Please wait a minute...
浙江大学学报（理学版）
浙江大学学报（理学版）  2019, Vol. 46 Issue (5): 565-573    DOI: 10.3785/j.issn.1008-9497.2019.05.008
数学与计算机科学     
网络广告点击率预估的特征学习及技术研究进展
刘华玲1, 恽文婧1, 林蓓1, 丁宇杰2
1.上海对外经贸大学 统计与信息学院，上海 201620
2.上海财经大学 信息管理与工程学院，上海 200433
A survey on feature learning and technologies of online advertising click-through rate estimation.
LIU Hualing1, YUN Wenjing1, LIN Bei1, DING Yujie2
1.School of Statistics and Information, Shanghai University of International Business and Economics, Shanghai 201620, China
2.School of Information Management and Engineering, Shanghai University of Finance and Economics, Shanghai 200433, China
 全文: PDF(552 KB)   HTML  
摘要： 大数据时代有效预估网络广告点击率，对企业精准营销和提高投资回报率具有至关重要的作用。对网络广告点击率预估的特征学习及技术研究进行了综述，从原始数据特点及解决方法、点击率预估的特征学习、点击率预估模型构建、评价指标选取等方面，分析了网络广告点击率预估的国内外研究现状。点击率预估可应用于互联网广告投放、推荐系统等多个领域，具有较高的研究价值。
关键词： 点击率预估;  特征学习;  网络广告    
Abstract: How to effectively estimate the click-through rate (CTR) of online advertising in the era of big data plays a crucial role in the accurate marketing of enterprises and the improvement of return on investment (ROI). It also helps improve user experience in real online advertising scenarios. This paper reviews the feature learning and technologies of online advertising click-through rate estimation. Specifically, in the four aspects of the abundant historical data characteristics and their corresponding solutions, feature engineering, the construction of click-rate estimation model, and the selection of evaluation indicators, the current state of domestic and international research of online advertising click-through rate estimation is analyzed. It shows that the click-through rate estimation can be applied to many areas such as internet advertising and recommendation systems, and has high research value. However, the problem of conversion rate estimation in online advertising is different from that of click-through rate estimation, and further researches are needed.
Key words: click rate estimation    feature learning    online advertising
收稿日期: 2018-10-08 出版日期: 2019-09-25
CLC:  TP 181  
基金资助: 上海哲学社会科学规划课题项目(2018BJB023)； 国家社会科学重大课题（16ZDA055）.
作者简介: 刘华玲(1964—)，ORCID: http://orcid.org/ 0000-0002-3980-6955 ，女，博士，教授，主要从事知识管理与智能决策、隐私保护数据挖掘、互联网金融研究，E-mail：liuhl@suibe.edu.cn.
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
刘华玲
恽文婧
林蓓
丁宇杰

引用本文:

刘华玲, 恽文婧, 林蓓, 丁宇杰. 网络广告点击率预估的特征学习及技术研究进展[J]. 浙江大学学报（理学版）, 2019, 46(5): 565-573.

LIU Hualing, YUN Wenjing, LIN Bei, DING Yujie. A survey on feature learning and technologies of online advertising click-through rate estimation.. Journal of ZheJIang University(Science Edition), 2019, 46(5): 565-573.

链接本文:

https://www.zjujournals.com/sci/CN/10.3785/j.issn.1008-9497.2019.05.008    或    https://www.zjujournals.com/sci/CN/Y2019/V46/I5/565

1 iResearch. 2017 Q3 China Online Advertising and Segmentation Media Market Data Release Research Report[R]. Shanghai: iResearch, 2017.
2 LIUP, WANGC. Computational Advertising [M]. Beijing: The People's Posts and Telecommunications Press, 2015: 61-63.
3 JIW D, WANGX L, ZHOUA Y. Techniques for estimating click-through rates of Web advertisements: A survey[J]. Journal of East China Normal University (Natural Science), 2013(3): 2-14.DOI:10.3969/j.issn.1000-5641.2013.03.001
4 ZHANGZ Q, ZHOUY, XIEX Q, et al. Research on advertising click-through rate estimation based on feature learning[J]. Chinese Journal of Computers, 2016, 39(4): 780-794.
5 PANB, ZHANGQ C, YUC C, et al. The application of integration model based on factorization machine in advertising CTR prediction[J]. Computer Applications and Software, 2018, 35(1): 107-111, 148.
6 WEIX H, YUC C, TIANC L, et al. Internet CTR prediction model on big data platform[J]. Computer Engineering and Design, 2017, 38(9): 2504-2508.DOI:10.16208/j.issn1000-7024.2017.09.038
7 RENDLES. Factorization machines[C]// 2010 IEEE International Conference on Data Mining. Sydney:IEEE, 2011: 995-1000. DOI:10.1109/icdm.2010.127
8 JUANY C, ZHUANGY, CHINW S, et al. Field-aware factorization machines for CTR prediction[C]// Proceedings of the 10th ACM Conference on Recommender System. Boston:ACM, 2016: 43-50.DOI:10.1145/2959100.2959134
9 BAQ L. The Recommendation Technology Research Based on User Attribute Clustering and SVD Algorithm[D]. Beijing: Beijing University of Posts and Telecommunications, 2013.
10 AGARWALD, AGARWALR, KHANNAR, et al. Estimating rates of rare events with multiple hierarchies through scalable log-linear models[C]//Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Washington DC：ACM, 2010: 213-222. DOI:10.1145/1835804.1835834
11 ZHUZ B, LIB, LIUX J, et al. Research on click-through rate prediction of Internet advertising based on LDA[J]. Application Research of Computers, 2016, 33(4): 979-982.DOI:10.3969/j.issn.1001-3695.2016.04.004
12 YANL, LIW, XUEG, et al. Coupled Group Lasso for Web-Scale CTR Prediction in Display Advertising[C]// Proceedings of the 31st International Conference on Machine Learning. Beijing: JMLR W&CP, 2014.
13 SHIM Y, GUJ J. Balance-sampling based light-weighted advertisement CTR prediction method[J], Application Research of Computers, 2014, 31(1): 33-36. DOI:10.3969/j.issn.1001-3695.2014.01.006
14 LIUY, LIUD, WANGY W, et al. Online advertising prediction model based on multiple source fusion feature extraction[J]. Computer Engineering, 2019,45(1):178-185,191.
15 LIUT. Research on Click-through Rate Prediction of Sponsored Search Using Multi-class Features[D]. Beijing: Beijing University of Posts and Telecommunications, 2012.
16 YANGC Y. Personalized Advertising Recommendation Based on Goods’ Category[D]. Xi’an: Xidian University, 2017.
17 XIAF.Large-scale machine learning on advertising data[EB/OL].(2014-03-21)[2019-01-25]. https://www.infoq.cn/article/2014%2F03%2Fbaidu-salon48-summary.
18 JIW D. Time-Aware Conversion Prediction and Attribution Analysis[D]. Shanghai: East China Normal University, 2017.
19 CHENQ H, SUNC H, YUS M. et al. Research on estimation of ads click rate based on recurrent neural network[J]. Journal of Zhejiang Sci-Tech University (Natural Sciences Edition), 2016, 35(6): 880-885.
20 CHENGH, ZWOLR V, AZIMIJ, et al. Multimedia features for click prediction of new ads in display advertising[C]// Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.Beijing:AMC, 2012: 777-785. DOI:10.1145/2339530.2339652
21 XUT. Design and Implementation of Click Through Rate Prediction Platform for Display Advertising[D]. Harbin: Harbin Institute of Technology, 2017.
22 FUX F. Research and Application of Mobile Advertisement Recommendation Technology Based on User Profile[D]. Chengdu: University of Electronic Science and Technology of China, 2017.
23 HILLARDD, MANAVOGLUE, RAGHAVANH, et al. The sum of its parts: Reducing sparsity in click estimation with query segments[J]. Information Retrieval, 2011, 14(3): 315-316.DOI:10.1007/s10791-010-9152-6
24 ZHOUG R, MOU N, FANY, et al. Deep interest evaluation network for click-through rate prediction[C]// Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence. Hawaii: AAAI, 2019. DOI:10.1145/3219819.3219823
25 HEX R, PANJ F, JINO, et al. Practical lessons from predicting clicks on ads at facebook[C]//Proceedings of the 8th International Workshop on Data Mining for Online Advertising. New York:ACM, 2014: 1-9. DOI:10.1145/2648584.2648589
26 AGARWALD, LONGB, TRAUPMANJ, et al. LASER: A scalable response prediction platform for online advertising[C]//Proceedings of the 7th ACM International Conference on Web Search and Data Mining. New York: ACM, 2014: 173-182.
27 CHANP P K, HUX, ZHAOL L, et al. Convolutional neural networks based click-through rate prediction with multiple feature sequence[C]// Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. Stockholm: International Joint Conferences on Artificial Intelligence Organization, 2018: 2007-2013.DOI:10.24963/ijcai.2018/277
28 SONGW P, SHIC, XIAOZ P, et al. AutoInt: Automatic feature interaction learning via self-attentive neural networks[J]. arXiv:1810.11921,2018.
29 XIEG L. Analysis and Research of E-commerce’s User Data[D]. Beijing: Beijing University of Posts and Telecommunications, 2017.
30 YANGC. Click through rate prediction algorithm based on user’s real-time feedback[J]. Journal of Computer Applications, 2017,37(10): 2866-2870.DOI:10.11772/j.issn.1001-9081.2017.10.2866
31 JOACHIMST, GRANKAL, PANB, et al. Accurately interpreting click through data as implicit feedback[C]// Proceedings of 28th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2005: 154-161.DOI:10.1145/3130332.3130334
32 JOACHIMST. Optimizing search engines using click through data[C]//Proceedings of Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Edmonton: ACM, 2002: 133-142. DOI:10.1145/775047.775067
33 GRAEPELT, CANDELAJ Q, NBORCHERTT, et al. Web-scale Bayesian click-through rate prediction for sponsored search advertising in microsoft’s bing search engine[C]//Proceedings of the 27th International Conference on International Conference on Machine Learning (ICML-10). Haifa: Omni Press, 2010: 13-20.
34 CHAPELLEO, ZHANGY. A dynamic Bayesian network click model for web search ranking[C] //Proceedings of the 18th International Conference on World Wide Web. Madrid: ACM, 2009: 1-10.DOI:10.1145/1526709.1526711
35 ZHANGY Y, DAIH J, XUC, et al. Sequential click prediction for sponsored search with recurrent neural networks[C]//Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence. Québec City: AAAI Press, 2014: 1369-1375.
36 GAIK, ZHUX Q, LIH, et al. Learning piece-wise linear models from large scale data for ad click prediction[J]. arXiv:1704.05194, 2017.
37 GUOZ X. Research on Ads’ Click-Through Rates Predicting Based on Recurrent Neural Networks[D]. Hangzhou: Zhejiang Sci-Tech University, 2014. DOI:10.1063/1.5039130
38 WANGX S. Click-through-Rate Prediction Based on Deep Neural Network Model[D]. Beijing: Beijing University of Posts and Telecommunications, 2015.
39 TUD D, SHUC C, YUH Y. Using unified probabilistic matrix factorization for contextual advertisement recommendation[J]. Journal of Software, 2013(3): 454-464.
40 PANS M, YANN, XIEJ K. Study on advertising click-through rate prediction based on user similarity and feature differentiation[J]. Computer Science, 2017, 44(2): 283-289.
41 MAX, ZHAOL Q, HUANGG, et al. Entire space multi-task model: An effective approach for estimating post-click conversion rate[C]//Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. New York:ACM， 2018: 1137-1140.
42 YOSHIKAWAY, IMAIY. A nonparametric delayed feedback model for conversion rate prediction[J]. arXiv:1802.00255, 2018.
43 FATTAD D, PATTOND, VIGLIAG. The determinants of conversion rates in SME e-commerce websites[J]. Journal of Retailing & Consumer Services, 2018, 41: 161-168.DOI:10.1016/j.jretconser.2017.12.008
[1] 胡东滨,冯婧瑜,杨艺,易国栋. 考虑处置效果的苯系物泄露应急方案生成方法[J]. 浙江大学学报（理学版）, 2022, 49(4): 457-466.