than or equal to the average revenue information of multiple customers), and a high proportion of customers (the aforementioned customer proportion information is greater than a preset threshold); Group 3, with a low dependence score (i.e., the aforementioned Group 2 customers), high revenue contribution, and a low proportion of customers; and Group 4, with a low dependence score, low revenue contribution, and a high proportion of customers.

[0092] Through the above steps, the technical effect of refining customer group classification from the dual perspectives of economic benefits and dependence is achieved, providing strong data support and decision-making basis for financial institutions to implement personalized customer service strategies, optimize resource allocation, improve customer satisfaction, and enhance market competitiveness.

[0093] Furthermore, corresponding service strategies for financial institutions can be adopted for the four customer groups categorized in the above embodiments. The first customer group represents the financial institution's high-quality clients; this group should be provided with the best service, with close communication to ensure their needs are met promptly. For the second customer group, which has a large number of clients, more financial products can be recommended, such as those favored by this group or promotional activities. For the third customer group, which contributes significantly to revenue but has low dependence and a small number of clients, the focus should be on providing high-quality and personalized services to reduce customer churn. For the fourth customer group, which contributes very little to revenue and has low dependence, but constitutes a large proportion of clients, they should be guided to low-cost service channels (e.g., self-service banking, mobile banking applications) to reduce service costs.

[0094] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0095] In summary, the method for determining the service strategy of financial institutions provided in this application collects transaction data from multiple customers of the financial institution and extracts multiple types of indicator information from the transaction data. These multiple customers are those who use at least one of multiple services and whose age falls within a preset range. The method determines the dependence score of the multiple customers on the financial institution based on the multiple types of indicator information. It then clusters the multiple customers based on the dependence score and the multiple types of indicator information to obtain a first clustering result. Finally, it determines the customer group information corresponding to each customer based on the first clustering result. This solves the problem in related technologies where financial institutions classify customers based solely on a single transaction indicator when determining customer group information, leading to inaccurate classification results.

[0096] By collecting transaction data from multiple customers within financial institutions and extracting various indicators including the most recent transaction time, transaction frequency, and transaction amount, a comprehensive quantification of customers' multidimensional behavioral characteristics can be achieved, thus enabling the construction of a comprehensive dependency scoring system. Simultaneously, by combining dependency scoring with multiple indicator information for cluster analysis, the customer group is subdivided into several primary clusters with different behavioral patterns. This achieves multi-level and multi-angle precise customer classification, further improving the accuracy of customer classification and optimizing the financial institution's customer management strategies. These steps overcome the limitations of related technologies that rely solely on a single transaction indicator for classification, ensuring the comprehensiveness and effectiveness of financial institutions in identifying customer segment information.

[0097] Example 2

[0098] This application also provides an apparatus for determining a financial institution's service strategy. It should be noted that this apparatus can be used to execute the method for determining a financial institution's service strategy provided in this application. The apparatus for determining a financial institution's service strategy provided in this application is described below.

[0099] According to an embodiment of this application, an apparatus for implementing the above-described method for determining financial institution service strategies is also provided. Figure 4 This is a schematic diagram of a device for determining a financial institution's service strategy according to Embodiment 2 of this application. Figure 4 As shown, the device includes: a data acquisition unit 401, a calculation unit 402, a clustering unit 403, and a determination unit 404.

[0100] Specifically, the collection unit 401 is used to collect transaction data of multiple customers in a financial institution and extract multiple types of indicator information from the transaction data. Among them, multiple customers are customers who use at least one of multiple services and whose age is within a preset range.

[0101] The calculation unit 402 is used to determine the degree of dependence of multiple customers on financial institutions based on multiple types of indicator information.

[0102] Clustering unit 403 is used to cluster multiple customers based on dependency scores and multi-category indicator information to obtain the first clustering result.

[0103] The determination unit 404 is used to determine the customer group information corresponding to each customer among multiple customers based on the first clustering result.

[0104] The financial institution service strategy determination device provided in this application embodiment collects transaction data of multiple customers in the financial institution through a collection unit 401 and extracts multiple types of indicator information from the transaction data. The multiple customers are those who use at least one of multiple services and whose age is within a preset range. The calculation unit 402 determines the dependence score of multiple customers on the financial institution based on the multiple types of indicator information. The clustering unit 403 clusters the multiple customers based on the dependence score and the multiple types of indicator information to obtain a first clustering result. The determination unit 404 determines the customer group information corresponding to each customer in the multiple customers based on the first clustering result. This solves the problem in related technologies where financial institutions classify customers based on only a single transaction indicator when determining the customer group information corresponding to customers, resulting in inaccurate classification results.

[0105] By collecting transaction data from multiple customers within financial institutions and extracting various indicators including the most recent transaction time, transaction frequency, and transaction amount, a comprehensive quantification of customers' multidimensional behavioral characteristics can be achieved, thus enabling the construction of a comprehensive dependency scoring system. Simultaneously, by combining dependency scoring with multiple indicator information for cluster analysis, the customer group is subdivided into several primary clusters with different behavioral patterns. This achieves multi-level and multi-angle precise customer classification, further improving the accuracy of customer classification and optimizing the financial institution's customer management strategies. These steps overcome the limitations of related technologies that rely solely on a single transaction indicator for classification, ensuring the comprehensiveness and effectiveness of financial institutions in identifying customer segment information.

[0106] Optionally, in the financial institution service strategy determination device provided in Embodiment 2 of this application, the multiple services include at least: a first type of service and a second type of service. The first type of service represents transaction services, and the second type of service represents non-transaction services. The first type of service includes at least: a first service and a second service. The first service represents current deposit service, and the second service represents bank card payment service. The second type of service includes at least: a third service, a fourth service, and a fifth service. The third service represents time deposit service, the fourth service represents asset management service, and the fifth service represents credit service.

[0107] Optionally, in the financial institution service strategy determination device provided in Embodiment 2 of this application, the multiple services include at least: a first service, a second service, a third service, a fourth service, and a fifth service. The first service represents a current deposit service, the second service represents a bank card payment service, the third service represents a time deposit service, the fourth service represents an asset management service, and the fifth service represents a credit service. The aforementioned acquisition unit 401 includes an extraction subunit, used to extract indicator information of each service from the transaction data based on transaction time indicators, transaction frequency indicators, and transaction amount indicators to obtain multiple types of indicator information. Among them, the multiple types of indicator information include at least: the most recent transaction time, service duration, balance information, and financial institution revenue information for each service. The indicator information of the first service also includes at least: transaction amount and transaction frequency. The indicator information of the second service also includes at least: transaction amount, consumption frequency, number of active card usages, number of active cards, number of inactive cards, and credit limit information. The indicator information of the third service also includes at least: the number of service holders. The indicator information of the fourth service also includes at least: the number of applications, the type of service held, and the number of service held. The indicator information of the fifth service also includes at least: the number of repayments and the number of service holders.

[0108] Optionally, in the financial institution service strategy determination device provided in Embodiment 2 of this application, the aforementioned calculation unit 402 includes: a processing subunit, configured to, for each of the multiple customers, standardize each indicator included in each category of indicators corresponding to each service in the multiple categories of indicator information to obtain each indicator score of each category of indicators corresponding to each service, wherein the value of each indicator score is an integer value within a preset numerical range; a first calculation subunit, configured to, based on each indicator score of each category of indicators corresponding to each service and the preset weight information of each indicator, determine the indicator score of each category of indicators corresponding to each service, and perform a product operation on the indicator scores of each category of indicators corresponding to each service to obtain the indicator score of each service; a determination subunit, configured to, based on the degree of influence of each service on the dependence score, determine the target weight information of the indicator score of each service; and a second calculation subunit, configured to, based on the indicator score of each service and the target weight information of the indicator score of each service, determine the dependence score of multiple customers on the financial institution.

[0109] Optionally, in the financial institution service strategy determination device provided in Embodiment 2 of this application, the clustering unit 403 includes: a first clustering subunit, used to cluster multiple customers based on the dependence rating of multiple customers on financial institutions to obtain a second clustering result, wherein the second clustering result includes at least a first type of customer and a second type of customer, and the first type of customer has a higher dependence on financial institutions than the second type of customer; a third calculation subunit, used to determine the customer distribution information of each service based on the indicator rating of each service corresponding to each customer; and a second clustering subunit, used to cluster the first type of customer and the second type of customer based on the financial institution's revenue information and the customer distribution information of each service respectively to obtain the first clustering result.

[0110] Optionally, in the financial institution service strategy determination device provided in Embodiment 2 of this application, the aforementioned third calculation subunit includes: a first calculation module, used to determine the average indicator score of each service based on the indicator score of each service corresponding to each customer for each service among multiple services; a classification module, used to classify multiple customers based on the average indicator score of each service to obtain the classification result corresponding to each service, wherein the classification result corresponding to each service includes at least a third type of customer and a fourth type of customer, and for any service, the indicator score of the service corresponding to the third type of customer is greater than the average indicator score of the service, and the indicator score of the service corresponding to the fourth type of customer is less than or equal to the average indicator score of the service; and a second calculation module, used to determine the proportion of the number of third type of customers and the proportion of the number of fourth type of customers in each service based on the classification result corresponding to each service to obtain customer distribution information for each service.

[0111] Optionally, in the financial institution service strategy determination device provided in Embodiment 2 of this application, the first clustering subunit includes: a third calculation module, used to sum the dependence scores of multiple customers on financial institutions to obtain a total dependence score; a fourth calculation module, used to determine an average dependence score based on the number of customers and the total dependence score of multiple customers; and a division module, used to divide multiple customers into a first type of customer and a second type of customer based on the average dependence score to obtain a second clustering result.

[0112] Optionally, in the financial institution service strategy determination device provided in Embodiment 2 of this application, the second clustering subunit includes: a fifth calculation module, used to determine the average revenue information of each customer based on the financial institution revenue information of multiple services corresponding to each customer in the multi-category indicator information; a determination module, used to determine the customer proportion information of each customer in the customer group to which each customer belongs in the classification result based on the customer distribution information of each service; and a clustering module, used to cluster the first type of customer and the second type of customer respectively based on the average revenue information of each customer and the customer proportion information corresponding to each customer to obtain the first clustering result.

[0113] It should be noted that the acquisition unit 401, calculation unit 402, clustering unit 403, and determination unit 404 mentioned above correspond to steps S201 to S204 in Embodiment 1. The two modules and their corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above modules can also be part of a device and run in the computer terminal 10 provided in Embodiment 1.

[0114] Example 3

[0115] Embodiments of this application may provide an electronic device. Figure 5 This is a schematic diagram of an electronic device for determining a financial institution's service strategy according to Embodiment 3 of this application. Figure 5 As shown, the electronic device may include: one or more ( Figure 5 (Only one is shown) processor 502, memory 504, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0116] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in this application embodiment. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned method for determining the service strategy of financial institutions. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0117] Those skilled in the art will understand that Figure 5 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 5 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 5 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 5 The different configurations shown.

[0118] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0119] Example 4

[0120] Embodiments of this application also provide a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the method for determining the financial institution service strategy provided in Embodiment 1.

[0121] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0122] This application also provides a computer program product that, when executed on a data processing device, is suitable for performing the steps of a method for determining a financial institution's service strategy.

[0123] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0124] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0125] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0126] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0127] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0128] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0129] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for determining a customer group, characterized in that, include: Collect transaction data from multiple customers in financial institutions and extract multiple types of indicator information from the transaction data. The multiple customers are those who use at least one of multiple services and whose age is within a preset range. The degree of dependence of the various customers on the financial institution is determined based on the aforementioned multiple indicator information. Based on the dependency score and the multi-category indicator information, the multiple customers are clustered to obtain the first clustering result; Based on the first clustering result, the customer group information corresponding to each of the multiple customers is determined.

2. The method according to claim 1, characterized in that, The multiple services include at least: a first service, a second service, a third service, a fourth service, and a fifth service. The first service represents a current deposit service, the second service represents a bank card payment service, the third service represents a time deposit service, the fourth service represents an asset management service, and the fifth service represents a credit service. Multiple types of indicator information are extracted from the transaction data, including: Based on transaction time-related indicators, transaction frequency-related indicators, and transaction amount-related indicators, the indicator information of each of the multiple services in the transaction data is extracted to obtain the multiple types of indicator information; The various types of indicator information include at least the following: the most recent transaction time, service duration, balance information, and financial institution revenue information for each service. The indicator information for the first service also includes at least the transaction amount and number of transactions. The indicator information for the second service also includes at least the transaction amount, number of consumptions, number of active card uses, number of active cards, number of inactive cards, and credit limit information. The indicator information for the third service also includes at least the number of service holders. The indicator information for the fourth service also includes at least the number of applications, service holding types, and service holding numbers. The indicator information for the fifth service also includes at least the number of repayments and the number of service holders.

3. The method according to claim 1, characterized in that, Based on the aforementioned multiple indicator information, a score is determined on the degree of dependence of the various customers on the financial institution, including: For each of the multiple customers, each indicator included in each category of indicators corresponding to each service in the multiple types of indicator information is standardized to obtain the score of each indicator for each category of indicators corresponding to each service. The value of each indicator score is an integer value within a preset numerical range. Based on the score of each indicator for each category of each service and the preset weight information of each indicator, the score of each indicator for each service is determined, and the score of each indicator for each category of each service is multiplied to obtain the score of each service. The target weight information for the indicator score of each service is determined based on the degree of influence of each service on the dependence score; The dependence rating of the multiple customers on the financial institution is determined based on the indicator score of each service and the target weight information of the indicator score of each service.

4. The method according to claim 3, characterized in that, Based on the dependency score and the multi-category indicator information, the multiple customers are clustered to obtain a first clustering result, including: The multiple customers are clustered based on their dependence scores on the financial institution to obtain a second clustering result. The second clustering result includes at least a first group of customers and a second group of customers, where the first group of customers has a higher dependence on the financial institution than the second group of customers. Determine the customer distribution information for each service based on the indicator scores for each service corresponding to each customer; Based on the financial institution's revenue information and the customer distribution information for each service, the first type of customers and the second type of customers are clustered respectively to obtain the first clustering result.

5. The method according to claim 4, characterized in that, Based on the performance metrics scores for each service corresponding to each customer, the customer distribution information for each service is determined, including: For each of the multiple services, the average indicator score for each service is determined based on the indicator score for each service corresponding to each customer; The multiple customers are classified according to the average indicator score of each service to obtain the classification result corresponding to each service. The classification result corresponding to each service includes at least a third type of customer and a fourth type of customer. For any service, the indicator score of the third type of customer for that service is greater than the average indicator score of that service, and the indicator score of the fourth type of customer for that service is less than or equal to the average indicator score of that service. Based on the classification results corresponding to each service, determine the proportion of customers in the third category and the proportion of customers in the fourth category in each service to obtain customer distribution information for each service.

6. The method according to claim 4, characterized in that, Based on the customer dependence ratings of the multiple customers on the financial institution, the multiple customers are clustered to obtain a second clustering result, including: The dependence scores of the multiple customers on the financial institution are summed to obtain the total dependence score. The average dependency score is determined based on the number of customers of the multiple customers and the sum of the dependency scores; Based on the average dependency score, the multiple customers are divided into a first category of customers and a second category of customers, thus obtaining the second clustering result.

7. The method according to claim 4, characterized in that, Based on the financial institution's revenue information and the customer distribution information for each service, the first type of customers and the second type of customers are clustered respectively to obtain the first clustering result, including: The average revenue information for each customer is determined based on the financial institution revenue information for multiple services corresponding to each customer in the aforementioned multi-category indicator information. For each service, the customer percentage information of each customer in the customer group to which each customer belongs in the classification result is determined based on the customer distribution information of each service. Based on the average revenue information of each customer and the customer proportion information corresponding to each customer, the first type of customers and the second type of customers are clustered respectively to obtain the first clustering result.

8. A customer group determination device, characterized in that, include: The data collection unit is used to collect transaction data from multiple customers in a financial institution and extract multiple types of indicator information from the transaction data. The multiple customers are those who use at least one of multiple services and whose age is within a preset range. A calculation unit is used to determine the dependence rating of the multiple customers on the financial institution based on the multiple types of indicator information; A clustering unit is used to cluster the multiple customers based on the dependency score and the multi-category indicator information to obtain a first clustering result; The determining unit is used to determine the customer group information corresponding to each of the multiple customers based on the first clustering result.

9. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the customer group determination method according to any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the steps of the customer group determination method according to any one of claims 1 to 7.

Images