Professional Documents
Culture Documents
Collaborative Filtering
Collaborative Filtering
Customer’s World
• What Book Should I read Next
• Which movie/ web-series to watch
• What food to order
• What dress to buy
You visit an online bookstore
On the webpage, they will display 5 book covers, especially for you.
• Item-based
• Recommend things that are similar to the items that you have
viewed/purchased before
User Profiles
For user-based recommendation, sites need to have some kind of user
profile.
Age
You
Salary
(Think in terms of many dimensions, not just these two)
K-Nearest Neighbour based Recommendation
Age
You
Salary
Your neighbours: recommend things that they have viewed/purchased
Collaborative Filtering: The main idea
E.g. Here are user ratings for some items: “?” means unrated.
A B C D E F G H
You: 7 2 1 8 9 9 ? ?
User1 1 8 8 2 ? 2 8 7
User2 6 3 3 7 6 5 3 1
User3 7 2 1 7 7 ? 3 1