计算机工程

• 人工智能及识别技术 • 上一篇    下一篇

一种带标签的协同过滤广告推荐算法

金紫嫣 1a,张娟 2,李向军 1a,1b,温海平 1a,张华薇 1a   

  1. (1.南昌大学 a.计算机科学与技术系; b.软件学院,南昌330031; 2.共青科技职业学院,江西 共青 332020)
  • 收稿日期:2017-02-21 出版日期:2018-04-15 发布日期:2018-04-15
  • 作者简介:金紫嫣(1993—),女,硕士研究生,主研方向为协同过滤、数据挖掘;张娟,讲师;李向军,教授;温海平、张华薇,硕士研究生。
  • 基金项目:
    国家自然科学基金(61262049,51367014);江西省自然科学基金(20142BAB207011);江西省主要学科学术和技术带头人计划项目(20172BCB22035);江西省青年科学家培养计划项目(20112BCB23004);江西省科技重点研发项目(20161BBG70235,20111B BE50008);江西省教育厅科技计划项目(GJJ161387);江西省研究生创新专项(YC2015-S035)。

A Collaborative Filtering Advertising Recommendation Algorithm with Tag

JIN Ziyan 1a,ZHANG Juan 2,LI Xiangjun 1a,1b,WEN Haiping 1a,ZHANG Huawei 1a   

  1. (1a.Department of Computer Science and Technology; b.School of Software,Nanchang University,Nanchang 330031,China;2.Gongqing Vocational College of Science and Technology,Gongqing,Jiangxi 332020,China)
  • Received:2017-02-21 Online:2018-04-15 Published:2018-04-15

摘要: 为准确预测点击率(CTR)并合理利用其进行广告推荐,基于标签推荐技术与协同过滤方法,提出一种新的混合式广告推荐算法。将广告关键词作为标签引入到Query页的相似性计算中,采用Query页加权综合相似度度量方法降低相似矩阵的稀疏性,建立一种基于广告关键词的搜索广告兴趣模型。使用Top-N策略以减少最近邻候选集的大小,并基于预测CTR筛选出广告推荐结果。通过实验调节Query页加权综合相似度度量参数并验证算法的可扩展性。在KDDCUP2012数据集上的实验结果表明,与传统协同过滤算法、基于标签的推荐算法及基于标签和项目关系的推荐算法相比,带标签的协同过滤广告推荐算法具有更好的可扩展性和较优的推荐质量。

关键词: 广告推荐, 协同过滤, 标签, 广告关键词, 点击率

Abstract: To accurately predict Click-Through Rate(CTR) and make reasonable use of them for advertisement recommendation,based on tag recommendation technology and Collaborative Filtering(CF) methods,a new hybrid advertising recommendation algorithm is proposed.The advertisement key words are introduced into the similarity calculation of Query pages as labels,the sparsity of the similarity matrix is reduced by using Query page weighting comprehensive similarity measure method,and a search advertisement interest model based on the advertisement key words is given.It uses the Top-N policy to reduce the size of the nearest-neighbor candidate sets and filters out the recommended ads based on the predicted CTR,and adjusts Query weighting comprehensive similarity measure parameters and verifies the scalability of the algorithm by experiment.The experimental results on KDDCUP2012 dataset show that compared with traditional collaborative filtering algorithms,tag-based recommendation algorithms and tag-based and project-based recommendation algorithms,the tag-based collaborative filtering advertising recommendation algorithm has better scalability and better recommended quality.

Key words: advertising recommendation, Collaborative Filtering(CF), tag, advertising key words, Click-Through Rate(CTR)

中图分类号: