Collaborative filtering algorithm

1, user-based collaborative filtering algorithm steps:

1.1 Find user collections that are similar to the interest of the target user

1.2 Find items in this collection that the user likes, and the target user has not heard the item recommended to the target user

The key to step 1 is to calculate the interest similarity of 2 users.

2. Object-based collaborative filtering algorithm

2.1 Calculating the similarity between items

2.2 Generate a referral list based on the similarity of the item and the user's historical behavior

USERCF: Recommend items to users who are interested in public interest.

Focus on the focus of small groups that reflect the interests of users; socialization, reflecting the popularity of items in small interest groups where the user is located

ITEMCF: Recommend items that are similar to those he liked before.

Focus on maintaining the user's historical interest; personalization, reflecting the user's own interests and heritage

Collaborative filtering algorithm