基于购买行为及评论行为的用户购买预测研究

北京邮电大学学报(社科版) ›› 2016, Vol. 18 ›› Issue (4): 18-25.

基于购买行为及评论行为的用户购买预测研究

1北京邮电大学经济管理学院，北京100876；2可信分布式计算与服务教育部重点实验室（北京邮电大学），
北京100876；3上海对外经贸大学，上海201620

收稿日期:2016-04-21 出版日期:2016-08-31
基金资助:
国家自然科学基金项目（71171023）；国家自然科学基金重点项目（71231002）；973基础重大课题（2013CB329604）；973项目（2012CB315805）

Customer Purchase Prediction Based on Buying Behavior and Comment Behavior

1 School of Economics and Management, Beijing University of Posts and Telecommunications,
Beijing 100876, China; 2 Key Laboratory of Trustworthy Distributed Computing and Service
(Beijing University of Posts and Telecommunications), Ministry of Education, Beijing 100876, China;
3 Shanghai University of International Business and Economics, Shanghai 201620, China

Received:2016-04-21 Online:2016-08-31

摘要/Abstract

摘要：

随着网络消费的兴起，第三方点评网站也在蓬勃发展，针对非契约情景下用户未来购买行为预测是用户终身价值评估、用户流失管理等研究领域的关键。为了实现用户购买预测研究，选取了大众点评网的用户数据，结合大众点评网的用户行为特征，借鉴非契约情境中经典的Pareto/NBD模型对用户购买行为进行预测研究，同时尝试在原模型的基础上引入协变量，取得了较理想的改进效果，揭示了大众点评网评论平台中的用户评论数据对用户购买数据的预测作用。

关键词: 非契约情景, 用户行为预测, Pareto/NBD模型, 协变量

Abstract:

In recent years, with the development of online-shopping, “Dianping” as the representative of the review sites is booming The forecast for customers’ future buying behavior in non-contractual transaction setting is the key research of customer lifetime value (CLV) evaluation and the prediction of customer loss The data of “Dianping com” is used, and then by analyzing the Dianping users’ behavioral characteristics and using the Pareto/NBD model in the non-contractual setting, the buying behavior of users is predicted Meanwhile, through introducing comments and purchase amounts as covariates, the effect of the result has been improved It reveals that users’ reviews can help predict users’ purchase behavior

Key words: non-contractual setting, customer behavior prediction, Pareto/NBD model, covariate

中图分类号:

李美其1,2，齐佳音2,3. 基于购买行为及评论行为的用户购买预测研究[J]. 北京邮电大学学报(社科版), 2016, 18(4): 18-25.

LI Mei-qi1,2，QI Jia-yin2,3. Customer Purchase Prediction Based on Buying Behavior and Comment Behavior[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2016, 18(4): 18-25.

参考文献

［1］中国互联网络信息中心. 第34次中国互联网络发展状况统计报告［R/OL］. 人民网, （2013-07-23）. http://yuqing.people.com.cn/n/2014/0723/c209043-25327218.html.
［2］吕秀莹. 浅析Web2.0环境下我国第三方点评网站的发展现状——以大众点评网和豆瓣网为例［J］. 东南大学学报（哲学社会科学版）, 2011, 13(S1): 87-92.
［3］ Wei C P, Chiu I T. Turning telecommunications call details to churn prediction: A data mining approach［J］. Expert Systems with Applications, 2002, 23(2): 103-112.
［4］蒋国瑞, 司学峰. 基于代价敏感SVM的电信客户流失预测研究［J］. 计算机应用研究, 2009, 26(2): 87-93.
［5］ Li Shibo, Sun Baohong, Wilcox R T. Cross-selling sequentially ordered products: An application to consumer banking［J］. Journal of Marketing Research, 2005, 42(2): 233-239.
［6］ Schmittlein D C, Colombo R. Counting your customers: Who are they and what will they do next?［J］. Management Science, 1987, 33(1): 1-24.
［7］马少辉. Pareto/NBD模型扩展［J］. 系统工程, 2008, 26(8): 123-126.
［8］马费成, 苏小敏, 望俊成. Pareto/NBD模型在网络信息失效判别分析中的探索性研究［J］. 情报理论与实践, 2011, 34(11): 50-55.
［9］刘学伟. 基于Pareto/NBD+朴素贝叶斯组合模型的电子商务客户流失预测研究［D］. 成都: 四川大学, 2006.
［10］ Kumar V, Ramani G, Bohling T. Customer lifetime value approaches and best practice applications［J］. Journal of Interactive Marketing, 2004, 18(3): 60-72.
［11］齐佳音, 李怀祖, 舒华英, 等. SMC模型在IT分销业的实证案例研究［J］. 系统工程理论与实践, 2004, 24(3): 69-78.
［12］ Fader P S, Hardie B G S, Shang J. Customer-base analysis in a discrete-time noncontractual setting［J］. Marketing Science, 2010, 29(6): 1086-1108.
［13］蔡瑞, 齐佳音. 基于改进的Pareto/NBD模型预测博客用户在线行为［J］. 统计与信息论坛, 2013, 28(6): 69-75.
［14］ Sabavala D J. Generalizing the NBD model for customer purchases: What are the implications and is it worth the effort? Comment［J］. Journal of Business & Economic Statistics, 1988, 6(6): 161-162.
［15］ Fader P S, Hardie B G S, Lee K L. “Counting your customers” the easy way: An alternative to the Pareto/NBD model［J］. Marketing Science, 2005, 24(2): 275-284.