mall&expo平台湖北省用户电话增值服务购买分析数据

基于精细化运营的需求，需要精准地对购买增值服务的用户进行分类，确定高价值用户和低价值用户群体，从而为不同价值的用户提供差异化服务和营销策略。1、数据收集：采集自在本企业电商网站mall&expo的电话增值服务销售数据；
2、特征选择：选择购买的订单数、调整后订单金额和浏览次数作为特征值。结合实际情况，通过调整金额特征的权重系数来确保订单金额在聚类决策中占主导地位，本模型的权重系数为订单金额*2作为调整后订单金额。
3、使用轮廓系数方法确定最佳聚类数k=4。
4、使用选定的特征值和k值，运行k-means算法对用户进行聚类。算法随机初始化k个质心，然后迭代地将每个样本分配给最近的质心，并更新质心位置，直到满足收敛条件。
5、分析每个簇的特征，包括簇内用户的平均购买订单数、订单金额和商品浏览次数等。根据业务目标和簇的特征，实现客户的分类。结合聚类分组数量和分组阀值及企业实际情况，调优用户的分类结果，将用户最终分类为运营所需的4类群体“A.高价值用户、B.潜力发展用户、C.一般价值用户、D.低价值用户”，用3表示高价值用户，2表示低价值用户，1表示一般价值用户，0表示潜力发展用户，从而帮助运营实现精准营销和服务。

In order to support refined operational practices, there is a requirement to accurately classify users who purchase paid value-added services, distinguish high-value and low-value user cohorts, and thereby deliver tailored services and marketing strategies for users across different value tiers.
1. Data Collection: The dataset is derived from the sales data of telephone-based value-added services on the enterprise's e-commerce platform "mall&expo".
2. Feature Selection: Three feature variables are selected: the number of placed orders, adjusted order amount, and number of product browsing sessions. In line with actual business scenarios, the weight of the order amount feature is adjusted to ensure its leading role in clustering decision-making. For this model, the adjusted order amount is calculated as order amount multiplied by 2.
3. Optimal Cluster Number Determination: The silhouette coefficient method is utilized to determine the optimal number of clusters, with k=4 selected as the final cluster count.
4. Clustering Implementation: Using the selected features and the determined k value, the k-means clustering algorithm is executed to cluster users. The algorithm randomly initializes k cluster centroids, then iteratively assigns each sample to the nearest centroid and updates the centroid positions until convergence conditions are satisfied.
5. Cluster Analysis and Final User Classification: Analyze the characteristics of each cluster, including the average number of purchase orders, order amount, and product browsing frequency of users within the cluster. Complete the initial user classification based on business objectives and cluster characteristics. Further optimize the classification results by combining the number of cluster groups, group thresholds, and actual enterprise operational conditions, and finally categorize users into 4 target groups required for operations:
- A. High-value users
- B. Potential development users
- C. General-value users
- D. Low-value users
The corresponding classification labels are assigned as follows: 3 for high-value users, 2 for low-value users, 1 for general-value users, and 0 for potential development users, so as to enable operations teams to implement precise marketing and service strategies.

搜集汇总

数据集介绍

特点

该数据集包含730条记录，每月更新，主要用于分析用户购买电话增值服务的行为，通过k-means算法将用户分为高价值、潜力发展、一般价值和低价值四类，以支持差异化服务和营销策略。