System and method for recommending items in a social network

Stéphane Caron, Branislav Kveton, Marc Lelarge and Smriti Bhagat. US Patent Application US-20150199715-A1.


I'm not particularly proud of this. The patent system stems from a laudable principle: incenting companies to disclose technological knowledge, lest it is lost if the company shuts down. Yet, contemporary patent systems suffer from patent trolls. Legal threats, and the resulting dynamics where companies file offensive or defensive patents, makes me doubt that patents support technological advancement so much as they participate in monopoly consolidation.


The present principles consider stochastic bandits with side observations, a model that accounts for both the exploration/exploitation dilemma and relationships between arms. In this setting, after pulling an arm i, the decision maker also observes the rewards for some other actions related to i. The present principles provide a method and a system for efficiently leveraging additional information based on the responses provided by other users connected to the user via a computerized social network and derive new bounds improving on standard regret guarantees. We will see that this model is suited to content recommendation in social networks, where users' reactions may be endorsed or not by their friends.


  title = {System and method for recommending items in a social network},
  author = {St{\'e}phane Caron and Branislav Kveton and Marc Lelarge and Smriti Bhagat},
  year = {2015},
  month = jul,
  note = {US Patent App. 14/411,856},
  url = {},
© Stéphane Caron — All content on this website is licensed under the CC BY 4.0 license.