concept content - base filtering in category recommender system

This is an excerpt from Manning's book Practical Recommender Systems. Login to get full access to this book.

Content-based filtering uses the metadata you have on the items in your catalog. Netflix uses descriptions of its movies, for example.

Depending on the specific algorithm, the system can calculate recommendations either by taking the items the user has liked and finding similar content, by comparing the items and user profiles, or, if there’s no user involved, by finding similar content between items. When there’s a user profile, the system calculates a profile for each user that contains categories of the content. If Netflix used content-based filtering, it could create a user profile of genres like thrillers, comedies, drama, and new films, and give values to them all. Then a film gets recommended if it has similar values as the user.

You’ll be introduced to content-based filtering.

Figure 10.5. The item retriever returning recommendations with content-based filtering online.