Personalized Ad Recommendation Systems for Life-Time Value Optimization with Guarantees

By Georgios Theocharous, Philip S. Thomas, Mohammad Ghavamzadeh. 2015

125 citations recorded by the source corpus.

Subfields: Optimization & Training, Recommender Systems

How researchers see this paper

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

In Optimization & Training

In Recommender Systems

Citations in the corpus

Bridging the Gap Between Value and Policy Based Reinforcement Learning (2017, background): “Model-free RL has a myriad of applications in games [22, 37], robotics [16, 17], and marketing [18, 38], to name a few.”
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems (2020, background): “…offline data has included studies on optimizing newspaper article click-through-rates (Strehl et al., 2010; Garcin et al., 2014), advertisement ranking on search pages (Bottou et al., 2013), and personalized ad recommendation for digital marketing (Theocharous et al., 2015; Thomas et al., 2017).”
Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning (2016, methodology): “…of a reinforcement learning algo-rithm has already deployed some policy, e.g., for determining which advertisement to show a user visiting a website (Theocharous et al., 2015), for determining which medical treatment to suggest for a patient (Thapa et al., 2005), or for suggesting a personalized…”
More Robust Doubly Robust Off-policy Evaluation (2018, background): “2015; Jiang & Li 2016; Thomas & Brunskill 2016), and some of the results have been applied to problems in marketing (e.g., Li et al. 2011; Theocharous et al. 2015), healthcare (e.”
Benchmarks for Deep Off-Policy Evaluation (2021, background): “, 2018), recommender systems (Dudík et al., 2014; Theocharous et al., 2015; Swaminathan et al., 2017), education (Mandel et al.”
Recurrent Reinforcement Learning: A Hybrid Approach (2015, methodology): “Closest to this work is a recent application of DQN to CRM (Tkachenko, 2015), which uses the same benchmark data.”
Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling (2019, methodology): “…RL algorithms have already been deployed, e.g., targeted advertising and marketing [Bottou et al., 2013; Tang et al., 2013; Chapelle et al., 2015; Theocharous et al., 2015; Thomas et al., 2017] or medical treatments [Murphy et al., 2001; Ernst et al., 2006; Raghu et al., 2017], online policy…”
Off-Policy Evaluation via Off-Policy Classification (2019, background): “Prior works [7, 10, 13, 21, 28, 34] do so with importance sampling (IS) [11], MDP modeling, or both.”
Towards Safe Policy Improvement for Non-Stationary MDPs (2020, unknown): “Non-stationary Recommender System (RecoSys): Online recommendation systems for tutorials, movies, advertisements and other products are ubiquitous [54, 55].”
On Ensuring that Intelligent Machines Are Well-Behaved (2017, background): “In our past work we found that Seldonian batch reinforcement learning algorithms often require large amounts of data, which although practical for big-data problems [Theocharous et al., 2015], often is not practical.”
Preventing undesirable behavior of intelligent machines (2019, background): “Although practical when large amounts of data are available, as in problems involving “big-data” [145], for many problems it is difficult to obtain the needed amount of data.”
Autonomous navigation of stratospheric balloons using reinforcement learning (2020, background): “Reinforcement learning has proven effective in optimization problems in which a model of the process is available 13–16 , and has shown promising results in simulations of real applications and back-testing 17–20 with some commercial success in internet applications 21,22 .”
Deep Reinforcement Learning: An Overview (2017, background): “Theocharous et al. (2015) formulated a personalized Ad recommendation systems as an RL problem to maximize life-time value (LTV) with theoretical guarantees.”
Reinforcement Knowledge Graph Reasoning for Explainable Recommendation (2019, background): “nderstand the environment, and enabling them to infer high-level causal relationships. There have been attempts to invoke RL in recommender systems in a non-KG setting, such as for ads recommendation [25], news recommendation [35] and post-hoc explainable recommendation [27]. At the same time, resea”
Predictive Off-Policy Policy Evaluation for Nonstationary Decision Problems, with Applications to Digital Marketing (2017, background): “For example, this sort of jump may occur in digital marketing applications (Theocharous, Thomas, and Ghavamzadeh 2015) due to media coverage of a relevant topic rapidly changing public opinion of a product.”