{"version":1,"type":"rich","provider_name":"Libsyn","provider_url":"https:\/\/www.libsyn.com","height":90,"width":600,"title":"Recommender Systems Optimization Goals","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\u2014and risks\u2014of large language models in shaping what gets recommended to us. ","author_name":"Data Skeptic","author_url":"https:\/\/dataskeptic.com","html":"<iframe title=\"Libsyn Player\" style=\"border: none\" src=\"\/\/html5-player.libsyn.com\/embed\/episode\/id\/42647865\/height\/90\/theme\/custom\/thumbnail\/yes\/direction\/forward\/render-playlist\/no\/custom-color\/88AA3C\/\" height=\"90\" width=\"600\" scrolling=\"no\"  allowfullscreen webkitallowfullscreen mozallowfullscreen oallowfullscreen msallowfullscreen><\/iframe>","thumbnail_url":"https:\/\/assets.libsyn.com\/secure\/content\/205682445"}