{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dynamic-learning-of-sequential-choice-bandit","title":"Dynamic Learning of Sequential Choice Bandit Problem under Marketing Fatigue","arxiv_id":"1903.08193","date":"2019-03-19","proceeding":null,"authors":["Junyu Cao","Wei Sun"],"abstract":"Motivated by the observation that overexposure to unwanted marketing\nactivities leads to customer dissatisfaction, we consider a setting where a\nplatform offers a sequence of messages to its users and is penalized when users\nabandon the platform due to marketing fatigue. We propose a novel sequential\nchoice model to capture multiple interactions taking place between the platform\nand its user: Upon receiving a message, a user decides on one of the three\nactions: accept the message, skip and receive the next message, or abandon the\nplatform. Based on user feedback, the platform dynamically learns users'\nabandonment distribution and their valuations of messages to determine the\nlength of the sequence and the order of the messages, while maximizing the\ncumulative payoff over a horizon of length T. We refer to this online learning\ntask as the sequential choice bandit problem. For the offline combinatorial\noptimization problem, we show that an efficient polynomial-time algorithm\nexists. For the online problem, we propose an algorithm that balances\nexploration and exploitation, and characterize its regret bound. Lastly, we\ndemonstrate how to extend the model with user contexts to incorporate\npersonalization.","url_abs":"http://arxiv.org/abs/1903.08193v1","url_pdf":"http://arxiv.org/pdf/1903.08193v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dynamic-learning-of-sequential-choice-bandit","repo_url":"https://github.com/bettyttytty/Thompson-Sampling-for-a-Fatigue-aware-Online-Recommendation-System","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"combinatorial-optimization","task_name":"Combinatorial Optimization"},{"task_slug":"marketing","task_name":"Marketing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1903.08193","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}