Linked from

The 29 pages that link to Recommender system, each with the reason it gives.

• Artificial intelligenceBroader topic: Recommendation algorithms use learned patterns to rank content, products, or services.

• Social mediaRelated: Recommendation systems extend social media distribution beyond accounts users already follow.

• Content moderationRelated: Visibility decisions can amplify content without removing it, raising moderation questions.

• Machine learningRelated: Learned preferences and item patterns help rank products, films, or other choices.

• PornographyRelated: Automated recommendations can shape exposure to and discovery of explicit material.

• NetflixRelated: Netflix uses personalized recommendations to help surface titles within a large catalog.

• Information retrievalCompared with: Recommendations rank items by predicted user interest, unlike retrieval's query-centered information need.

• Viral videoRelated: Platform recommendations can amplify videos beyond the people who first shared them.

• Attention economyRelated: Recommendations select what appears next, shaping where attention goes.

• Reinforcement learningRelated: Some recommenders optimize long-term engagement through feedback from user interactions.

• User-generated contentRelated: Recommendations can make a small share of user-made content widely visible.

• Search engineCompared with: Recommendations anticipate interests, while search engines respond to an explicit query.

• Sparse matrixRelated: User–item interaction data often forms a huge, mostly empty matrix.

• Filter bubbleNarrower topic: Ranking content by predicted interest can repeatedly favor familiar topics and viewpoints.

• Platform governanceRelated: Ranking and recommendations govern which content gains visibility.

• Civil service examinationCompared with: Early Chinese recruitment relied more heavily on recommendations than the later examination system did.

• Knowledge graphRelated: Graph connections can reveal related products, people, or content for recommendations.

• Cosine similarityRelated: It can compare user and item embeddings by their directional alignment.

• Social networking serviceRelated: Recommendations can surface posts and accounts beyond a user's direct connections.

• Data scienceBroader topic: Recommendation is a familiar deployment of data-driven prediction.

• PornhubRelated: Recommendations help organize a large catalog and influence which videos receive attention.

• MatchmakingRelated: Dating platforms apply recommendation methods to rank potential partners.

• Daniel EkRelated: Personalized discovery helps Spotify keep listeners engaged across a vast catalog.

• xHamsterRelated: Recommendations help organize a large catalog into personalized video suggestions.

• Zhang YimingNarrower topic: Personalized recommendations became central to ByteDance’s content-distribution strategy.

• Dead Internet theoryRelated: Ranking algorithms can shape what appears popular without creating the underlying posts.

• Pro-anaRelated: Recommendations may shape whether users encounter pro-ana material after related searches or viewing.

• Short-form contentRelated: Personalized ranking determines which brief videos and posts gain visibility.

• XNXXRelated: Recommendations can shape which videos viewers encounter.