Click-through rate prediction of online advertisements based on probabilistic graphical model
-
摘要: 点击率预测可以提高用户对所展示互联网广告的满意度,支持广告的有效投放,是针对用户进行广告的个性化推荐的重要依据.对于没有历史点击记录的用户,仍需对其推荐广告,预测所推荐广告的点击率.针对这类用户,以贝叶斯网这一重要的概率图模型,作为不同用户之间广告搜索行为的相似性及其不确定性的表示和推理框架,通过对用户搜索广告的历史记录进行统计计算,构建反映用户间相似关系的贝叶斯网,进而基于概率推理机制,定量度量没有历史点击记录的用户与存在历史点击记录的用户之间的相似性,从而预测没有历史点击记录的用户对广告的点击率,为广告推荐提供依据.通过建立在KDD Cup 2012-Track 2的Tencent CA训练数据集上的实验,测试了方法的有效性.Abstract: CTR (Click-Through Rate) prediction can be used to improve users satisfaction with respect to the presented online advertisements (ads) and support effective advertising. CTR prediction is the basis for personalized recommendation of online ads. It is also necessary to re-commend ads and predict their CTRs for the users that have no historical click-through records. In this paper, we adopted BN (Bayesian network), an important probabilistic graphical model, as the framework for representing and inferring the similarity and the corresponding uncertainty of the behaviors in ad search of different users. First, we constructed the BN to reflect the similarity between users by means of statistic computations on the historical records of users ad search. Then, we measured the behavior similarity between the users with click-through records and those without records quantitatively based on the mechanism of BNs probabilistic inferences. Consequently, we predicted the CTRs of ads with respect to the users without historical click-through records, in order to provide a metric for ad recommendation. We made experiments on the training data of Tencent CA from KDD Cup 2012-Track 2 and tested the effectiveness of our methods.
-
[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] REGELSON M, FAIN D. Predicting click-through rate using keyword clusters[C]//Proceedings of the Second Workshop on Sponsored Search Auctions, EC 2006. Michigan: ACM, 2006.[3] AGARWAL D,BRODER A, CHAKRABARTI D, et al. Estimating rates of rare events at multiple resolutions. Proceedings of the ACM SIGMOD International Conference on Management of Data. Beijing: ACM, 2007: 16-25.[4] RICHARDSON M, DOMINIWSKA E, RAGNO R. Predicting Clicks: Estimating the Click-Through Rate for New Ads[C]//Proceedings of the 16th International Conference on World Wide Web, WWW 2007. Banff: ACM, 2007: 521-530.[5] CHAKRABARTI D, AGARWAL D, JOSIFOVSKI V. Contextual Advertising by Combining Relevance with Click Feedback[C]//Proceedings of the 17th International Conference on World Wide Web, WWW 2008. Beijing: ACM, 2008: 417-426.[6] GOLLAPUDI S, PANIGRAHY R, GOLDSZMIDT M. Inferring Clickthrough Rates on Ads from Click Behavior on Search Results[C]//Proceedings of the Workshop on User Modeling for Web Applications, Fourth International Conference on Web Search and Web Data Mining, WSDM 2011. Hong Kong: ACM,2011.[7] YAN J, LIU N, WANG G, et al. How much can Behavioral Targeting Help Online Advertising?[C]//Proceedings of the 18th International Conference on World Wide Web, WWW 2009. Madrid: ACM, 2009: 261-270.[8] AHMED A, LOW Y, ALY M, et al. Scalable distributed inference of dynamic user interests for behavioral targeting[C]//Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Diego, CA: ACM, 2011: 114-122.[9] WANG X, LI W, CUI Y, et al. Click Through Rate Estimation for Rare Events in Online Advertising. Online Multimedia Advertising: Techniques and Technologies, Chapter1 [M/OL]. 2011[2012-06-15]. http://labs.yahoo.com/node/434.[10] PEARL J. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference [M]. San Mateo, CA: Morgan Kaufmann Publishers, 1988.[11] RUSSEL S, NORVIG P. Artificial Intelligence—A Modern Approach [M]. Boston: Pearson Education, Publishing as Prentice-Hall, 2002.[12] DEMBCZYNSKI K, KOTLOWSKI W, WEISS D. Predicting Ads’ Click Through Rate with Decision Rules. [EB/OL]. 2008-03-31[2012-06-15].Yahoo Research, http://research.yahoo.com/workshops/troa-2008/papers/ submission_12.pdf.[13] GRAEPEL T, BORCHERT T, HERBRICH R, et al. Probabilistic Machine Learning in Computational Advertising Microsoft Research [EB/OL]. 2010-12-10 [2012-06-15]. http://research.microsoft.com/en-us/um/ beijing/events/mload-2010/.[14] CHAPELLE O, ZHANG Y. A dynamic Bayesian network click model for web search ranking[C]//Proceedings of the 18th International Conference on World Wide Web, WWW 2009. Madrid: ACM, 2009: 1-10.[15] 张少中,高飞.一种基于小世界网络和贝叶斯网的混合推荐模型 [J]. 小型微型计算机系统, 2010, 31(10): 1974-1978.[16] HRYCEJ T. Gibbs sampling in Bayesian networks [J]. Artificial Intelligence, 1990, 46: 351-363.[17] PEARL J. Evidential reasoning using stochastic simulation of causal models [J]. Artificial Intelligence, 1987, 32: 245-257.[18] KDD CUP 2012 Track 2: Predict the click-through rate of ads given the query and user information [EB/OL].2012-02-20[2012-06-15]. http://www. kddcup2012.org/c/kddcup2012-track2.
点击查看大图
计量
- 文章访问数: 5526
- HTML全文浏览量: 88
- PDF下载量: 6446
- 被引次数: 0