湖北省闯货平台客户消费行为分析数据

通过对闯货平台湖北地区的用户进行分层,平台可以识别高价值用户,提供差异化的服务和营销策略,提高用户粘性和忠诚度。RFM模型还可以与其他用户属性数据结合,实现精细化的客户细分和精准营销。此外,通过分析用户RFM综合评分的变化趋势,平台可以预测用户生命周期价值,优化用户留存策略。RFM模型通过计算用户最近一次消费时间(R)、消费频率(F)和消费金额(M)这三个维度来评估用户价值。对于R维度,根据用户最后支付时间距离当前分析时间的天数（D）,划分为5个等级: 0≤D≤4为5分，4＜D≤7 为4分，7＜D≤15 为3分，15＜D≤29为2分，D ＞29为1分；对于F维度,根据用户在过去180天订单数量（C）,划分为5个等级: 0≤C≤1为1分，2≤C≤5 为2分，6≤C≤11 为3分，12≤C≤19为4分，C≥20为5分；对于M维度,根据用户在过去180天消费金额（G）,划分为5个等级，G≥2000为5分，1200≤G＜2000为4分，800≤G＜1200为3分，400≤G＜800为2分，0≤G＜400为1分。RFM综合评分（X）=0.3*R+0.4*F+0.6*M，再根据RFM综合评分（X）对客户进行分类，0≤X＜1为一般客户，1≤X＜2为新客户，2≤X＜4 为潜力深耕客户，4≤X＜6为重要维系客户，X ≥6为高粘度客户，基于消费频次、消费金额等不同维度获得的聚类分组成果，对聚类分组数量和分组阀值、以及维度权重进行人为干预，使客户分类趋于合理。By segmenting users in the Hubei region of the Chuanghuo Platform, the platform can identify high-value users, deliver differentiated services and marketing strategies, and enhance user stickiness and loyalty. The RFM model can also be combined with other user attribute data to achieve refined customer segmentation and precision marketing. Furthermore, by analyzing the changing trends of users' comprehensive RFM scores, the platform can predict user lifetime value and optimize user retention strategies. The RFM model evaluates user value by calculating three dimensions: recency of last purchase (R), purchase frequency (F), and consumption monetary value (M). For the R dimension, users are divided into 5 levels based on the number of days (D) between their last payment time and the current analysis time: 5 points for 0≤D≤4, 4 points for 4<D≤7, 3 points for 7<D≤15, 2 points for 15<D≤29, and 1 point for D>29; For the F dimension, users are divided into 5 levels based on the number of orders (C) in the past 180 days: 1 point for 0≤C≤1, 2 points for 2≤C≤5, 3 points for 6≤C≤11, 4 points for 12≤C≤19, and 5 points for C≥20; For the M dimension, users are divided into 5 levels based on their consumption amount (G) in the past 180 days: 5 points for G≥2000, 4 points for 1200≤G<2000, 3 points for 800≤G<1200, 2 points for 400≤G<800, and 1 point for 0≤G<400. The comprehensive RFM score (X) is calculated as 0.3*R + 0.4*F + 0.6*M. Customers are then categorized based on their comprehensive RFM score (X): general customers for 0≤X<1, new customers for 1≤X<2, potential deep-cultivated customers for 2≤X<4, important retention customers for 4≤X<6, and high-stickiness customers for X≥6. Based on the clustering grouping results obtained from different dimensions such as consumption frequency and consumption amount, manual intervention is conducted on the number of clustering groups, grouping thresholds, and dimension weights to make customer classification more reasonable.

搜集汇总

数据集介绍

特点

该数据集包含991条湖北省闯货平台客户的消费行为数据，每日更新，应用RFM模型对用户进行分层，以识别高价值用户并提供差异化服务和营销策略。数据涵盖用户编号、省份、城市、消费金额、订单数量等字段，适用于客户细分和精准营销场景。