江苏地区阿里平台光伏产品消费者分类数据

本数据支持购买光伏产品的消费者分类运营，旨在为精准营销提供必要的消费者分类数据，精准营销的关键在于深入理解不同消费者群体的需求、购买行为及偏好，从而制定个性化的营销策略。通过对消费者进行分层管理，所有企业可在后期对不同层级的消费者采取不同的运营策略提供数据依据。1.数据来源：通过自家账号登录后台查询、采集江苏地区内的不同消费者在各个年度的购买消费数据。 2.模型选择：RFM数据模型。通过对消费者的消费频次、消费总金额、距上次消费天数等获得多维度的消费者分类数据。 3.模型参数及优化：分别通过对消费者的平均消费频次、平均消费金额、平均消费天数比较，从而对R、F、M的数据进行评分（例如对于R评分，如果消费频次/平均消费频次≥1.3则评6分，1.0≤消费频次/平均消费频次<1.3则评4分，消费频次/平均消费频次<1则评1.5分，F、M的评价也同理计算），RFM综合评分=0.35R评分+0.35F评分+0.3M评分，再根据RFM综合评分对消费者进行分类，得分5分以上为高粘度消费者，4~5分为重要维系消费者，3~4分为潜力深耕消费者，2~3分为新消费者，2分以下为一般消费者。

This dataset supports consumer segmentation operations for photovoltaic (PV) product purchasers, aiming to provide necessary consumer classification data for precision marketing. The core of precision marketing lies in deeply understanding the demands, purchase behaviors and preferences of different consumer groups, so as to formulate personalized marketing strategies. Through hierarchical management of consumers, all enterprises can acquire data basis for implementing differentiated operational strategies for consumers of different tiers in the later stage.
1. Data Source: Query and collect annual purchase and consumption data of various consumers in Jiangsu Province by logging into the backend via the company's own accounts.
2. Model Selection: RFM data model. Multi-dimensional consumer classification data is obtained by analyzing indicators including consumers' purchase frequency, total consumption amount and days since last purchase.
3. Model Parameters and Optimization: Score the R, F and M data by comparing the average purchase frequency, average total consumption amount and average days since last purchase of consumers respectively. For example, for the R score: 6 points if purchase frequency / average purchase frequency ≥ 1.3; 4 points if 1.0 ≤ purchase frequency / average purchase frequency < 1.3; 1.5 points if purchase frequency / average purchase frequency < 1. The scoring for F and M follows the same calculation logic. The RFM comprehensive score is calculated as 0.35*R score + 0.35*F score + 0.3*M score. Then classify consumers based on the RFM comprehensive score: consumers with a score above 5 are high-loyalty consumers; those with 4 to 5 points are important retention consumers; those with 3 to 4 points are potential deep-cultivation consumers; those with 2 to 3 points are new consumers; and those with a score below 2 points are general consumers.

搜集汇总

数据集介绍

特点

该数据集提供了江苏地区阿里平台光伏产品消费者的分类信息，基于RFM模型对消费者进行评分和分类，适用于精准营销和消费者分层管理，数据规模为1798条，每年更新一次。