作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2019, Vol. 45 ›› Issue (1): 178-185,191. doi: 10.19678/j.issn.1000-3428.0049207

• 人工智能及识别技术 • 上一篇    下一篇

基于多源融合特征提取的在线广告预测模型

刘冶1,2,3,刘荻1,2,王砚文3,4,傅自豪2,3,印鉴1,2   

  1. 1.中山大学 数据科学与计算机学院,广州 510006; 2.广东省大数据分析与处理重点实验室,广州 510006; 3.火烈鸟网络(广州)股份有限公司 数据中心,广州 510630; 4.香港理工大学 电子计算学系,中国 香港 999077
  • 收稿日期:2017-11-07 出版日期:2019-01-15 发布日期:2019-01-15
  • 作者简介:刘冶(1989—),男,博士研究生,主研方向为机器学习、神经网络、网络挖掘;刘荻,硕士;王砚文,博士研究生;傅自豪,硕士;印鉴,教授、博士、博士生导师。
  • 基金资助:

    广东省科技计划项目(2012A010701013);广州市科技计划项目(2013J4500059);广州市天河区科技计划项目(201601YG152,201701YG127);广东省大数据分析与处理重点实验室开放基金(2017017,201805)。

Online Advertising Prediction Model Based on Multiple Source Fusion Feature Extraction

LIU Ye 1,2,3,LIU Di 1,2,WANG Yanwen 3,4,FU Zihao 2,3,YIN Jian 1,2   

  1. 1.School of Data and Computer Science,Sun Yat-sen University,Guangzhou 510006,China; 2.Guangdong Provincial Key Laboratory of Big Data Analysis and Processing,Guangzhou 510006,China; 3.Data Center,Flamingo Network Co.,Ltd.,Guangzhou 510630,China; 4.Department of Computing,The Hong Kong Polytechnic University,Hong Kong 999077,China
  • Received:2017-11-07 Online:2019-01-15 Published:2019-01-15

摘要:

针对智能移动终端应用平台上的广告点击率(CTR)预测问题,在传统PC端Web平台在线广告CTR预测方法的基础上,提出一个新的智能移动终端在线广告投放业务架构。基于此架构,构建基于机器学习的在线广告预测模型,对用户基本信息、广告内容、用户使用环境等多源特征进行融合提取,实现在线广告CTR的精确预测。结合移动APP应用环境的特点,将用户历史行为数据加入预测模型进一步提高CTR预测性能。实验结果表明,该模型具有较高的CTR预测准确率。

关键词: 计算广告, 广告点击率, 特征选择, 机器学习, 预测模型

Abstract:

Aiming at the problem of advertising Click Through Rate(CTR) prediction on intelligent mobile devices application platform,this paper proposes a novel online advertising business architecture for intelligent mobile devices based on the traditional CTR prediction method on PC Web platform.With this architecture,an online advertising prediction model based on machine learning is designed to integrate and extract the multiple source features such as user information,advertising content and user usage environment,so as to achieve accurate prediction of online advertising CTR.Combined with the characteristics of the mobile APP application environment,the CTR prediction performance is improved by adding the user’s historical behavior data into the prediction model.Experimental results show that this model has a high accuracy rate of CTR prediction.

Key words: computational advertising, advertising Click Through Rate(CTR), feature selection, machine learning, prediction model

中图分类号: