[[["容易理解","easyToUnderstand","thumb-up"],["確實解決了我的問題","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["缺少我需要的資訊","missingTheInformationINeed","thumb-down"],["過於複雜/步驟過多","tooComplicatedTooManySteps","thumb-down"],["過時","outOfDate","thumb-down"],["翻譯問題","translationIssue","thumb-down"],["示例/程式碼問題","samplesCodeIssue","thumb-down"],["其他","otherDown","thumb-down"]],["上次更新時間：2024-07-26 (世界標準時間)。"],[[["\u003cp\u003eRecommendation systems enhance content browsing and help users discover new items.\u003c/p\u003e\n"],["\u003cp\u003eRecommender systems are built with three primary components: candidate generation, scoring, and re-ranking.\u003c/p\u003e\n"],["\u003cp\u003eWhile machine learning is often associated with recommendation systems, using it solely to promote sponsored items is not recommended.\u003c/p\u003e\n"]]],[],null,["\u003cbr /\u003e\n\nWhy would you use recommendation systems? \nHaving a recommendation engine makes browsing content easier. \nPlus, a great recommendation system helps users find things they wouldn't have thought to look for on their own. \nYou think you have to sprinkle ML on everything. \nIt might seem that way, but in reality, there are much better reasons to use ML. \nYou want to direct users to sponsored items. \nYikes, this is not a great reason to use any ML solution. \nWhat are the primary components of a recommender system? \ncandidate generation, scoring, and re-ranking \nNicely done! These are the three primary components of any recommendation system. \nembedding, similarity metrics, and serving \nThese elements are related to recommendation systems, but they are not primary components. \nmatrix factorization, DNN, and reranking \nWhile re-ranking is a component, matrix factorization and DNN are types of candidate generators."]]
