|本期目录/Table of Contents|

[1]陈巧红,孙超红,余仕敏,等.基于递归神经网络的广告点击率预估研究[J].浙江理工大学学报,2016,35-36(自科6):880-885.
　CHEN Qiaohong,SUN Chaohong,YU Shimin,et al.Research on Estimation of Ads Click Rate Based on Recurrent Neural Network[J].Journal of Zhejiang Sci-Tech University,2016,35-36(自科6):880-885.
点击复制

基于递归神经网络的广告点击率预估研究()
分享到：

浙江理工大学学报[ISSN:1673-3851/CN:33-1338/TS]

卷:
第35-36卷
期数:
2016年自科6期
页码:
880-885
栏目:
出版日期:
2016-11-10

文章信息/Info

Title:
Research on Estimation of Ads Click Rate Based on Recurrent Neural Network
文章编号:
1673-3851 (2016) 06-0880-06
作者:
陈巧红; 孙超红; 余仕敏; 贾宇波
浙江理工大学信息学院，杭州 310018
Author(s):
CHEN Qiaohong;  SUN Chaohong;  YU Shimin;  JIA Yubo
School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China
关键词:
广告点击率; 递归神经网络; LSTM; 随机梯度下降; 交叉熵
分类号:
TP181
文献标志码:
A
摘要:
为提高广告点击率的预估准确率，从而提高在线广告的收益，对广告数据进行特征提取和特征降维，采用一种基于LSTM的改进的递归神经网络作为广告点击率预估模型。分别采用随机梯度下降法和交叉熵函数作为预估模型的优化算法和目标函数。实验表明，与逻辑回归、BP神经网络和递归神经网络相比，基于LSTM改进的递归神经网络模型，能有效提高广告点击率的预估准确率。该模型不仅有助于广告服务商制定合理的价格策略，也有助于广告主合理投放广告，实现广告产业链中各个角色的收益最大化。

参考文献/References:

［1］ 艾瑞咨询.艾瑞咨询:2015年中国网络广告行业年度数据监测.(2015-04-20)［2015-12-20］.http://www.iyunying.org/seo/sjfx/12636.html.
［2］ 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.
［3］ JOACHIMS T. Optimizing search engines using clickthrough data［C］//Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data mining. ACM,2002:133-142.
［4］ 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］//Proceedings of the 27th International Conference on Machine Learning(ICML10).2010:13-20.
［5］ 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. ACM,2009:1-10.
［6］ DAVE  K, VARMA V. Predicting the ClickThrough Rate for Rare/New Ads［R］. Centre for Search and Information Extraction LabInternational Institute of Information Technology . Hyderabad,2010.
［7］ RICHARDSON M, DOMINOWSKA E, RAGNO R. Predicting clicks: estimating the clickthrough rate for new ads［C］//Proceedings of the 16th International Conference on World Wide Web. ACM,2007:521-530.
［8］ AGARWAL D, BRODER A Z, CHAKRABARTI D, et al. Estimating rates of rare events at multiple resolutions［C］//Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM,2007:16-25.
［9］ AGARWAL D, AGRAWAL R, KHANNA R, 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.ACM,2010:213-222.
［10］ ZHANG W V, JONES R. Comparing click logs and editorial labels for training query rewriting［C］//WWW 2007 Workshop on Query Log Analysis: Social And Technological Challenges.2007.

相似文献/References:

[1]陈巧红,余仕敏,贾宇波.广告点击率预估技术综述[J].浙江理工大学学报,2015,33-34(自科6):851.
　CHEN Qiao hong,YU Shi min,JIA Yu bo.Overview of Advertisement Clickthrough Rate Estimating Techniques[J].Journal of Zhejiang Sci-Tech University,2015,33-34(自科6):851.
[2]包晓安,常浩浩,徐海,等.基于LSTM的智能家居机器学习系统预测模型研究[J].浙江理工大学学报,2018,39-40(自科2):224.
　BAO Xiaoan,CHANG Haohao,XU Hai,et al.Research on LSTMbased prediction model of smart home machine learning system[J].Journal of Zhejiang Sci-Tech University,2018,39-40(自科6):224.

备注/Memo

备注/Memo:
收稿日期： 2016-04-08
作者简介： 陈巧红(1978- )，女，浙江临海人，副教授，博士，主要从事计算机辅助设计及机器学习技术方面的研究
更新日期/Last Update: 2016-11-21