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。
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.
作者
刘华玲
恽文婧
林蓓
丁宇杰
LIU Hualing;YUN Wenjing;LIN Bei;DING Yujie(School of Statistics and Information,Shanghai University of International Business and Economics,Shanghai 201620,China;School of Information Management and Engineering,Shanghai University of Finance and Economics,Shanghai 200433,China)
出处
《浙江大学学报（理学版）》
CAS
CSCD
北大核心
2019年第5期565-573,共9页
Journal of Zhejiang University（Science Edition）
基金
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)
关键词
点击率预估
特征学习
网络广告
click rate estimation
feature learning
online advertising
