Recommender Systems Optimization Goals
Podcast: Data SkepticPublished On: Tue Sep 01 2026
Description: 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.
The note was deleted
The note was saved
Your message was sent