|本期目录/Table of Contents|

[1]陈巧红,董雯,孙麒,等.基于门控循环单元神经网络的广告点击率预估[J].浙江理工大学学报,2018,39-40(自科5):587-592.
 CHEN Qiaohong,DONG Wen,SUN Qi,et al.Advertisement clickthrough rate predicting based  on gated recurrent unit neural networks[J].Journal of Zhejiang Sci-Tech University,2018,39-40(自科5):587-592.
点击复制

基于门控循环单元神经网络的广告点击率预估()
分享到:

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

卷:
第39-40卷
期数:
2018年自科5期
页码:
587-592
栏目:
出版日期:
2018-08-31

文章信息/Info

Title:
Advertisement clickthrough rate predicting based  on gated recurrent unit neural networks
文章编号:
1673-3851 (2018) 09-0587-06
作者:
陈巧红董雯孙麒贾宇波
浙江理工大学信息学院,杭州 310018
Author(s):
CHEN Qiaohong DONG Wen SUN Qi JIA Yubo
School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China
关键词:
线广告门控循环单元点击率按时间反向传播三方博弈
分类号:
TP181
文献标志码:
A
摘要:
为提高在线广告的投放效果,改善用户广告体验度,增加广告收益,提出了一种基于门控循环单元神经网络模型的广告点击率预估方法。该方法结合了门控循环单元网络特有的门控单元结构和广告数据时序性特点,利用按时间反向传播算法训练网络模型;提出一种门控循环单元神经网络训练步长改进算法,使得训练时间更少,模型更加精确。实验表明,与逻辑斯特回归、随机森林、朴素贝叶斯和循环神经网络模型相比,提出的方法在广告点击率预估的概率上更准确,有助于广告主、媒体和目标受众用户三方博弈,实现共赢。

参考文献/References:

[1] 刘鹏,王超.计算广告[M].北京:人民邮电出版社,2015:24-24.
[2] 刘庆振.计算广告学:大数据时代的广告传播变革:以“互联网+”技术经济范式的视角[J].现代经济探讨,2016(2):87-91.
[3] Dave K S, Varma V. Learning the clickthrough rate for rare/new ads from similar ads[C]// International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM,2010:897-898.
[4] Oentaryo R J, Lim E P, Low J W, et al. Predicting response in mobile advertising with hierarchical importanceaware factorization machine[C]// ACM International Conference on Web Search and Data Mining. ACM,2014:123-132.
[5] Zhu W Y, Wang C H, Shih W Y, et al. SEM: A softmaxbased ensemble model for CTR estimation in realtime bidding advertising[C]// IEEE International Conference on Big Data and Smart Computing. IEEE,2017:5-12.[6] Chapelle O, Zhang Y. A dynamic bayesian network click model for web search ranking[C]// International Conference on World Wide Web. ACM,2009:1-10.
[7] Zhang Y, Dai H, Xu C, et al. Sequential click prediction for sponsored search with recurrent neural networks[C]// TwentyEighth AAAI Conference on Artificial Intelligence. AAAI Press,2014:1369-1375.
[8] Jozefowicz R, Zaremba W, Sutskever I. An empirical exploration of recurrent network architectures[C]// International Conference on International Conference on Machine Learning. JMLR.org,2015:2342-2350.
[9] Tjandra A, Sakti S, Manurung R, et al. Gated recurrent neural tensor network[C]// International Joint Conference on Neural Networks. IEEE,2016:448-455.
[10] Zhou G B, Wu J, Zhang C L, et al. Minimal gated unit for recurrent neural networks[J]. International Journal of Automation and Computing,2016,13(3):226-234.

备注/Memo

备注/Memo:
收稿日期: 2017-10-31
网络出版日期: 2018-05-07
基金项目: 浙江省自然科学基金项目(LY17E050028)
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: 2018-09-12