from Hacker News

Calibrating Recommendations to Better Match User Interests

by skelts on 12/19/24, 1:54 PM with 2 comments

  • by skelts on 12/19/24, 1:54 PM

    Recommender systems often overfocus on dominant interests, neglecting diversity. Shaped introduces a method to calibrate recommendations using minimum-cost flow optimization, ensuring results reflect the breadth of user preferences. This approach improves balance and relevance, outperforming standard methods.
  • by yurimo on 12/19/24, 4:19 PM

    How do you define and quantify ‘calibration’ in this context? Is it purely based on aligning recommendations with explicit user preferences, or are you also trying to infer latent interests?