基于矩阵分解的最近邻推荐系统及其应用
|
摘要
网络和电子商务的发展,促进了推荐系统的应用。最近邻推荐算法有很直观的解释而在推荐系统中发挥着巨大作用。随着海量数据的可获得性,传统的推荐算法在推荐系统中表现不佳。矩阵分解作为一种新的推荐算法极大地提高了稀疏评分矩阵的推荐质量。文章将矩阵分解的结果应用于基于用户的最近邻推荐系统,其优势在于充分考虑了用户与项目及用户之间的联系。将该方法应用于书籍评分数据,提高了预测精度且能对结果作出很好的解释。
The development of network and e-commerce promotes the application of recommender system. Nearest neighbor recommendation algorithm has a very intuitive explanation and plays an important role in the recommender system. With the availability of massive amounts of data, traditional recommendation algorithms do not perform well in the recommendation system. As a new recommendation algorithm, matrix decomposition greatly improves the quality of the recommendation in the sparse score matrix. This paper applies the results of matrix decomposition to the nearest neighbor recommendation system based on users, with advantage of fully considering the relationship between users and items. The application of the proposed method in book rating data improves the prediction precision and gives a good explanation of the results.
The development of network and e-commerce promotes the application of recommender system. Nearest neighbor recommendation algorithm has a very intuitive explanation and plays an important role in the recommender system. With the availability of massive amounts of data, traditional recommendation algorithms do not perform well in the recommendation system. As a new recommendation algorithm, matrix decomposition greatly improves the quality of the recommendation in the sparse score matrix. This paper applies the results of matrix decomposition to the nearest neighbor recommendation system based on users, with advantage of fully considering the relationship between users and items. The application of the proposed method in book rating data improves the prediction precision and gives a good explanation of the results.
引文
[1]Blancofernandez Y,Pazosarias J J,Gilsolla A,et al.Providing Entertainment by Content-based Filtering and Semantic Reasoning in Intelligent Recommender Systems[J].IEEE Transactions on Consumer Electronics,2008,54(2).
[2]Lops P,Gemmis M D,Semeraro G.Content-based Recommender Systems:State of the Art and Trends[M].Recommender Systems Handbook.Springer US,2011.
[3]Mooney R J,Roy L.Content-based Book Recommending Using Learning for Text Categorization[C].ACM,2000.
[4]Pazzani M J,Billsus D.Content-based Recommendation Systems[M].The Adaptive Web.Springer-Verlag,2007.
[5]Bell R M,Koren Y.Scalable Collaborative Filtering With Jointly Derived Neighborhood Interpolation Weights[C].IEEE International Conference on Data Mining.IEEE,2007.
[6]Koren Y.Factor in the Neighbors:Scalable and Accurate Collaborative Filtering[J].Acm Transactions on Knowledge Discovery From Data,2010,4(1).
[7]Koren Y,Bell R,Volinsky C.Matrix Factorization Techniques for Recommender Systems[J].Computer,2009,42(8).
[8]Cacheda F,Formoso V.Comparison of Collaborative Filtering Algorithms:Limitations of Current Techniques and Proposals for Scalable,High-performance Recommender Systems[J].Acm Transactions on the Web,2011,5(1).
[9]Nguyen J,Zhu M.Content-boosted Matrix Factorization Techniques for Recommender Systems[J].Statistical Analysis&Data Mining the Asa Data Science Journal,2013,6(4).
[10]Wu M.Collaborative Filtering via Ensembles of Matrix Factorizations[J].Proceedings of Kdd Cup&Workshop,2007,(30).
[11]Melville P,Mooney R J,Nagarajan R.Content-boosted Collaborative filtering for Improved Recommendations[C].Eighteenth National Conference on Artificial Intelligence,American Association for Artificial Intelligence,2002./
[2]Lops P,Gemmis M D,Semeraro G.Content-based Recommender Systems:State of the Art and Trends[M].Recommender Systems Handbook.Springer US,2011.
[3]Mooney R J,Roy L.Content-based Book Recommending Using Learning for Text Categorization[C].ACM,2000.
[4]Pazzani M J,Billsus D.Content-based Recommendation Systems[M].The Adaptive Web.Springer-Verlag,2007.
[5]Bell R M,Koren Y.Scalable Collaborative Filtering With Jointly Derived Neighborhood Interpolation Weights[C].IEEE International Conference on Data Mining.IEEE,2007.
[6]Koren Y.Factor in the Neighbors:Scalable and Accurate Collaborative Filtering[J].Acm Transactions on Knowledge Discovery From Data,2010,4(1).
[7]Koren Y,Bell R,Volinsky C.Matrix Factorization Techniques for Recommender Systems[J].Computer,2009,42(8).
[8]Cacheda F,Formoso V.Comparison of Collaborative Filtering Algorithms:Limitations of Current Techniques and Proposals for Scalable,High-performance Recommender Systems[J].Acm Transactions on the Web,2011,5(1).
[9]Nguyen J,Zhu M.Content-boosted Matrix Factorization Techniques for Recommender Systems[J].Statistical Analysis&Data Mining the Asa Data Science Journal,2013,6(4).
[10]Wu M.Collaborative Filtering via Ensembles of Matrix Factorizations[J].Proceedings of Kdd Cup&Workshop,2007,(30).
[11]Melville P,Mooney R J,Nagarajan R.Content-boosted Collaborative filtering for Improved Recommendations[C].Eighteenth National Conference on Artificial Intelligence,American Association for Artificial Intelligence,2002./