Filters








5 Hits in 2.1 sec

TopRec

Xi Zhang, Jian Cheng, Ting Yuan, Biao Niu, Hanqing Lu
2013 Proceedings of the 22nd international conference on World Wide Web - WWW '13  
In this paper, we propose a unified framework, TopRec, which detects topical communities to construct interpretable domains for domain-specific collaborative filtering.  ...  Traditionally, Collaborative Filtering assumes that similar users have similar responses to similar items.  ...  Memory-based CF algorithm usually search for the similar users or items to produce a prediction or top-n recommendation [22, 9] .  ... 
doi:10.1145/2488388.2488519 dblp:conf/www/ZhangCYNL13 fatcat:ybcj3rfxzjbrddn5yvepvoscwy

TopRecs + : Pushing the Envelope on Recommender Systems

Mohammad Khabbaz, Min Xie, Laks V. S. Lakshmanan
2011 IEEE Data Engineering Bulletin  
We follow item-based collaborative filtering (CF) [4] , which is used widely in academia and practice [14, 5] .  ...  Rating Matrix Item Recommendation Process Item Metadata Package Recommendation Process Users Similarity Matrix Top-k Item Recommendation Algorithm Top-k Items Top-k Packages TopRecs + Figure  ... 
dblp:journals/debu/KhabbazXL11 fatcat:5o2cciyusvgnll6m6rvgtdntma

Fast Group Recommendations by Applying User Clustering [chapter]

Eirini Ntoutsi, Kostas Stefanidis, Kjetil Nørvåg, Hans-Peter Kriegel
2012 Lecture Notes in Computer Science  
We efficiently aggregate the single user recommendations into group recommendations by leveraging the power of a top-k algorithm. We evaluate our approach in a real dataset of movie ratings.  ...  However, there are contexts in which the items to be suggested are not intended for a single user but for a group of people.  ...  The k most prominent items for the group are identified by exploiting a top-k algorithm.  ... 
doi:10.1007/978-3-642-34002-4_10 fatcat:mxyaxzitp5fhnp34nmdxoc4e3q

Fifty Shades of Ratings

Evgeny Frolov, Ivan Oseledets
2016 Proceedings of the 10th ACM Conference on Recommender Systems - RecSys '16  
Conventional collaborative filtering techniques treat a top-n recommendations problem as a task of generating a list of the most relevant items.  ...  Due to that bias, standard algorithms, as well as commonly used evaluation metrics, become insensitive to negative feedback.  ...  Conventional collaborative filtering algorithms, such as matrix factorization or similarity-based models, tend to favor similar items, which are likely to be irrelevant in that case.  ... 
doi:10.1145/2959100.2959170 dblp:conf/recsys/FrolovO16 fatcat:fepqjkbgszh75p2sao5iacutei

A Survey of Recommender System from Data Sources Perspective

Huaiyu Pi, Zhenyan Ji, Chun Yang
2018 Proceedings of the 2018 8th International Conference on Management, Education and Information (MEICI 2018)   unpublished
Collaborative filtering, as a classical algorithm, has become the basis of the recommender system.  ...  In recent years, there are more and more recommender systems based on multiple data sources are proposed.  ...  Acknowledgements Supported by the Fundamental Research Funds for the Central Universities (2017YJS215).  ... 
doi:10.2991/meici-18.2018.2 fatcat:sltkgknckfhqbosx56yyml3nze