Monday, October 02, 2006

Recommendation Systems & Netflix

Here's an interesting article from the NY Times on recommendation systems and Netflix:

To quote the Times:

"Recommendation systems, also known as collaborative filtering systems, try to predict whether a customer will like a movie, book or piece of music by comparing his or her past preferences to those of other people with similar tastes. Such systems will look at, say, the last 10 books, movies or songs a customer has rated highly and try to extrapolate an 11th." has already shown that such systems can be used to sell books and perhaps libraries would do well to augment Online Public Access Catalogs (OPACs) with recommendation features (many OPACs already store patrons' borrowing histories, right?). Perhaps such an implementation is presently impracticable. At any rate, the article is interesting, relevant to our class, and (in my opinion) warrants a read.


At 8:54 PM, Blogger Belle And Sebastian said...

This is an interesting idea, but i wonder if people would feel like this is a violation of their privacy. According to some in another class that I've taken, some people have considered it rude for library staff to make recommendations about books based on the percieved taste of the person reading the books.

This follows from the idea that selecting the book may be a very personal and or secret act, and for somone to notice, recommend and in doing so comment on the selection of the book it might risk the anonymity of the patron\user\consumer in that they might not want other people to know what they are reading, and they may wish to conduct their search for information in secret if it is a very personal issue around which they are seeking information.


Post a Comment

Links to this post:

Create a Link

<< Home