基于数据挖掘的电商搜索广告投放策略研究

doi:10.3969/j.issn.1007-7375.2019.01.009

工业工程 ›› 2019, Vol. 22 ›› Issue (1): 69-78.doi: 10.3969/j.issn.1007-7375.2019.01.009

基于数据挖掘的电商搜索广告投放策略研究

张磊, 郭峰, 侯小超

中国矿业大学管理学院, 江苏徐州 221116

收稿日期:2018-07-28 出版日期:2019-02-28 发布日期:2019-02-26
作者简介:张磊(1975-),男,江苏省人,教授,博士,主要研究方向为电子商务、能源经济
基金资助:
国家自然科学基金资助项目（71373261；71874187）

An E-commerce Searching Advertisement Serving Strategy Based on Data Mining

ZHANG Lei, GUO Feng, HOU Xiaochao

School of Management, China University of Mining and Technology, Xuzhou 221116, China

Received:2018-07-28 Online:2019-02-28 Published:2019-02-26

摘要/Abstract

摘要： 为了降低商家的广告投入成本，同时优化用户在电商平台中的购物体验，本文应用阿里“天池大数据”平台提供的海量真实数据，构建并训练出以广告转化率为预测目标的机器学习模型。通过分析模型学习结果，挖掘出搜索广告转化率的影响因素及影响效应。结果表明：店铺物流服务、广告商品销量、消费者偏好、电商平台智能化程度等对转化率的影响较大。同时对所有影响因素在用户、店铺、广告商品、广告上下文4个维度进行归类和分析。据此提出基于平台视角及商家视角下的广告投放策略，为电商平台及其入驻商家提供参考。

关键词: 搜索广告, 转化率, 数据挖掘, 广告投放策略

Abstract: In order to reduce the cost of advertising investment for businesses, and optimize the shopping experience of users in the e-commerce platform, the massive real data provided by Ali "Tianchi Big Data" platform is applied and a machine learning model is built and trained with the target of advertising conversion rate. By analyzing the model learning results, the influencing factors and effects of search advertising conversion rate are explored. The results show that store logistics services, advertising product sales, consumer preferences, and the degree of intelligence of e-commerce platforms have a greater impact on conversion rates. At the same time, all the influencing factors are classified and analyzed in the four dimensions of users, shops, advertising products and advertising contexts. Based on this, the advertisement serving strategy based on the platform and the merchant perspectives is proposed to provide reference for the e-commerce platform and its resident merchants.

Key words: searching advertisement, conversion rate, data mining, advertisement serving strategy

中图分类号:

F272.3

张磊, 郭峰, 侯小超. 基于数据挖掘的电商搜索广告投放策略研究[J]. 工业工程, 2019, 22(1): 69-78.

ZHANG Lei, GUO Feng, HOU Xiaochao. An E-commerce Searching Advertisement Serving Strategy Based on Data Mining[J]. Industrial Engineering Journal , 2019, 22(1): 69-78.

参考文献

[1] HUANG P, LURIE N H, MITRA S. Searching for experience on the web:an empirical examination of consumer behavior for search and experience goods[J]. Journal of Marketing, 2009, 73(2):55-69
[2] 刘鹏, 王超. 计算广告:互联网商业变现的市场与技术[M]. 北京:人民邮电出版社, 2015.23
[3] MALAGA R A. Web 2.0 Techniques for search engine optimization:two case studies[J]. Review of Business Research, 2009, 9(1):33-45
[4] LI K, LIN M, LIN Z, et al. Running and chasing——the competition between paid search marketing and search engine optimization[C/OL]. (2014-03-10). http://www.ieeexplore.ieee.org/document/6758988
[5] 卢向华. 竞价排名广告的关键词投放策略及其绩效研究——基于淘宝网的实证分析[J]. 管理科学学报, 2013, 16(6):1-9 LU Xianghua. Empirical study of keywords biding strategy and search engineadvertising performance[J]. Journal of Management Science in China, 2013, 16(6):1-9
[6] 陈远, 成全, 钟晓星. 基于搜索引擎的关键词广告及策略[J]. 情报理论与实践, 2005, 28(2):169-172
[7] FENG J. Optimal mechanism for selling a set of commonly ranked objects[J]. Marketing Science, 2008, 27(3):501-512
[8] 印卫华, 周志伟. 基于同义关键词的广告位拍卖与定价研究[J]. 南京理工大学学报(自然科学版), 2017, 41(6):784-791 YIN Weihua, ZHOU Zhiwei. Auction and pricing for advertising based on synonymous keywords[J]. Journal of Nanjing University of Science and Technology (Natural Science Edition), 2017, 41(6):784-791
[9] 黄河, 杨琴, 李慧. 考虑用户福利的关键词拍卖机制研究[J]. 管理工程学报, 2012, 26(4):146-153 HUANG He, YANG Qin, LI Hui. The mechanism design of keyword auction with user benefits[J]. Journal of Management Engineering, 2012, 26(4):146-153
[10] PARDOE D, CHAKRABORTY D, STONE P. TacTex09:a champion bidding agent for ad auctions[C/OL]. (2010-05). http://www.cs.utexas.edu/users/pstone/Papers/bib2html-links/AAMAS10-pardoe.pdf.
[11] 阳成虎, 杜青龙. 不完全信息下关键字竞价策略研究[J]. 统计与决策, 2009, 13(13):38-39
[12] 赵大营. 企业的Google广告关键词竞价策略研究[D]. 哈尔滨:哈尔滨工业大学, 2010. ZHAO Daying. Optimal bidding strategy for enterprise using Google keyword advertising[D]. Harbin:Harbin Institute of Technology, 2010.
[13] VOROBEYCHIK Y. Simulation-based analysis of keyword auctions[DB/OL]. (2009-07). http://www.sigecom.org/exchanges/volume_8/1/vorobeychik.pdf.
[14] 贺笛. 搜索引擎广告派放机制设计的研究[D]. 北京:北京大学, 2013. HE Di. Improved mechanism design for sponsored search[D]. Beijing:Peking University, 2013.
[15] 纪文迪, 王晓玲, 周傲英. 广告点击率估算技术综述[J]. 上海华东师范大学学报(自然科学版), 2013(3):2-14 JI Wendi, WANG Xiaoling, ZHOU Aoying. Techniques for estimating click-through rates of web advertisements:a survey[J]. Journal of East China Normal University (Natural Science Edition), 2013(3):2-14
[16] 王冰. 浅析网络广告投放的基本策略[J]. 信息技术, 2009, 33(1):102-104 WANG Bing. Strategies of Internet advertisement placement[J]. Information Technology, 2009, 33(1):102-104
[17] 徐涛. 企业搜索引擎广告策略研究[D]. 上海:华东师范大学, 2010. XU Tao. The study of company's strategy in search engine advertising[D]. Shanghai:East China Normal University, 2010.
[18] 周荣庭, 陈果. 图书出版的搜索引擎营销策略[J]. 出版科学, 2007, 15(1):71-73 ZHOU Rongting, ChEN Guo. Search engine marketing for book publishing[J]. Publishing Science, 2007, 15(1):71-73
[19] 徐卫, 陈丽亚, 刘功申. 基于用户行为分析的网站广告投放策略[J]. 计算机工程与应用, 2006, 42(28):225-226 XU Wei, CHEN Liya, LIU Gongshen. Strategy of putting Adv on the specific web based on the action of user[J]. Computer Engineering and Applications, 2006, 42(28):225-226
[20] 李凯, 邓智文, 严建援. 搜索引擎营销研究综述及展望[J]. 外国经济与管理, 2014, 36(10):13-21 LI Kai, DENG Zhiwen, YAN Jianyuan. A literature review of search engine marketing and prospects[J]. Foreign Economy and Management, 2014, 36(10):13-21
[21] KE G, MENG Q, FINLEY T, et al. LightGBM:a highly efficient gradient boosting decision tree[C/OL]. (2017-12). https://papers.nips.cc/paper/6907-lightgbm-a-highly-efficient-gradient-boosting-decision-tree.pdf.

基于数据挖掘的电商搜索广告投放策略研究

An E-commerce Searching Advertisement Serving Strategy Based on Data Mining

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

[1]	蒲国利1, 2，苏秦2,3. 食品质量安全网络预警研究综述[J]. 工业工程, 2013, 16(3): 143-147.
[2]	张旭梅，石瀚凌. 基于分类挖掘方法的商业银行个人理财业务客户流失分析[J]. 工业工程, 2011, 14(6): 126-132.
[3]	关迎莹, 张毕西, 宋静, 廖朝辉. 3G客户关系稳定度建模与应用[J]. 工业工程, 2011, 14(2): 95-99.
[4]	刘晶1,2, 季海鹏3. 基于神经网络的关联规则在故障诊断中的应用[J]. 工业工程, 2011, 14(2): 118-121.