coordinated filtering
There are mainly two recommended methods
User-Based Collaborative Filtering
item-based collaborative filtering
Core idea: Recommend items similar to items they liked before to users
It is generally believed that if most users who like item A like item B, your items A and B are very similar.
User-based collaborative filtering:
Recommended steps:
1. Calculate the similarity between users
2. Recommend items from other users who have similar interests to the user
item-based collaborative filtering
Recommended steps:
1. Calculate the similarity between items
2. Recommend items to the user that are similar to the items he liked before
The formula for calculating similarity is generally:
1. Pearson correlation coefficient
2. Euclidean distance
3. Cosine Theorem
Equal formula
Refer to Xiang Liang's "Recommendation System Practice"