芜湖地区教育咨询客户评级数据

此数据是通过2024年1月1日-2025年7月1日营销活动与教育芜湖地区意向客户建立联系，对意向客户的反馈行为，定义用户行为系数，分析用户购买意向来预测用户销售转化率，并根据用户购买历史数据，对用户忠诚度进行评级，帮助企业定位活动完成情况，分析营销活动的有效性，为企业不同类型活动的策划以及活动推广营销策略提供数据支持。该数据方法可广泛应用于教育服务、咨询行业等单位，有助于企业通过此类分析数据来制定运营策略和营销方式，节省成本、提升营销效果和用户忠诚度。数据采集：收集2024年1月1日-2025年7月1日营销活动数据进行加工。数据处理：取用户ID为唯一标识，根据数据来源，对原始数据经过清洗去重，根据用户行为定义用户行为系数，通过用户购买意向预测用户销售转化率，结合用户购买历史数据确定用户忠诚度评级。 数据加工：该数据集中“营销方式”：短信、邮件、超级短信、微信模板消息、AI外呼、小程序订阅消息、抖音短信、企微消息；“用户行为”：点击、回复、退订、打开、提交、分享；“用户行为系数”：点击(0.2)、回复(0.5)、退订(0.1)、打开(0.4)、提交(0.6)、分享(0.7)；“用户购买意向阶段”：P1(无意向)、P2(初步了解)、P3(比较产品)、P4(准备购买)；“用户购买意向系数”：P1(0.1)、P2(0.3)、P3(0.5)、P4(0.8)；用户销售转化率预测 =（用户行为系数*0.2+用户购买意向系数*0.4+用户购买历史次数*0.4/12）*100%；“用户忠诚度评级”：A(用户购买历史次数10次以上)、B(用户购买历史次数6-9次)、C(用户购买历史次数2-5次)、D(用户购买历史次数1次)、E(用户购买历史次数0次)。 数据应用：通过此数据的全面分析和分组管理，企业能够通过用户以触达方式的反应行为，预测用户的销售转化率，从而确定用户以于企业的忠诚度，能更好的实现差异化营销策略，从而推动用户忠诚度的提升和有效触达方式的选择，该数据也可以广泛应用于教育服务、咨询行业等企业单位。

This dataset is established by connecting with potential customers in the education sector of Wuhu through marketing campaigns held from January 1, 2024 to July 1, 2025. User behavior coefficients are defined based on the feedback behaviors of these potential customers, to analyze users' purchase intentions and predict their sales conversion rates. Moreover, user loyalty ratings are determined using users' purchase history data, which helps enterprises assess the completion of marketing activities, analyze the effectiveness of marketing campaigns, and provide data support for the planning and promotion strategies of different types of enterprise activities.

This methodology can be widely applied to organizations in education services, consulting industries and other sectors, assisting enterprises in formulating operational strategies and marketing approaches via such analytical data, thereby reducing costs, improving marketing effectiveness and enhancing user loyalty.

### Data Collection
Marketing campaign data from January 1, 2024 to July 1, 2025 is collected and processed.

### Data Processing
User ID is taken as the unique identifier. Raw data is cleaned and deduplicated based on data sources. User behavior coefficients are defined according to user behaviors. User sales conversion rates are predicted based on users' purchase intentions, and user loyalty ratings are determined by combining users' purchase history data.

### Data Enrichment
In this dataset:
- "Marketing channels": SMS, email, super SMS, WeChat template messages, AI outbound calls, mini-program subscription messages, Douyin SMS, and Enterprise WeChat messages;
- "User behaviors": click, reply, unsubscribe, open, submit, share;
- "User behavior coefficients": click (0.2), reply (0.5), unsubscribe (0.1), open (0.4), submit (0.6), share (0.7);
- "User purchase intention stages": P1 (no purchase intention), P2 (preliminary understanding), P3 (product comparison), P4 (ready to purchase);
- "User purchase intention coefficients": P1 (0.1), P2 (0.3), P3 (0.5), P4 (0.8);
The formula for predicting user sales conversion rate is: (user behavior coefficient * 0.2 + user purchase intention coefficient * 0.4 + (number of user purchase history records / 12) * 0.4) * 100%;
- "User loyalty ratings": A (more than 10 purchase history records), B (6-9 purchase history records), C (2-5 purchase history records), D (1 purchase history record), E (0 purchase history records).

### Data Application
Through comprehensive analysis and grouped management of this dataset, enterprises can predict users' sales conversion rates based on their response behaviors to different touchpoint methods, thereby determining users' loyalty to the enterprise. This enables better implementation of differentiated marketing strategies, promoting the improvement of user loyalty and the selection of effective touchpoint methods. This dataset can also be widely applied to enterprises and organizations in education services, consulting industries and other fields.

搜集汇总

背景与挑战

背景概述

该数据集包含606条记录，基于2024年至2025年芜湖地区教育咨询客户的营销活动数据，通过用户行为和购买意向预测销售转化率，并进行忠诚度评级，旨在帮助企业优化营销策略和提升用户忠诚度。