Learning Collaborative Information Filters

By Daniel Billsus, Michael J. Pazzani. 1998

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

A Neural Autoregressive Approach to Collaborative Filtering (2016, neutral): “Speciﬁcally, Billsus & Pazzani (1998) proposed to apply Singular Value Decomposition (SVD) to CF tasks, which is an early work on MF-based CF. Bias MF (Ko-ren et al., 2009) is proposed to improve the performance of SVD by introducing systematic biases associated with users and items.”
Evaluating collaborative filtering recommender systems (2004, methodology): “For the evaluation of recommender systems, they have been used by Billsus and Pazzani [1998], Basu et al. [1998], and Sarwar et al. [2000a, 2000b].”
A Taxonomy of Recommender Agents on the Internet (2003, background): “Some examples of classiﬁers are implemented in Basu et al. (1998), Good et al. (1999) and Billsus and Pazzani (1998).”
Multi-Domain Collaborative Filtering (2010, methodology): “Among all model-based CF methods, matrix factorization methods are perhaps the most popular one in recent years [2, 25, 20, 5, 21, 22, 14, 32, 29].”
Discovering Urban Functional Zones Using Latent Activity Trajectories (2015, background): “The frequency of POI is not an intrinsic representation of the latent structure of the POI configuration for each region [9], thus it is not suitable for measuring the similarity of location semantics between regions.”
Robust Matrix Completion via Joint Schatten p-Norm and lp-Norm Minimization (2012, methodology): “Besides comparing the matrix completion methods as in previous subsections, we also compare our method to two link prediction methods which are widely used in the studies of social networks, including common neighbors (CN) method [24] and SVD method [25].”
Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions (2005, methodology): “Both [15] and [11] compare their respective model-based approaches with standard memory-based approaches and report that, in some applications, model-based methods outperform memory-based approaches in terms of accuracy of recommendations.”
Addressing cold-start problem in recommendation systems (2008, methodology): “…users into classes [3], simultaneously hard-clustering users and items [16], soft-clustering users and items [8, 11], singular value decomposition [13], inferring item-item similarities [14], probabilistic modeling [3, 11, 12, 20], machine learning [2], and list ranking [4, 10] have been employed.”
An Empirical Analysis of Design Choices in Neighborhood-Based Collaborative Filtering Algorithms (2002, methodology): “1998), singular value decomposition with neural net classification (Billsus and Pazzani 1998), inductive rule learning (Basu et al.”
Weighted Low-Rank Approximations (2003, methodology): “Billsus and Pazzani (1998) use a singular value decomposition of a sparse binary observation matrix.”
A Comprehensive Survey of Neighborhood-based Recommendation Methods (2011, methodology): “For items in the form of text documents, such as news articles [8, 44] or Web documents [7, 58], this vector often contains the Term Frequency-Inverse Document Frequency (TFIDF) [65] weights of the most informative keywords.”
Understanding and improving automated collaborative filtering systems (2000, methodology): “Other algorithmic methods that have been used are Bayesian networks[12], singular value decomposition with neural net classification[10], and induction rule learning[16].”
A Harmonic Extension Approach for Collaborative Ranking (2016, methodology): “Popular model-based methods such as regularized SVD [3] minimize the sum-of-squares error over all the observed ratings.”
Recommender Systems (2016, unknown): “The relationship between collaborative filtering and classification is discussed in [82].”
Collaborative Filtering: A Machine Learning Perspective (2004, unknown): “The framework of Billsus and Pazzani also obscures the true relationship between standard classification techniques from machine learning, and the set of methods popularized by Resnick et al. [49], Shardanand and Maes [52], and Herlocker et al [27].”
Recommender Systems for Large-scale E-Commerce : Scalable Neighborhood Formation Using Clustering (2002, background): “In particular, since the correlation coefficient is only defined between customers who have rated at least two products in common, many pairs of customers have no correlation at all [1].”
Collaborative Recommendation via Adaptive Association Rule Mining (2000, methodology): “Billsus and Pazzani [4] tested three collaborative recommendation techniques on the EachMovie dataset: a correlation-based method, neural networks paired with Information Gain, and neural networks paired with Singular Value Decomposition.”
Beyond Recommender Systems: Helping People Help Each Other (2001, background): “Billsus and Pazzani [8] took another approach to addressing problems with collaborative filtering.”
Unifying collaborative and content-based filtering (2004, methodology): “Similarly, the approaches of (Billsus & Pazzani, 1998) and (Crammer & Singer, 2002) described above can directly incorporate item features, if available.”