Home
Roger Chen's Library tagged → View Popular
CEUR-WS.org/Vol-532 - Recommender Systems and the Social Web 2009
Proceedings of the Workshop on Recommender Systems and the Social Web,
collocated with the 3rd ACM Conference on Recommender Systems (RecSys'09),
TechnoCalifornia: The Wisdom of the Few
One of the most common approaches to Recommender Systems is the so-called Collaborative Filtering. The main rationale is the following: In order to predict items that you will like, we find the most similar users to you by looking at your previous likes and dislikes. We then recommend items that those users have liked, but you still don't know.
Whimsley: Netflix Prize: Was The Napoleon Dynamite Problem Solved?
-
people aren't lists of numbers and don't watch movies as if they were
-
Anchoring suggests that rating systems need to take account of inertia — a user who has recently given a lot of above-average ratings is likely to continue to do so.
- 7 more annotations...
Mining gold from the Internet Movie Database, part 1: decoding user ratings
The Internet Movie Database (IMDb) is a rich source of online movie information. The problem is, the true gold is buried deep beneath the site’s user-friendly exterior and hidden within the database itself. With a little digging, however, we can extract the gold, nugget by nugget, and learn about fun statistical tools for data analysis.
向量 Vector 的空间: 关于下一代推荐系统的一些看法
-
单纯的collaborative filtering在实际系统中是不够的，我们需要利用内容信息，但是我们在使用内容时往往是简单的用来计算相似度。比如我们有书的作者，出版社，书名，标签信息。我们往往用这些信息来比较书的相似度，然后推荐相似的书给用户。但是我在研究中发现，用户对书的不同属性的依赖是不同的，有些用户比较信赖出版社，比如我买计算机书，只买几个著名出版社的，其他出版社的书我对他的质量不信任。也有些时候看作者，比如C++，一般只买大牛的书。
-
在电影推荐系统中，电影数总是少于用户数的，但在个性化搜索中，用户数是远远小于网页数的。
- 2 more annotations...
Selected Tags
Related Tags
Sponsored Links
Top Contributors
Groups interested in recommen...
Highlighter, Sticky notes, Tagging, Groups and Network: integrated suite dramatically boosting research productivity. Learn more »
Join Diigo