Automobile industry customer value evaluation method based on RFM model
By increasing the recommended purchase times, brand loyalty and consumption level indicators in the RFM model, and conducting unsupervised clustering analysis, the problem of inability to accurately identify the target customer group in the existing technology is solved, and more accurate customer value assessment and Personalized service support.
Patent Information
- Application Number
- CN202411037597.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-11-26
AI Technical Summary
The existing RFM model cannot accurately identify and understand the target customer group in the automotive industry customer value assessment. It is not enough to accurately define customer value based solely on the recent purchase time, frequency and amount, and misses key factors such as vehicle mileage and usage habits.
Based on the RFM model, the number of recommended purchases, brand loyalty and consumption level related indicators are added, and customer value evaluation is conducted in combination with the characteristics of the automobile industry, and the evaluation results are stored in the customer relationship management system.
It provides more accurate customer value assessment, meets actual business needs, supports personalized services and differentiated operation strategies, and improves the accuracy of customer identification and grading.
Smart Images

Figure CN119027154A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer software, and in particular to a method for evaluating customer value in the automotive industry based on a RFM model. Background Art
[0002] In recent years, with the development of Internet technology, in the automotive industry, in order to help automotive after-sales service providers and other companies provide matching business services to their customers more accurately, the existing technology often adopts the customer value evaluation analysis model RFM, which evaluates the customer value in the enterprise organization based on the customer's historical transaction data, and then formulates business services that match the customer's value stage for the customer, so as to improve the business service efficiency of the enterprise. The factors in the customer value evaluation analysis model RFM mainly revolve around three factors, namely R (Recency): the last purchase time, F (Frequency): purchase frequency, and M (Monetary): purchase amount.
[0003] However, existing technologies perform customer segmentation entirely based on the RFM model, which results in missing key factors. For example, the demand for after-sales service for automobiles is usually closely related to the mileage and usage habits of the vehicle, rather than simply based on the frequency of customer returns to the store. The demand for automobiles is closely related to factors such as vehicle age and mileage, and customers' consumption is not limited to the purchase of the car itself, but also includes insurance, online shopping and other consumption scenarios. Therefore, evaluating customer value based solely on the time, frequency and amount of recent purchases may not be enough to accurately define the company's customer value. Summary of the invention
[0004] In view of the defects in the prior art, the purpose of the present invention is to provide a customer value assessment method for the automotive industry based on the RFM model, to solve the problem in the prior art that the target customer group cannot be accurately identified and understood, and to propose a customer value assessment method that is more in line with actual business.
[0005] In order to achieve the above technical effects, the present invention adopts the following technical solutions:
[0006] The present invention provides a method for evaluating customer value in the automotive industry based on the RFM model, comprising:
[0007] Information collection: obtaining basic data;
[0008] Model optimization: retain the most recent purchase time, purchase frequency, and purchase amount, and add indicators related to the number of recommended purchases, brand loyalty, and consumption level;
[0009] Value assessment: Based on the optimized model, unsupervised cluster analysis is performed on the basic data to obtain assessment data information;
[0010] Data application: Based on the evaluation data information, customers are graded according to preset evaluation rules, and evaluation result data is obtained and stored in the customer relationship management system for user reference.
[0011] Preferably, the recommended purchase number related indicator includes the number of times a customer successfully recommends a new user to purchase a vehicle;
[0012] The brand loyalty related indicators include at least one of the following indicators: the number of customer visits to the store, the number of visits to the store in the past year, the average interval between visits to the store, and the time interval between the last visit to the store and the current visit;
[0013] The consumption level-related indicators include at least one of the following indicators: total customer consumption, unit mileage consumption, total car purchase consumption, total after-sales repair consumption, total maintenance consumption, total renewal and value-added service consumption, after-sales repair consumption in the most recent year, maintenance consumption in the most recent year, renewal and value-added service consumption in the most recent year.
[0014] Preferably, the preset evaluation rule is to classify customers into high-value customers, key retention customers, key development customers, new customers, general customers, and low-value customers after taking preset weights for the evaluation indicators, and assign characteristic information to each customer group based on the comparison information between each customer group and the overall indicators.
[0015] Compared with the prior art, the present invention has the following beneficial effects:
[0016] 1. The customer value assessment method for the automotive industry based on the RFM model provided by the present invention is not limited to the assessment factors of the traditional RFM model. It supplements and expands the assessment factors in combination with the characteristics of the automotive industry, which is more in line with actual business. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:
[0018] Figure 1 The figure is a schematic diagram of a method flow of an embodiment of the present invention. DETAILED DESCRIPTION
[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.
[0020] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.
[0021] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in the subsequent figures. In addition, all directional indications in this application (such as up, down, left, right, front, back, bottom...) are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the figures). If the specific posture changes, the directional indication will also change accordingly. Furthermore, the descriptions involving "first", "second", etc. in the application are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Specific embodiments
[0023] The technical solution of the present invention is described in detail below through examples. The following examples are merely exemplary and can only be used to explain and illustrate the technical solution of the present invention, but are not to be construed as limiting the technical solution of the present invention.
[0024] This embodiment provides a customer value assessment method based on the RFM model to improve the accuracy of customer identification and differentiation and provide data support for subsequent personalized services. This embodiment uses customer information from multiple channels as the data basis, integrates and manages information through the CRM system (customer relationship management system), generates multi-dimensional customer indicator definitions in the enterprise data center, applies the optimized RFM model method, develops a customer value assessment method suitable for the automotive industry, and uses unsupervised clustering algorithms to calculate customer levels and customer value labels based on weighted attributes.
[0025] Specifically, this embodiment uses Python data analysis technology and K-means clustering algorithm to perform cluster analysis on the customer data of after-sales service of the enterprise in the past year, divides the customers into six groups according to the weights of different attributes, and compares the statistical indicators of each group with the overall statistical value. Furthermore, by comparing the statistical value of the customer indicators of each group with the overall statistical value, the specific characteristics of each group are clarified.
[0026] It should be noted that the implementation environment scenario diagram of the customer value assessment method provided in this embodiment is only an example. The implementation environment scenario of the customer value assessment method described in the embodiment of this application is to more clearly illustrate the technical solution of the embodiment of this application, and does not constitute a limitation on the technical solution provided in the embodiment of this application. It is known to those skilled in the art that with the evolution of customer value assessment and the emergence of new business scenarios, the technical solution provided in this application is also applicable to similar technical problems.
[0027] like Figure 1 As shown, this embodiment mainly includes the following steps:
[0028] In step S1, data collection is performed to obtain basic data, vehicle data, behavior data, and preference data associated with the target object through online or offline channels.
[0029] In step S2, the indicators are optimized. In combination with the characteristics of the automobile industry, specific indicators such as the number of recommended purchases, brand loyalty, and consumption level are added to the original RFM model. In actual operation, considering that automobile sales are the core business of ordinary automobile manufacturers, and commercial vehicle customers often consider the recommendations of family or friends when making purchasing decisions; brand loyalty evaluation is based on the interval and frequency of customers' return to the store, and the interval between return to the store is recorded by after-sales service; consumption level is comprehensively analyzed through the three dimensions of the customer's total online and offline consumption amount, the consumption amount calculated by mileage, and the consumption amount calculated by the number of times. The unit mileage consumption indicator is specially introduced to reduce the impact of the vehicle age variable on the evaluation results. The specific indicator design is shown in the following table:
[0030]
[0031] In step S3, customer value assessment is performed. After obtaining the basic data, clustering can be performed based on the optimized indicators to obtain at least one category set and the category label corresponding to the category set. Among them, there are many ways to cluster the customer to be evaluated based on the transaction indicator. For example, an unsupervised clustering algorithm (such as K-Means algorithm) can be used to cluster the customer to be evaluated based on the transaction indicator. After obtaining a detailed data set, this embodiment uses the RFM model after optimizing the indicators and combines the customer lifetime value (CLV) evaluation system. Through Python data analysis and K-means clustering algorithm, the customer data of the company's after-sales service in the past year is clustered. According to the weights of different attributes, the customers are divided into six groups, and the statistical indicators of each group are compared with the overall. When determining the relative weight of each indicator, refer to the product life cycle theory and consider the differences in the contribution of different product life cycle stages to the enterprise value. Further, by comparing the customer indicator statistics of each group with the overall statistics, the specific characteristics of each group are clarified. The company's customer value assessment results and customer classification data are shown in the following table.
[0032]
[0033] In step S4, the evaluation results are applied and optimized. The evaluation results are stored in the company's CRM system, which supports custom customer tags, allowing the team to quickly identify characteristics based on customer value. The customer classification tags in the CRM are displayed on the follow-up interface of the mobile terminal, helping front-line employees to quickly understand customer attributes and implement corresponding marketing strategies, and formulate marketing plans based on this, maintain relationships, and increase customer return rates and satisfaction.
[0034] Customer tag definition is the most critical step after collecting and managing customer information, and its purpose is to filter out the types of information that are valuable to the company. This process not only provides a basis for front-line staff who contact customers to collect customer information, but also accurately classifies potential and existing customers and labels them with specific customer tags based on a detailed analysis of key customer characteristics and the company's resource advantages in the field of complete vehicles and parts. Specifically, the classification of relevant tags can be considered: car purchase intention, including channel retention, price intention, interaction frequency, small order messages, brand awareness, parameter preferences; function use, including length of stay, number of active times, loading time, system feedback, retention rate, and bounce rate; conversion value, including recommended purchases, second-hand car evaluations, return to the factory, activity frequency, consumption amount, and purchase interval.
[0035] The method provided in this embodiment optimizes the model based on the RFM model, supplements and expands the evaluation factors in combination with the characteristics of the automobile industry, provides key data support for differentiated operation strategies, designs more appropriate customer indicators based on various dimensions of customer data and stores them in the CRM system, and supports dynamic update and maintenance.
[0036] The above describes the specific embodiments of the present invention. Based on the above description, relevant personnel can make various changes and modifications without departing from the technical concept of the present invention.
Claims
1. A customer value assessment method for the automotive industry based on the RFM model, characterized in that: include: Information collection: obtaining basic data; Model optimization: retain the most recent purchase time, purchase frequency, and purchase amount, and add indicators related to the number of recommended purchases, brand loyalty, and consumption level; Value assessment: Based on the optimized model, unsupervised cluster analysis is performed on the basic data to obtain assessment data information; Data application: Based on the evaluation data information, customers are graded according to preset evaluation rules, and evaluation result data is obtained and stored in the customer relationship management system for user reference.
2. According to claim 1, a method for evaluating customer value in the automotive industry based on the RFM model is characterized in that: The recommended purchase frequency related indicator includes the number of times a customer successfully recommends a new user to purchase a vehicle; The brand loyalty related indicators include at least one of the following indicators: the number of customer visits to the store, the number of visits to the store in the past year, the average interval between visits to the store, and the time interval between the last visit to the store and the current visit; The consumption level-related indicators include at least one of the following indicators: total customer consumption, unit mileage consumption, total car purchase consumption, total after-sales repair consumption, total maintenance consumption, total renewal and value-added service consumption, after-sales repair consumption in the most recent year, maintenance consumption in the most recent year, renewal and value-added service consumption in the most recent year.
3. The method for evaluating customer value in the automotive industry based on the RFM model according to claim 1, characterized in that: The preset evaluation rules are as follows: after taking preset weights for the evaluation indicators, customers are divided into high-value customers, key retention customers, key development customers, new customers, general customers, and low-value customers, and characteristic information is assigned to each customer group based on the comparison information between each customer group and the overall indicators.
Citation Information
Patent Citations
User feature data processing method and device
CN106022800A
Automobile industry customer value analysis system
CN112256759A
Reusable user car purchase intention rating method and device
CN117670407A
Cited By
Customer classification evaluation method based on RFM model
CN119295125A
Security customer analysis method, storage medium and computer equipment
CN119624649A
A method for analyzing securities customers, a storage medium, and a computer device
CN119624649B
Consumption decline prediction method and system for gas station customers
CN119693048A
