基于RFM模型的充电桩用户分级评价数据

通过对乌海市公共汽车租赁服务公司充电管理平台的用户微信充值行为数据进行深入分析，采用RFM模型来对用户进行细致的价值评级，通过用户的最近一次消费时间（Recency, R）、一定时期内的消费频次（Frequency, F）以及同一时期内的消费金额（Monetary, M）三个维度，来评估用户的价值和潜在贡献。通过精细化的用户价值管理，为平台的不同价值用户群体提供个性化的服务方案，不仅有助于优化积分和优惠券等激励措施的运营策略，还能为其他营销活动提供坚实的数据支持。具体而言，通过识别出最近消费、消费频次高、消费金额大的高价值用户，并为其提供更加定制化的服务和优惠，对于消费频次较低或消费金额较小的用户，可设计针对性的营销活动，以激发其消费潜力，提升用户活跃度和忠诚度。1、数据采集：从乌海市公共汽车租赁服务公司充电管理平台，提取平台会员管理中充值订单数据，以手机号为唯一标识对采集到的数据进行脱敏、清洗、聚集、分析。2、数据加工：计算充值到数据处理时间间隔(天)=数据处理时间-充值时间，利用MINIF函数求单个用户R，利用COUNT函数求单个用户F、单个用户M，利用AVERAGE函数求所有用户平均R、所有用户平均F、所有用户平均M，再利用IF函数结合赋分法求用户综合评分=IF(单个用户R<所有用户平均R,1,-1)+IF(单个用户F>所有用户平均F,1,-1)+IF(单个用户M>所有用户平均M,1,-1)，A∈[-3，3]3、数据分级：用户综合评分大于1评为A类，用户综合评分等于1评为B类，用户综合评分小于1评为C类。This study conducts an in-depth analysis of users' WeChat top-up behavior data from the charging management platform of Wuhai City Public Bus Rental Service Company, and adopts the RFM model to perform detailed user value rating. User value and potential contribution are evaluated from three dimensions: Recency (R, time since the user's last top-up), Frequency (F, top-up frequency within a specific period), and Monetary (M, total top-up amount within the same period). Through refined user value management and personalized service plans for user groups of different value tiers, this work not only helps optimize the operation strategies of incentive measures such as points and coupons, but also provides solid data support for other marketing activities. Specifically, by identifying high-value users with recent top-ups, high top-up frequency and large transaction amount and providing them with more customized services and preferential treatments, targeted marketing campaigns can be designed for users with low top-up frequency or small transaction amount to stimulate their consumption potential, thereby enhancing user activity and loyalty. 1. Data Collection: Extract top-up order data from the member management module of the charging management platform of Wuhai City Public Bus Rental Service Company. Desensitize, clean, aggregate and analyze the collected data using phone numbers as the unique identifier. 2. Data Processing: Calculate the time interval (in days) from top-up to data processing time = data processing time - top-up time. Use the MINIF function to obtain the Recency (R) value of individual users, use the COUNT function to obtain the Frequency (F) and Monetary (M) values of individual users, and use the AVERAGE function to calculate the average R, average F and average M values across all users. Then derive the comprehensive user score via the IF function combined with the scoring method: Comprehensive User Score = IF(Single User R < Average R of All Users, 1, -1) + IF(Single User F > Average F of All Users, 1, -1) + IF(Single User M > Average M of All Users, 1, -1), where A ∈ [-3, 3] 3. Data Classification: Classify users into Category A if their comprehensive user score is greater than 1, Category B if the score equals 1, and Category C if the score is less than 1.

搜集汇总

数据集介绍

特点

该数据集采用RFM模型对充电桩用户进行价值评级，包含用户充值行为数据，每日更新，适用于优化用户服务和营销策略。