
Recommender Systems Optimization Goals
In part two of the Data Skeptic Recommender Systems season finale, Kyle asks a deceptively difficult question: what should recommender systems actually optimize for? Drawing on conversations from across the season, the episode explores engagement, filter bubbles, popularity bias, fairness, human curation, embeddings, and the growing role - and risks - of large language models in shaping what gets recommended to us.
Audio and video play straight from the show's own hosting. PodSubs stores and serves no media.
