Personalizing Explainable Recommendations with Multi-objective Contextual Bandits
Speaker: Rishabh Mehrotra, Research Scientist, Spotify Research
Slides: https://www.slideshare.net/SessionsEvents/rishabh-mehrotra-recommendations-in-a-marketplace-personalizing-explainable-recommendations-with-multiobjective-contextual-bandits
Talk Description:
"In recent years, two sided marketplaces have emerged as viable business models in many real world applications (e.g. Amazon, AirBnb, Spotify, YouTube), wherein the platforms have customers not only on the demand side (e.g. users), but also on the supply side (e.g. retailer, artists). Such multi-sided marketplace involves interaction between multiple stakeholders among which there are different individuals with assorted needs. While traditional recommender systems focused specifically towards increasing consumer satisfaction by providing relevant content to the consumers, two-sided marketplaces face an interesting problem of optimizing their models for supplier preferences, and visibility.
In this talk, we begin by describing a contextual bandit model developed for serving explainable music recommendations to users and showcase the need for explicitly considering supplier-centric objectives during optimization. To jointly optimize the objectives of the different marketplace constituents, we present a multi-objective contextual bandit model aimed at maximizing long-term vectorial rewards across different competing objectives. Finally, we discuss theoretical performance guarantees as well as experimental results with historical log data and tests with live production traffic in a large-scale music recommendation service."
Видео Personalizing Explainable Recommendations with Multi-objective Contextual Bandits канала MLconf
Slides: https://www.slideshare.net/SessionsEvents/rishabh-mehrotra-recommendations-in-a-marketplace-personalizing-explainable-recommendations-with-multiobjective-contextual-bandits
Talk Description:
"In recent years, two sided marketplaces have emerged as viable business models in many real world applications (e.g. Amazon, AirBnb, Spotify, YouTube), wherein the platforms have customers not only on the demand side (e.g. users), but also on the supply side (e.g. retailer, artists). Such multi-sided marketplace involves interaction between multiple stakeholders among which there are different individuals with assorted needs. While traditional recommender systems focused specifically towards increasing consumer satisfaction by providing relevant content to the consumers, two-sided marketplaces face an interesting problem of optimizing their models for supplier preferences, and visibility.
In this talk, we begin by describing a contextual bandit model developed for serving explainable music recommendations to users and showcase the need for explicitly considering supplier-centric objectives during optimization. To jointly optimize the objectives of the different marketplace constituents, we present a multi-objective contextual bandit model aimed at maximizing long-term vectorial rewards across different competing objectives. Finally, we discuss theoretical performance guarantees as well as experimental results with historical log data and tests with live production traffic in a large-scale music recommendation service."
Видео Personalizing Explainable Recommendations with Multi-objective Contextual Bandits канала MLconf
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Multi-Armed Bandits: A Cartoon Introduction - DCBA #1Deep Recommender Systems at Facebook feat. Carole-Jean Wu | Stanford MLSys Seminar Episode 24Taming the Monster: A Fast and Simple Algorithm for Contextual BanditsWhy Do Computers Use 1s and 0s? Binary and Transistors Explained.How to learn any language in six months | Chris Lonsdale | TEDxLingnanUniversityReinforcement Learning: Machine Learning Meets Control TheoryHow Recommender Systems Work (Netflix/Amazon)How to learn any language easily | Matthew Youlden | TEDxClaphamRecSys 2016: Paper Session 6 - Deep Neural Networks for YouTube RecommendationsAmazon AI Conclave 2019 - Contextual Bandits for Efficient A/B TestingRecSys 2020 Tutorial: Introduction to Bandits in Recommender SystemsThompson sampling, one armed bandits, and the Beta distributionMusic Recommendations at Spotify - Oskar Stål, SpotifyA Multi-Armed Bandit Framework for Recommendations at Netflix | NetflixNeural Recommender SystemsMIT 6.S191: Reinforcement LearningThe Contextual Bandits ProblemHow to Design and Build a Recommendation System Pipeline in Python (Jill Cates)DM 19 • Duolingo • Design Language: How Duolingo Learned to Teach Everyone • Beth ChasseMachine Learning for Personalization