基于网络店铺订单数据的群体用户画像构建研究
|
摘要
针对电子商务平台中网络店铺的订单数据,提出了一种用于精准客户细分的群体用户画像构建方法。该方法主要分为4个步骤:第一步,通过用户基本属性及领域词汇表创建用户画像模板;第二步,根据订单数据构建单用户画像实例,形成用户画像数据库;第三步,对单用户画像的各种类型属性指标进行规范化处理;第四步,通过属性相似度计算,运用聚类算法实现群体用户画像聚类。以淘宝网某"线上礼裙"企业店铺为例进行实验,结果表明:7个属性平均精确度为0.913,综合精确度为0.522,说明该方法是有效的。
Based on order data of online stores on E-Commerce platform, this paper proposes the method of group user portrait for more precise customer segmentation. This method is divided into four steps:(1) creating portrait templates according to user profile and domain vocabulary;(2) constructing single user portrait as an example based on order data so as to form a database;(3) standardizing all kinds of attribute indices of single user;(4) clustering group users by calculating attribute similarity via clustering algorithm. The paper makes a case study of an online dress store from Taobao platform, and draws that the average precision of the seven attributes is 0.913 and that the comprehensive precision is 0.522, indicating effectiveness of the method of group user portrait.
Based on order data of online stores on E-Commerce platform, this paper proposes the method of group user portrait for more precise customer segmentation. This method is divided into four steps:(1) creating portrait templates according to user profile and domain vocabulary;(2) constructing single user portrait as an example based on order data so as to form a database;(3) standardizing all kinds of attribute indices of single user;(4) clustering group users by calculating attribute similarity via clustering algorithm. The paper makes a case study of an online dress store from Taobao platform, and draws that the average precision of the seven attributes is 0.913 and that the comprehensive precision is 0.522, indicating effectiveness of the method of group user portrait.
引文
[1] 阿里巴巴. 2018年3月份季度及2018财年全年业绩[EB/OL]. (2018-03-10) [2018-11-10]. https://www.alibabagroup.com/cn/ir/earnings.
[2] COOPER A. The inmates are running the asylum:why hightech products drive us crazy and how to restore the sanity[M]. Indianapolis: Sams, 2004.
[3] 单晓红,张晓月,刘晓燕.基于在线评论的用户画像研究:以携程酒店为例[J].情报理论与实践,2018,41(4):99-104, 149.
[4] MUELLER J, STUMME G. Gender inference using statistical name characteristics in twitter[EB/OL]. (2016-6-17) [2018-3-01]. https://arxiv.org/abs/1606.05467.
[5] ROSENTHAL S, MCKEOWN K. Age prediction in blogs: a study of style, content, and online behavior in pre- and post-social media generations[EB/OL]. (2011-6-19) [2018-3-01]. https://dl.acm.org/citation.cfm?id=2002569.
[6] 王凌霄,沈卓,李艳.社会化问答社区用户画像构建[J].情报理论与实践,2018,41(1):129-134.
[7] 黄文彬,徐山川,吴家辉,等.移动用户画像构建研究[J].现代情报,2016,36(10):54-61.
[8] 汪强兵,章成志.融合内容与用户手势行为的用户画像构建系统设计与实现[J].数据分析与知识发现,2017,1(2):80-86.
[9] 胡媛,毛宁.基于用户画像的数字图书馆知识社区用户模型构建[J].图书馆理论与实践,2017(4):82-85,97.
[10] 王庆,赵发珍.基于“用户画像”的图书馆资源推荐模式设计与分析[J].现代情报,2018,38(3):105-109,137.
[11] 林燕霞,谢湘生.基于社会认同理论的微博群体用户画像[J].情报理论与实践,2018,41(3):142-148.
[12] 赵曙光.高转化率的社交媒体用户画像:基于500用户的深访研究[J].现代传播(中国传媒大学学报),2014,36(6):115-120.
[13] 刘海,卢慧,阮金花,等.基于“用户画像”挖掘的精准营销细分模型研究[J].丝绸,2015,52(12):37-42,47.
[14] 邓晓懿,金淳,樋口良之,等.移动商务中面向客户细分的KSP混合聚类算法[J].管理科学,2011,24(4):54-61.
[15] PAZZANI M J, BILLSUS D.Content-based recommendation systems[M]. Heidelberg: Springer, 2007.
[16] 刘英姿,吴昊.客户细分方法研究综述[J].管理工程学报,2006(1):53-57.
[17] 孟巍,吴雪霞,李静,等.基于大数据技术的电力用户画像[J].电信科学,2017,33(S1):15-20.
[18] HAN J, PEI J, KAMBER M. Data mining: concepts and techniques(3rd)[M]. Singapore:Elsevier, 2012.
[19] 张光卫,何锐,刘禹,等.基于云模型的进化算法[J].计算机学报,2008(7):1082-1091.
[2] COOPER A. The inmates are running the asylum:why hightech products drive us crazy and how to restore the sanity[M]. Indianapolis: Sams, 2004.
[3] 单晓红,张晓月,刘晓燕.基于在线评论的用户画像研究:以携程酒店为例[J].情报理论与实践,2018,41(4):99-104, 149.
[4] MUELLER J, STUMME G. Gender inference using statistical name characteristics in twitter[EB/OL]. (2016-6-17) [2018-3-01]. https://arxiv.org/abs/1606.05467.
[5] ROSENTHAL S, MCKEOWN K. Age prediction in blogs: a study of style, content, and online behavior in pre- and post-social media generations[EB/OL]. (2011-6-19) [2018-3-01]. https://dl.acm.org/citation.cfm?id=2002569.
[6] 王凌霄,沈卓,李艳.社会化问答社区用户画像构建[J].情报理论与实践,2018,41(1):129-134.
[7] 黄文彬,徐山川,吴家辉,等.移动用户画像构建研究[J].现代情报,2016,36(10):54-61.
[8] 汪强兵,章成志.融合内容与用户手势行为的用户画像构建系统设计与实现[J].数据分析与知识发现,2017,1(2):80-86.
[9] 胡媛,毛宁.基于用户画像的数字图书馆知识社区用户模型构建[J].图书馆理论与实践,2017(4):82-85,97.
[10] 王庆,赵发珍.基于“用户画像”的图书馆资源推荐模式设计与分析[J].现代情报,2018,38(3):105-109,137.
[11] 林燕霞,谢湘生.基于社会认同理论的微博群体用户画像[J].情报理论与实践,2018,41(3):142-148.
[12] 赵曙光.高转化率的社交媒体用户画像:基于500用户的深访研究[J].现代传播(中国传媒大学学报),2014,36(6):115-120.
[13] 刘海,卢慧,阮金花,等.基于“用户画像”挖掘的精准营销细分模型研究[J].丝绸,2015,52(12):37-42,47.
[14] 邓晓懿,金淳,樋口良之,等.移动商务中面向客户细分的KSP混合聚类算法[J].管理科学,2011,24(4):54-61.
[15] PAZZANI M J, BILLSUS D.Content-based recommendation systems[M]. Heidelberg: Springer, 2007.
[16] 刘英姿,吴昊.客户细分方法研究综述[J].管理工程学报,2006(1):53-57.
[17] 孟巍,吴雪霞,李静,等.基于大数据技术的电力用户画像[J].电信科学,2017,33(S1):15-20.
[18] HAN J, PEI J, KAMBER M. Data mining: concepts and techniques(3rd)[M]. Singapore:Elsevier, 2012.
[19] 张光卫,何锐,刘禹,等.基于云模型的进化算法[J].计算机学报,2008(7):1082-1091.