计算机应用 ›› 2017, Vol. 37 ›› Issue (10): 2866-2870.DOI: 10.11772/j.issn.1001-9081.2017.10.2866

• 人工智能 • 上一篇    下一篇

基于用户实时反馈的点击率预估算法

杨诚   

  1. 常州信息职业技术学院 网络与通信工程学院, 江苏 常州 213164
  • 收稿日期:2017-04-17 修回日期:2017-06-08 出版日期:2017-10-10 发布日期:2017-10-16
  • 通讯作者: 杨诚(1975-),男,江苏常州人,副教授,硕士,CCF会员,主要研究方向:机器学习、数据挖掘,E-mail:phlsage@163.com
  • 作者简介:杨诚(1975-),男,江苏常州人,副教授,硕士,CCF会员,主要研究方向:机器学习、数据挖掘.

Click through rate prediction algorithm based on user's real-time feedback

YANG Cheng   

  1. School of Network and Communication Engineering, Changzhou College of Information Technology, Changzhou Jiangsu 213164, China
  • Received:2017-04-17 Revised:2017-06-08 Online:2017-10-10 Published:2017-10-16

摘要: 当前主流的在线广告点击率(CTR)预估算法主要通过机器学习方法从大规模日志数据中挖掘用户与广告间的相关性从而提升点击率预估精度,其不足之处在于没有充分考虑用户实时行为对CTR的影响。对大规模真实在线广告日志进行分析后发现,在会话中,用户CTR的动态变化和用户先前的反馈行为高度相关,不同的用户行为对用户实时CTR的影响不尽相同。基于上述分析结果,提出一种基于用户实时反馈的点击率预估算法。首先,从大规模真实在线广告日志数据中定量分析用户反馈和点击率预估精度的相关关系;然后,根据分析结果将用户的反馈行为特征化;最后,使用机器学习方法对用户的行为进行建模,并根据用户的反馈实时动态调整广告投放,从而提升在线广告系统的点击率预估精度。实验结果表明,用户实时反馈特征和用户点击率高度相关;相比于传统没有用户实时反馈信息的预测模型,该算法在测试集上对AUC(Area Under the Curve)和RIG(Relative Information Gain)指标提升分别为0.83%和6.68%。实验结果表明,用户实时反馈特征显著提高点击率预估的精度。

关键词: 机器学习, 计算广告学, 点击率预估, 个性化, 实时反馈

Abstract: At present, most of the Click Through Rate (CTR) prediction algorithms for online advertising mainly focus on mining the correlation between users and advertisements from large-scale log data by using machine learning methods, but not considering the impact of user's real-time feedback. After analyzing a lot of real world online advertising log data, it is found that the dynamic changes of CTR is highly correlated with previous feedback of user, which is that the different behaviors of users typically have different effects on real-time CTR. On the basis of the above analysis, an algorithm based on user's real-time feedback was proposed. Firstly, the correlation between user's feedback and real-time CTR were quantitatively analyzed on large scale of real world online advertising logs. Secondly, based on the analysis results, the user's feedback was characterized and fed into machine learning model to model the user's behavior. Finally, the online advertising impression was dynamically adjusted by user's feedback, which improves the precision of CTR prediction. The experimental results on real world online advertising datasets show that the proposed algorithm improves the precision of CTR prediction significantly, compared with the contrast models, the metrics of Area Under the ROC Curve (AUC) and Relative Information Gain (RIG) are increased by 0.83% and 6.68%, respectively.

Key words: machine learning, computational advertising, Click Through Rate (CTR) prediction, personalization, real-time feedback

中图分类号: