Industry report: Amazon.com recommendations: Item-to-item collaborative filtering

Citations in the corpus

On the Effectiveness of Linear Models for One-Class Collaborative Filtering (2016, methodology): “Typically, one chooses the similarity matrix S ∗ as a prede-ﬁned function of R , such as cosine similarity (Sarwar et al. 2001; Linden, Smith, and York 2003): for item-based meth-ods, this is given by Other examples are the Pearson correlation, Jaccard coef-ﬁcient and conditional probability…”
QoS Ranking Prediction for Cloud Services (2013, background): “The most analyzed examples of memory-based collaborative filtering include user-based approaches [4], [9], item-based approaches [7], [11], [16], and their fusion [13], [16], [17], [22], [23].”
Collaborative Web Service QoS Prediction via Neighborhood Integrated Matrix Factorization (2013, background): “The most analyzed examples of neighborhood-based collaborative filtering include user-based approaches [21], [37], item-based approaches [38], [39], and their fusion [40], [23].”
The Behavioral Intervention Technology Model: An Integrated Conceptual and Technological Framework for eHealth and mHealth Interventions (2014, methodology): “…personalization, adaptive systems, using artificial intelligence and machine learning techniques, can potentially use population-level data along with individual user data to determine the workflow of an intervention, similar to commercial recommendation systems such as Netflix or Amazon [25-27].”
A Comprehensive Survey on Poisoning Attacks and Countermeasures in Machine Learning (2022, methodology): “Literature Adversarial Setting Target Model Poisoning Technique Application Evaluation Year Knowledge Capability [106] N-K to P-K IN PCA data inserting intrusion detection ROC 2009 [10] N-K to L-K MO SVM label manipulation binary classification accuracy 2011 [11] P-K IN SVM data manipulation image c”
Tagommenders: connecting users to items through tags (2009, unknown): “Most recommender systems now follow Amazon s model.”
Recommender Systems (2016, unknown): “Subsequently, item-based methods [181, 360, 524] were proposed, which compute predicted ratings as a function of the ratings of the same user on similar items.”
GraphJet: Real-Time Content Recommendations at Twitter (2016, background): “Although there is a tremendous amount of work on recommender systems in the academic literature, relatively few papers describe actual production systems, and those that do (e.g., [29, 10, 1]) focus mostly on algorithms, as opposed to systems infrastructure—which is the perspective we take.”
We know what you want to buy: a demographic-based system for product recommendation on microblogs (2014, background): “Research has found that product recommendation largely inﬂuences consumers’ purchase decisions and is likely to boost sales [23, 26, 14].”