User-based collaborative filtering
In the previous section, the algorithm was based on items and the steps to identify recommendations were as follows:
Identify which items are similar in terms of having been purchased by the same people
Recommend to a new user the items that are similar to its purchases
In this section, we will use the opposite approach. First, given a new user, we will identify its similar users. Then, we will recommend the top-rated items purchased by similar users. This approach is called user-based collaborative filtering. For each new user, these are the steps:
Measure how similar each user is to the new one. Like IBCF, popular similarity measures are correlation and cosine.
Identify the most similar users. The options are:
Take account of the top k users (k-nearest_neighbors)
Take account of the users whose similarity is above a defined threshold
Rate the items purchased by the most similar users. The rating is the average rating among similar users and the approaches are...
