TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Ask HN: Favorite Online Recommendation Engine?

1 点作者 dexy超过 13 年前
What recommendation systems stand out as the most effective/relevant to you guys? These can be largely explicit feedback based systems (ie Netflix), implicit feedback based (ie Amazon), social graph based, etc.<p>Not looking for RMSE metrics or traffic driving numbers as much as subjective personal opinions.

1 comment

dexy超过 13 年前
Personally, I find Netflix does the best job and is easily worth the rating-entry time investment required.<p>It's not because of the content they show me, but rather because of the accuracy of their "predicted star rating" metric. Netflix showing me a broad spectrum of content I can immediately parse through by looking at predicted ratings combined with all the other standard quality metrics I look for has led me to find an immense wealth of content I never would have guessed I'd like.