登录 | 注册 | 充值 | 退出 | 公司首页 | 繁体中文 | 满意度调查
综合馆
基于核方法的User-Based协同过滤推荐算法
  • 摘要

    作为在实际系统中运用最为广泛和成功的推荐技术,协同过滤算法得到了研究者们的广泛关注.传统的协同过滤算法面临着数据稀疏和冷启动等问题的挑战,在计算用户之间相似度时只能考虑有限的数据,因此难以对用户之间的相似度进行准确的估计.提出了一种基于核密度估计的用户兴趣估计模型,并基于此模型,提出了一种基于核方法的user-based协同过滤推荐算法.通过挖掘用户在有限的评分数据上表现出来的潜在兴趣,该算法能更好地描述用户兴趣在项目空间上的分布,进而可以更好地估计用户之间的兴趣相似度.实验表明,该算法可以有效地提高推荐系统的性能,尤其在数据稀疏的情况下能显著地提高推荐结果的质量.

  • 作者

    王鹏  王晶晶  俞能海  Wang Peng  Wang Jingjing  Yu Nenghai 

  • 作者单位

    中国科学技术大学电子工程与信息科学系 合肥230027

  • 刊期

    2013年7期 ISTIC EI PKU

  • 关键词

    协同过滤  个性化推荐  核方法  数据稀疏  相似性度量  collaborative filtering  personalized recommendation  kernel method  data sparseness  similarity measurement 

参考文献
  • [1] 赵亮,胡乃静,张守志. 个性化推荐算法设计. 计算机研究与发展, 2002,8
  • [2] Wolpert, D.H.;Macready, W.G.. No free lunch theorems for optimization. IEEE transactions on evolutionary computation, 1997,1
  • [3] Pu P;Chen L. Trust building with explanation interfaces. New York:ACM, 2006
  • [4] Pu P;Chen L. Trust-inspiring explanation interfaces for recommender systems. Journal of Knowledge Based Systems, 2007,06
  • [5] Hill W;Stead L;Rosenstein M. Recommending and evaluating choices in a virtual community of use. New York:ACM, 1995
  • [6] Herlocker J;Konstan J A;Riedl J. An empirical analysis of design choices in neighborhood-based collaborative filtering algorithms. Information Retrieval, 2002,04
  • [7] Givens G H;Hoeting J A. Computational Statistics. New York:Wiley-Interscience, 2005
  • [8] Jiang Kai;Wang Peng;Yu Nenghai. ContextRank:Personalized tourism recommendation by exploiting context information of geotagged Web photos. Los Alamitos,CA:IEEE Computer Society, 2011
  • [9] GroupLens. MovieLens Data Sets. http://www.grouplens.org, 2012-05-30
  • [10] Sarwar B;Karypis G;Konstan J. Item-based collaborative filtering recommendation algorithms. New York:ACM, 2001
  • [11] Shi Y;Larson M;Hanjalic A. Exploiting user similarity based on rated-item pools for improved user-basedcollaborative filtering. New York:ACM, 2009
  • [12] Kamishima T;Akaho S. Nantonac collaborative filtering:a model-based approach. New York:ACM, 2010
  • [13] Resnick P;Iacovou N;Suchak M. GroupLens:An open architecture for collaborative filtering of netnews. New York:ACM, 1994
  • [14] Degemmis M;Lops P;Semeraro G. A content-collaborative recommender that exploits wordnet-based user profiles for neighborhood formation. Journal of User Modeling and User-Adapted Interaction, 2007,03
  • [15] Zhou Ke;Yang Shuanghong;Zha Hongyuan. Functional matrix factorizations for cold-start recommendation. New York:ACM, 2011
  • [16] Deshpande M;Karypis G. Item-based top-N recommendation algorithms. ACM Transactions on Information Systems, 2004,t
  • [17] Breese J S;Heckerman D;Kadie C. Empirical analysis of predictive algorithms for collaborative filtering. San Francisco:Morgan Kaufmann Publishers, 1998
  • [18] Last.fm. Music recommendation service. http://www.last.fm, 2012-05-30
  • [19] Melville P;Mooney R J;Nagarajan R. Content-boosted collaborative filtering for improved recommendations. Menlo Park:American Association for Artificial Intelligence, 2002
  • [20] Billsus D;Pazzani M J. Learning collaborative information filters. San Francisco:Morgan Kaufmann Publishers, 1998
查看更多︾
相似文献 查看更多>>
34.228.38.35