大数据服务平台用户价值识别与细分研究——基于RFM修正模型

Research on User Value Identification and Segmentation of Big Data Service Platform: Based on RFM Correction Model

[目的/意义]随着数字经济的快速发展,数据资源需求的日益增加,大数据服务平台成为用户获取数据资源的主要渠道。如何有效地、精确地识别用户价值是平台快速发展和提高竞争优势的重要途径。[方法/过程]数据资源作为一种非快速消耗类、非周期性商品,其交易数据十分稀疏,导致传统RFM模型不再适用。为此,对传统RFM模型指标数据进行填充,构建ALC-RFM模型,并结合K-means方法对平台用户价值进行识别与细分。[结果/结论]实验结果表明:ALC-RFM模型结合K-means方法在用户价值识别与细分方面具有较好的效果,通过对数海大数据交易平台的用户进行价值识别与细分,得到重要价值用户、重要保持用户和重要挽留用户三大用户群体,并给出相应的服务策略。

[Purpose/significance] With the rapid development of the digital economy and the increasing demand for data resources,the big data service platform has become the main channel for users to obtain data resources.How to effectively and accurately identify user value is an important way for the rapid development and the improvement of competitive advantage of the platform.[Method/process] As a non-rapid consumed and non-cyclical commodity,the data which is for transaction is very sparse,which makes the traditional RFM model no longer applicable.To this end,the paper fills in the traditional RFM model’s indicator data,constructs the ALC-RFM model,and the K-means method is used to identify and subdivide the platform user value.[Result/conclusion] The experimental results show that the ALC-RFM model combined with the K-means method has a good effect on user value identification and segmentation.Through the value identification and subdivision of the users of the Shuhai big data trading platform,three major user groups of important value users,important maintenance users and important retention users were founded,and corresponding service strategies were given.