广告点击率估算技术综述

纪文迪; 王晓玲; 周傲英

广告点击率估算技术综述

1.
华东师范大学软件学院上海市高可信计算重点实验室,上海 200062;
2.
复旦大学上海市智能信息处理实验室,上海 200433

详细信息

中图分类号: TP391
计量
- 文章访问数: 6093
- HTML全文浏览量: 162
- PDF下载量: 7083
- 被引次数: 0
出版历程
- 收稿日期: 2013-03-01
- 修回日期: 2013-04-01
- 刊出日期: 2013-05-25

Techniques for estimating click-through rates of Web advertisements: A survey

1.
Software Engineering Institue, Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, Shanghai 200062, China;
2.
Shanghai Key Laboratory of Intelligent Information Process, Fudan University, Shanghai 200433, China

摘要

摘要: 计算广告是根据给定的用户和网页内容，通过计算得到与之最匹配的广告并进行精准定向投放的一种广告投放机制.广告的点击率预测是指利用点击日志预测的点击率，其结果受到广告的自身性质、广告位置、页面信息、用户性质，以及广告主信誉等诸多因素的影响.有效地预测广告的点击率，对于提高广告投放的效率有着至关重要的作用.本文介绍了广告点击率预测的常用模型，包括历史数据丰富的广告点击率预测模型、新广告和稀疏广告的点击率估算模型和点击率预测的优化模型，并通过真实数据集举例说明了其实现的方法.
- 计算广告 /
- 点击率估算 /
- 逻辑回归模型 /
- 贝叶斯方法
Abstract: Computational advertising is a kind of advertising mechanism which has the capability to find the most suitable ads for given users and web content, so as to advertises them accurately. Therefore, estimating click-through rate (CTR) precisely makes significant difference in the efficiency of advertising on the Internet. Ad click-through rate prediction is to estimate CTR with click log, which is influenced by the nature features of ad, the position, the page information, user properties, the reputation of advertisers and such other factors. This paper is aimed to illustrate useful CTR prediction models, including CTR models for ads of abundant history data, CTR models for rare ads or new ads and some optimization models. Finally, the implementation methods with real data set were demonstrated as examples.
- computational advertisement /
- click-through rate /
- logistic regression /
- Bayes method

HTML全文

参考文献(1)

[1]

［1］周傲英,周敏奇,宫学庆.计算广告：以数据为核心的Web综合应用［J］.计算机学报,2011,34(10): 1805-1819.

［2］ BRODER A, JOSIFOVSKI V. Introduction to Computational Advertising ［M/OL］//The Course of Computation Advertising, Stanford University. 2011［2013-03-21］. http://www.stanford.edu/class/msande239.

［3］ GABRILOVICH E. An Overview of Computational Advertising ［R/OL］. Yahoo Research. 2008［2013-03-21］. http://research.yahoo.com/pub/2915.

［4］ AGARWAL D, CHAKRABARTI D. Statistical Challenges in Online Advertising ［R/OL］. Yahoo Research. 2008［2013-03-21］. http://research.yahoo.com/ pub/2430.

［5］ GRAEPEL T, BORCHERT T, HERBRICH R, et al. Probabilistic Machine Learning in Computational Advertising ［R/OL］. Microsoft Research, 2009［2013-03-21］. http://research. microsoft.com/en-us/um/beijing/events/mload-2010.

［6］ DID-IT, ENQUIRO, EYETOOLS. Eye Tracking Study ［R/OL］. 2007［2013-03-21］. http://www.enquiro.com/ eye-tracking-pr.asp.

［7］ AGICHTEIN E, BRILL E, DUMAIS S. Improving web search ranking by incorporating user behavior information［C］//Proc 29th SIGIR, 2006:19-26.

［8］ JOACHIMS T. Optimizing search engines using clickthrough data［C］//Proc KDD, 2002.

［9］ JOACHIMS T, GRANKA L, PAN B, et al. Accurately interpreting clickthrough data as implicit feedback［C］//Proc SIGIR, 2005.

［10］ GRANKA L A, JOACHIMS T, GAY G. Eye-tracking analysis of user behavior in www search［C］//Proc SIGIR’04, 2004.

［11］ ZHANG V, JONES R. Comparing click logs and editorial labels for training query rewriting［C］//Query Log Analysis: Social And Technological Challenges. Banff: WWW’07, 2007.

［12］ RICHARDSON M, DOMINOWSKA E, RAGNO R. Predicting Clicks: Estimating the Click-Through Rate for New Ads［C］//Banff: WWW’07, 2007.

［13］ DUPRET G E, PIWOWARSKI B. A user browsing model to predict search engine click data from past observations.［C］//SIGIR’08, 2008.

［14］ CHAPELLE O, ZHANG Y. A dynamic Bayesian network click model for web search ranking［C］//WWW’09, 2009.

［15］ GUO F, LIU C, KANNAN A, et al. Click chain model in web search［C］//WWW’09, 2009.

［16］ LIU C, GUO F, FALOUTSOS C. Bbm: Bayesian browsing model from petabyte-scale data［C］//KDD’09, 2009.

［17］ ZHU Z A, CHEN W, MINKA T, et al. A novel click model and its applications to online advertising［C］//WSDM’10, 2010.

［18］ DUPRET G, LIAO C. A model to estimate intrinsic document relevance from the clickthrough logs of a web search engine［C］//WSDM’10, 2010.

［19］ BECKER H, MEEK C, CHICKERING D M. Modeling contextual factors of click rates［C］//AAAI’07, 2007.

［20］ CHEN W Z, JI Z L, SHEN S, et al. A Whole Page Click Model to Better Interpret Search Engine Click Data［C］//AAAI’11, 2011.

［21］ CHAKRABARTI D, AGARWAL D, JOSIFOVSKI V. Contextual Advertising by Combining Relevance with Click Feedback［C］//WWW’08, 2008.

［22］ GRAEPEL T, CANDELA J Q, BORCHERT T, et al. Web-Scale Bayesian Click-Through Rate Prediction for Sponsored Search Advertising in Microsoft’s Bing Search Engine［C］//ICML’10, 2010.

［23］ M Regelson, D C. Fain. Predicting Click Through Rate Using Keyword Clusters［C］//EC’06, 2006.

［24］ DEMBCZYNSKI K, KOTOWSKI W, WEISS D. Predicting Ads’ ClickThrough Rate with Decision Rules［C］//WWW’08, 2008.

［25］ WANG X, LI W, CUI Y, et al. Click Through Rate Estimation for Rare Events in Online Advertising［C/OL］//Online Multimedia Advertising: Techniques and Technologies, 2011, Chapter 1［2013-03-21］. http://labs.yahoo.com/node/434.

［26］ AGARWAL D, BRODER A Z, CHAKRABARTI D, et al. Estimating rates of rare events at multiple resolutions［C］//KDD’07, 2007.

［27］ AGARWAL D, AGRAWAL R, KHANNA R, et al. Estimating rates of rare events with multiple hierarchies through scalable log-linear models［C］//KDD’10, 2010.

［28］ AGARWAL D, CHEN B C, ELANGO P. Spatio-Temporal Models for Estimating Click through Rate［C］//WWW’09, 2009.

［29］ YAN J, LIU N, WANG G, et al. How much can Behavioral Targeting Help Online Advertising?［C］//WWW’09, 2009.

［30］ AGARWAL D, CHEN B-C, ELANGO P, et al. Click shaping to optimize multiple objectives［C］//KDD’11, 2011.

［31］ SHEN S, HU B, CHEN W Z, et al. Personalized click model through collaborative filtering［C］//WSDM’12, 2012.

［32］ CHEN W Z, WANG D, ZHANG Y C, et al. A noise-aware click model for web search［C］//WSDM’12, 2012.

［33］ HU B, ZHANG Y C, CHEN W Z, et al. Characterizing search intent diversity into click models［C］//WWW’11, 2011.

［34］ ASHKAN A, CLARKE C L A, AGICHTEIN E, et al. Estimating Ad Clickthrough Rate through Query Intent Analysis［C］//WI-IAT’09, 2009.

［35］ XIONG C, WANG T, DING W, et al. Relation Click prediction for sponsored search［C］//WSDM’12, 2012.

［36］ IMMORLICA N, JAIN K, MAHDIAN M, et al. Click Fraud Resistant Methods for Learning［C］//WINE’05, 2005.

［37］ GOLLAPUDI S, PANIGRAHY R, GOLDSZMIDT M. Inferring Clickthrough Rates on Ads from Click Behavior on Search Results［C］//WSDM’11, 2011.

［38］ TENCEN T. KDD CUP［EB/OL］.2012［2013-03-21］. http://www.kddcup2012.org/c/kddcup2012-track2.

施引文献

资源附件(0)

访问统计