基于转化的广告方式在应用和研究中逐渐得到重视,采用该方式的搜索广告在广告排序时需要对候选广告的转化概率进行预测,以提高广告的转化率,优化搜索引擎的广告收益。该文在对搜索广告中影响转化的各特征进行提取与分析的基础上,提出了描述广告、查询、用户三个因素与转化事件关系的概率因子图模型,并基于该模型对广告转化进行预测。最后我们使用从某商业搜索引擎采集的实际数据对预测模型进行评价并与朴素贝叶斯方法进行对比,实验结果表明,三类因素对转化具有不同程度的影响,我们提出的因子图模型可以较好地预测广告的转化。
Abstract
The CPA (Cost-per-Action) Advertising is attracting more and more attention in both industry and research. Sponsored search based on CPA requires predicting conversion probability for each candidate ad during ad ranking, in order to raise conversion rate and optimize ad revenue for search engine. After extracting and analyzing features which may influence conversion of ads, we propose a probabilistic factor graph based model for ad conversion prediction which describes the relation between the conversion event and three factors, i.e. ad, query, and user. The model is evaluated and compared with Naive Bayesian method on real-world data gathered from a commercial search engine. The experiment demonstrates a good result in the ad conversion prediction, as well as different influences of the three factors.
关键词
搜索广告 /
概率预测模型 /
CPA广告
{{custom_keyword}} /
Key words
sponsored search /
probabilistic prediction model /
CPA advertising
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Mitchell D. Click fraud and halli-bloggers[J]. New York Times, 2005, July.
[2] Rosales R, Cheng H, Manavoglu E. Post-click conversion modeling and analysis for non-guaranteed delivery display advertising[C]//Proceedings of the fifth ACM international conference on Web search and data mining. 2012:293-302.
[3] Kota N, Agarwal D. Temporal multi-hierarchy smoothing for estimating rates of rare events[C]//Proceedings of the 17th ACM SIGKDD international conference on knowledge discovery and data mining. 2011:1361-1369.
[4] Rutz O, Bucklin R. A model of individual keyword performance in paid search advertising[OL]. 2007. http://dx.doi.org/10.2139/ssrn.
[5] Becker H, Broder A, Gabrilovich E, et al. What happens after an ad click?: quantifying the impact of landing pages in web advertising[C]//Proceeding of the 18th ACM conference on information and knowledge management. 2009:57-66.
[6] Ghose A, Yang S. An empirical analysis of sponsored search performance in search engine advertising[C]//Proceedings of the international conference on Web search and web data mining. 2008:241-250.
[7] Graepel T, Candela J, Borchert T, et al. Web-scale Bayesian click-through rate prediction for sponsored search advertising in Microsoft’s Bing search engine[C]//Proceedings of the Twenty-Seventh International Conference on Machine Learning (ICML-10). 2010:13-20.
[8] Hillard D, Manavoglu E, Raghavan H, et al. The sum of its parts: reducing sparsity in click estimation with query segments[J]. Information Retrieval, 2011:1-22.
[9] Kschischang F, Frey B, Loeliger H. Factor graphs and the sum-product algorithm[J]. Information Theory, IEEE Transactions on, 2001, 47(2):498-519.
[10] Minka T. Expectation Propagation for approximate Bayesian inference[C]//Proceedings of the Seventeenth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-01). San Francisco, CA: Morgan Kaufmann, 2001:362-369.
[11] T Minka J G, J Winn, Knowles D. Infer.NET 2.4[OL]. Microsoft Research Cambridge, 2010, http://research.microsoft.com/infernet.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(5290 KB)
