Online Models for Content Optimization

By Deepak K. Agarwal, Bee-Chung Chen, Pradheep Elango, Nitin Motgi, Seung-Taek Park, Raghu Ramakrishnan, Scott Roy, J. Zachariah. 2008

145 citations recorded by the source corpus.

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 contextual-bandit approach to personalized news article recommendation (2010, methodology): “In practice, we usually explore the unknown by collecting consumers’ feedback in real time to evaluate the popularity of new content while monitoring changes in its value [3].”
Regression-based latent factor models (2009, background): “Yahoo! Front Page (Y!FP) data: Our main motivating application is the Today Module on Yahoo! Front Page[3].”
An Empirical Evaluation of Thompson Sampling (2011, methodology): “In this section, we consider another application of Thompson sampling in personalized news article recommendation on Yahoo! front page [2, 9].”
Reusing historical interaction data for faster online learning to rank for IR (2013, background): “ζ) do 9: (ri, l ′ i1 , l ′ i2 , c ′ i)← sample(h, 1) 10: append(oH , oH(l(p[1].”
Provable Optimal Algorithms for Generalized Linear Contextual Bandits (2017, background): “With the development of modern technologies, contextual bandit problems have more applications, especially in web-based recommendation, advertising and search (Agarwal et al., 2009; Li et al., 2010; 2012).”
A case study of behavior-driven conjoint analysis on Yahoo!: front page today module (2009, methodology): “We estimated the article CTR within segments by the same technique [1] used in the EMP approach.”
Personalized Recommendation via Parameter-Free Contextual Bandits (2015, background): “The aforementioned issues are often recognized as an exploration/exploitation problem, in which we have to ﬁnd a tradeoﬀ between two competing goals: maximizing users’ satisfaction in a long run, while exploring uncertainties of user interests [3].”
fLDA: matrix factorization through latent dirichlet allocation (2010, background): “† Content programming: Consider an application that recommends articles to users visiting a portal [ 3 ].”
Contextual Bandit Algorithms with Supervised Learning Guarantees (2010, background): “The problem we study is personalized news article recommendation on the Yahoo! front page [1, 15].”
Ensemble contextual bandits for personalized recommendation (2014, background): “This issue is often recognized as an exploration/exploitation problem, in which we have to ﬁnd a trade-oﬀ between two competing goals: maximizing users’ satisfaction in a long run, while exploring uncertainties of user interests [1].”
Personalized recommendation on dynamic content using predictive bilinear models (2009, methodology): “The CTR online tracking was implemented with the Kalman filter designed in [1], which has yielded very strong performance in the product.”