Recommendations : Modeling Music Ratings with Temporal Dynamics and Item Taxonomy

By Noam Koenigstein, Gideon Dror, Yehuda Koren. 2011

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

VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback (2015, background): “…a central role in helping people discover items of personal interest from huge corpora, ranging from movies and music (Bennett and Lanning, 2007; Koenigstein, Dror, and Koren, 2011), to research articles, news and books (Das et al., 2007; Lu et al., 2015), to tags and even other users (Xu et…”
In AI We Trust? Factors That Influence Trustworthiness of AI-infused Decision-Making Processes (2019, background): “s domains such as prison sentence recommendation [14], credit decisions [32], and hiring [8], as well as more familiar lower-stakes domains such as personalized shopping [25] and music recommendation [23]. Despite the growing popularity of training AI-based models to aid human decision makers, littl”
Recommender Systems (2016, unknown): “Similar models have also been applied to the music recommendation scenario [304].”
One-class collaborative filtering with random graphs (2013, background): “For Netflix’s five-star ratings datasets, this error is around one star [11], while an error of around 20 points in the 0-100 scale of the Yahoo! Music dataset is usual [3].”
To Index or Not to Index: Optimizing Exact Maximum Inner Product Search (2017, methodology): “For the Yahoo Music KDD dataset, the LEMP authors evaluated against the model found in [17], which is also considered one of the canonical reference models for this dataset.”
Neural Survival Recommender (2017, background): “Notably due to the Netﬂix prize [2], factorization-based models have been popular even after a decade of its ﬁrst development, and a lot of the eﬀort has been put into improving the performance under various circumstances [1, 23, 34, 35, 15, 21].”
Predicting the Next Location: A Recurrent Model with Spatial and Temporal Contexts (2016, background): “And timeSVD++ (Koren 2010; Koenigstein, Dror, and Koren 2011) extends SVD++ (Koren 2008) in the same way.”
Time-Sensitive Recommendation From Recurrent User Activities (2015, background): “However, since most models in literature are particularly optimized for predicting ratings [16, 23, 15, 3, 25, 13, 21],”
Your neighbors affect your ratings: on geographical neighborhood influence to rating prediction (2014, methodology): “As the most successful realization of latent factor model, matrix factorization (MF) [12,14,17] has been successfully applied to various recommender systems including music rating prediction for Yahoo! Music [11] and Last.”
Latent factor models with additive and hierarchically-smoothed user preferences (2013, background): “Taxonomies are commonly available for many domains [1] [12].”
Collaborative Filtering beyond the User-Item Matrix (2014, background): “One of the most common side information sources is attribute information [Agarwal and Chen 2009; Bao et al. 2009; Gantner et al. 2010a; Koenigstein et al. 2011; Li et al. 2010; Moshfeghi et al. 2011; Shi et .”
Recommending Groups to Users Using User-Group Engagement and Time-Dependent Matrix Factorization (2016, methodology): “Other authors have examined time-dependent methods such as tensor factorization, session-based temporal graph model and dynamic matrix factorization etc. (Xiong et al. 2010; Xiang et al. 2010; Koenigstein, Dror, and Koren 2011; Lathia, Hailes, and Capra 2009; Chua, Oentaryo, and Lim 2013).”
Daily-Aware Personalized Recommendation based on Feature-Level Time Series Analysis (2015, background): “Koren [16] and Xiang [34] adopted the approaches of dynamic modeling through time bins on explicit feedbacks, and sessions on implicit feedbacks, respectively, which were further combined by Dror [11] into Yahoo! Music recommendation and achieved superior results in KddCup-2011; At the same time, Lu”
The Yahoo! Music Dataset and KDD-Cup '11 (2012, unknown): “6 by a matrix factorization model [4].”
Efficient retrieval of recommendations in a matrix factorization framework (2012, methodology): “In fact, we use one such complex MF model (described in [6]) for evaluating our proposed methods.”
Speeding up the Xbox recommender system using a euclidean transformation for inner-product spaces (2014, methodology): “The users and items vectors were generated by the algorithm in [7].”
Time-aware recommender systems: a comprehensive survey and analysis of existing evaluation protocols (2013, methodology): “A different modeling scheme is presented in Koenigstein et al. (2011), where Koenigstein and colleagues use session factors to model specific user behavior in music listening sessions.”