# 推荐算法综述：协同过滤、基于内容和知识、混合推荐

2.2.2.1 协同过滤

CF 技术也可以分为非概率和概率算法。概率 CF 算法是基于潜在概率模型的 算法。非概率 CF 算法不基于概率模型。非概率 CF 算法是最常用的[29] [30] [31]。最近邻算法是众所周知的 CF 非概率算法。有两种不同类型的最近邻CF算法，它们是基于用户的最近邻居和基于物品的最近邻居。CF算法使用评级矩阵，R，表示完整的 m × n 用户-物品的评级数据，m n 代表第 m 个用户和第 n 个物品。每个条目 Ru,i 表示用户 u 在一定数值范围内评定的物品的分数。矩阵如下公式 2-1所示。

1. 在基于用户的邻居协同过滤推荐系统中(User-based CF)，针对用户 u 对物 品 i 的预测，是基于来自类似用户对该物品的评级。
2. 在基于物品的最近邻居算法中(Item-based CF)，是基于用户的最近邻居算 法的转置。基于物品的算法根据物品之间的相似性进行预测 [29]

2.2.2.2 基于内容的推荐

2.2.2.3 基于知识的推荐

2.2.2.4 混合推荐

[25] Bogers T, Van den Bosch A. Collaborative and content-based filtering for item recommendation on social bookmarking websites[J]. Submitted to CIKM, 2009, 9.

[26] Gunawardana A, Meek C, et al. A unified approach to building hybrid recommender systems. [J]. RecSys, 2009, 9: 117–124.

[27] Huang C L, Huang W L. Handling sequential pattern decay: Developing a two-stage collabo- rative recommender system[J]. Electronic Commerce Research and Applications, 2009, 8(3): 117–129.

[28] Olugbara O O, Ojo S O, Mphahlele M. Exploiting image content in location-based shopping recommender systems for mobile users[J]. International Journal of Information Technology & Decision Making, 2010, 9(05): 759–778.

[29] Schafer J B, Frankowski D, Herlocker J, et al. Collaborative filtering recommender systems [M]//The adaptive web. [S.l.]: Springer, 2007: 291–324

[30] Chen Z, Jiang Y, Zhao Y. A collaborative filtering recommendation algorithm based on user interest change and trust evaluation[J]. International Journal of Digital Content Technology and its Applications, 2010, 4(9): 106–113.

[31] Su X, Khoshgoftaar T M. A survey of collaborative filtering techniques[J]. Advances in artificial intelligence, 2009, 2009.
[32] Ricci F. Mobile recommender systems[J]. Information Technology & Tourism, 2010, 12(3): 205–231.

[33] De Gemmis M, Iaquinta L, Lops P, et al. Preference learning in recommender systems[J]. Preference Learning, 2009, 41.

[34] Pazzani M J, Billsus D. Content-based recommendation systems[M]//The adaptive web. [S.l.]: Springer, 2007: 325–341

[35] Melville P, Sindhwani V. Recommender systems[J]. Encyclopedia of Machine Learning and Data Mining, 2017: 1056–1066.

[36] Rendle S, Gantner Z, Freudenthaler C, et al. Fast context-aware recommendations with factor- ization machines[C]//SIGIR’11. [S.l.: s.n.], 2011: 635–644.

[37] Pham T A N, Li X, Cong G, et al. A general graph-based model for recommendation in event-based social networks[C]//ICDE’15. [S.l.: s.n.], 2015: 567–578.

[38] Cheng C, Yang H, Lyu M R, et al. Where you like to go next: Successive point-of-interest recommendation[C]//IJCAI’13. [S.l.: s.n.], 2013: 2605–2611.

[39] Qiao Z, Zhang P, Cao Y, et al. Combining heterogenous social and geographical information for event recommendation[C]//Twenty-Eighth AAAI conference on artificial intelligence. [S.l.: s.n.], 2014.

[40] Zhang W, Wang J, Feng W. Combining latent factor model with location features for event-based group recommendation[C]//Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining. [S.l.]: ACM, 2013: 910–918.

[关于转载]：本文为“AMiner”官网文章。转载本文请联系原作者获取授权，转载仅限全文转载并保留文章标题及内容，不得删改、添加内容绕开原创保护，且文章开头必须注明：转自“AMiner”官网。谢谢您的合作。