From the course: Building Recommender Systems with Machine Learning and AI
Unlock this course with a free trial
Join today to access over 23,200 courses taught by industry experts.
KNN recommenders - Python Tutorial
From the course: Building Recommender Systems with Machine Learning and AI
KNN recommenders
- As we've seen, it's very difficult to evaluate collaborative filtering without running expensive experiments on real-world users. Since they aren't based on making rating predictions, we can't really measure their accuracy offline. So the concept of collaborative filtering has been applied to recommender systems that do make rating predictions, and these are generally referred to in the literature as "KNN recommenders". Let's have a look at how they work. Let's revisit the architecture of a recommender system based on rating predictions. In this sort of system, we generate recommendation candidates by predicting the ratings of everything a user hasn't already rated and selecting the top K items with the highest predicted ratings. From there, everything else works more or less the same way. This obviously isn't a terribly efficient approach, but since we're predicting rating values, we can measure the offline accuracy of the system using train test or cross-validation, which is…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Contents
-
-
-
-
-
-
-
(Locked)
Measuring similarity and sparsity4m 49s
-
(Locked)
Similarity metrics8m 32s
-
User-based collaborative filtering7m 25s
-
(Locked)
User-based collaborative filtering: Hands-on4m 59s
-
(Locked)
Item-based collaborative filtering4m 14s
-
(Locked)
Item-based collaborative filtering: Hands-on2m 23s
-
(Locked)
Tuning collaborative filtering algorithms3m 31s
-
(Locked)
Evaluating collaborative filtering systems offline1m 28s
-
(Locked)
Measure the hit rate of item-based collaborative filtering2m 17s
-
(Locked)
KNN recommenders4m 4s
-
(Locked)
Running user- and item-based KNN on MovieLens2m 26s
-
(Locked)
Experiment with different KNN parameters4m 25s
-
(Locked)
Bleeding edge alert: Translation-based recommendations2m 29s
-
(Locked)
-
-
-
-
-
-
-
-