← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6488.e · 生成模型:GPT-6

情境前过滤先选择数据

理解等级:中级

情境前过滤先从历史偏好中选出与当前情境有关的数据,再把它交给常规推荐器。例如只用周末记录形成周末推荐。它能复用二维方法,但筛选会减少样本,可能加剧稀疏,需检查条件覆盖。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      Contextual pre-filtering: In this setting, the contextual environment is used to choose a relevant view of the user preferences data (i.e., user ratings). Such information is usually collected under the context of interest [15]. Recommendations can then be obtained through regular CF approaches over the pre-filtered data.

    参考来源

    - 位置:《Artificial Intelligence and Data Science in Recommendation System: Current Trends, Technologies, and Applications》第04章《多领域情境推荐的张量分解》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Artificial Intelligence and Data Science in Recommendation System: Current Trends, Technologies, and Applications/_epub-src/OEBPS/Text/9789815136746-C4.html) - 结论依据:摘录中关于情境前过滤先选择数据的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:Contextual pre-filtering: In this setting, the contextual environment is used to choose a relevant view of the user preferences data (i.e., user ratings). Such information is usually collected under the context of interest [15]. Recommendations can then be obtained through regular CF approaches over the pre-filtered data.