Slope One recommenders
Slope One recommenders are a part of a family of algorithms introduced in a 2005 paper by Daniel Lemire and Anna Maclachlan. In this chapter, we'll introduce the weighted Slope One recommender.
Note
You can read the paper introducing the Slope One recommender at http://lemire.me/fr/abstracts/SDM2005.html.
To illustrate how weighted Slope One recommendation works, let's consider the simple example of four users, labeled W, X, Y, and Z, who have rated three movies—Amadeus, Braveheart, and Casablanca. The ratings each user has provided are illustrated in the following diagram:
As with any recommendation problem, we're looking to ...
Get Clojure for Data Science now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
