Patents by Inventor Alois Gruson

Alois Gruson has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Personalizing explainable recommendations with bandits
    Patent number: 11977577
    Abstract: Methods, systems and computer program products are provided personalizing recommendations of items with associated explanations. The example embodiments described herein use contextual bandits to personalize explainable recommendations (“recsplanations”) as treatments (“Bart”). Bart learns and predicts satisfaction (e.g., click-through rate, consumption probability) for any combination of item, explanation, and context and, through logging and contextual bandit retraining, can learn from its mistakes in an online setting.
    Type: Grant
    Filed: June 8, 2023
    Date of Patent: May 7, 2024
    Assignee: Spotify AB
    Inventors: James E. McInerney, Benjamin Lacker, Samantha Hansen, Aloïs Gruson, Rishabh Mehrotra, Hugues Bouchard
  • PERSONALIZING EXPLAINABLE RECOMMENDATIONS WITH BANDITS
    Publication number: 20230376529
    Abstract: Methods, systems and computer program products are provided personalizing recommendations of items with associated explanations. The example embodiments described herein use contextual bandits to personalize explainable recommendations (“recsplanations”) as treatments (“Bart”). Bart learns and predicts satisfaction (e.g., click-through rate, consumption probability) for any combination of item, explanation, and context and, through logging and contextual bandit retraining, can learn from its mistakes in an online setting.
    Type: Application
    Filed: June 8, 2023
    Publication date: November 23, 2023
    Applicant: Spotify AB
    Inventors: James E. McInerney, Benjamin Lacker, Samantha Hansen, Aloïs Gruson, Rishabh Mehrotra, Hugues Bouchard
  • Personalizing explainable recommendations with bandits
    Patent number: 11709886
    Abstract: Methods, systems and computer program products are provided personalizing recommendations of items with associated explanations. The example embodiments described herein use contextual bandits to personalize explainable recommendations (“recsplanations”) as treatments (“Bart”). Bart learns and predicts satisfaction (e.g., click-through rate, consumption probability) for any combination of item, explanation, and context and, through logging and contextual bandit retraining, can learn from its mistakes in an online setting.
    Type: Grant
    Filed: March 7, 2022
    Date of Patent: July 25, 2023
    Assignee: Spotify AB
    Inventors: James E. McInerney, Benjamin Lacker, Samantha Hansen, Alois Gruson, Rishabh Mehrotra, Hugues Bouchard
  • PERSONALIZING EXPLAINABLE RECOMMENDATIONS WITH BANDITS
    Publication number: 20220237226
    Abstract: Methods, systems and computer program products are provided personalizing recommendations of items with associated explanations. The example embodiments described herein use contextual bandits to personalize explainable recommendations (“recsplanations”) as treatments (“Bart”). Bart learns and predicts satisfaction (e.g., click-through rate, consumption probability) for any combination of item, explanation, and context and, through logging and contextual bandit retraining, can learn from its mistakes in an online setting.
    Type: Application
    Filed: March 7, 2022
    Publication date: July 28, 2022
    Applicant: Spotify AB
    Inventors: James E. McInerney, Benjamin Lacker, Samantha Hansen, Aloïs Gruson, Rishabh Mehrotra, Hugues Bouchard
  • Personalizing explainable recommendations with bandits
    Patent number: 11301513
    Abstract: Methods, systems and computer program products are provided personalizing recommendations of items with associated explanations. The example embodiments described herein use contextual bandits to personalize explainable recommendations (“recsplanations”) as treatments (“Bart”). Bart learns and predicts satisfaction (e.g., click-through rate, consumption probability) for any combination of item, explanation, and context and, through logging and contextual bandit retraining, can learn from its mistakes in an online setting.
    Type: Grant
    Filed: July 3, 2019
    Date of Patent: April 12, 2022
    Assignee: Spotify AB
    Inventors: James E. McInerney, Benjamin Lacker, Samantha Hansen, Aloïs Gruson, Rishabh Mehrotra, Hugues Bouchard
  • PERSONALIZING EXPLAINABLE RECOMMENDATIONS WITH BANDITS
    Publication number: 20200012681
    Abstract: Methods, systems and computer program products are provided personalizing recommendations of items with associated explanations. The example embodiments described herein use contextual bandits to personalize explainable recommendations (“recsplanations”) as treatments (“Bart”). Bart learns and predicts satisfaction (e.g., click-through rate, consumption probability) for any combination of item, explanation, and context and, through logging and contextual bandit retraining, can learn from its mistakes in an online setting.
    Type: Application
    Filed: July 3, 2019
    Publication date: January 9, 2020
    Inventors: James E. McInerney, Benjamin Lacker, Samantha Hansen, Aloïs Gruson, Rishabh Mehrotra