{"id":12906,"date":"2023-03-04T09:43:55","date_gmt":"2023-03-04T14:43:55","guid":{"rendered":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/?p=12906"},"modified":"2023-03-11T11:05:12","modified_gmt":"2023-03-11T16:05:12","slug":"users-interests-are-multi-faceted-recommendation-models-should-be-too","status":"publish","type":"post","link":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/users-interests-are-multi-faceted-recommendation-models-should-be-too\/12906\/","title":{"rendered":"Users\u2019 Interests are Multi-Faceted: Recommendation Models Should Be Too"},"content":{"rendered":"Originally published in Spotify Research, Feb 22, 2023. A new approach to calibrating recommendations to user interests Users\u2019 interests are multi-faceted and representing different aspects of users\u2019 interest in their recommendations is an important factor for recommender systems to help users navigate more quickly to items or content they may be interested in. This property is often referred to as the\u00a0calibration\u00a0problem and has achieved significant attention recently. Calibration is particularly important given that a sole optimization towards accuracy can often lead to the user\u2019s minority interests being dominated by their main interests, or by a few overall popular <a href=\"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/users-interests-are-multi-faceted-recommendation-models-should-be-too\/12906\/\" class=\"more-link\">(more&hellip;)<\/a>","protected":false},"excerpt":{"rendered":"<p>Originally published in Spotify Research, Feb 22, 2023. A new approach to calibrating recommendations to user interests Users\u2019 interests are multi-faceted and representing different aspects of users\u2019 interest in their recommendations is an important factor for recommender systems to help users navigate more quickly to items or content they may be interested in. This property [&hellip;]<\/p>\n","protected":false},"author":72,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","_links_to":"","_links_to_target":""},"categories":[11,48],"tags":[879,368,1231,243,8],"class_list":["post-12906","post","type-post","status-publish","format-standard","hentry","category-industry-news","category-left-hand","tag-ai","tag-artificial-intelligence","tag-data-modeling","tag-machine-learning","tag-predictive-analytics"],"_links":{"self":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/12906","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/users\/72"}],"replies":[{"embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/comments?post=12906"}],"version-history":[{"count":3,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/12906\/revisions"}],"predecessor-version":[{"id":12909,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/posts\/12906\/revisions\/12909"}],"wp:attachment":[{"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/media?parent=12906"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/categories?post=12906"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.predictiveanalyticsworld.com\/machinelearningtimes\/wp-json\/wp\/v2\/tags?post=12906"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}