
Deep Learning with TensorFlow
By :

In this section, we will see how to utilize collaborative filtering to develop a recommendation engine. However, before that let's discuss the utility matrix of preferences.
In a collaborative filtering-based recommendation system, there are dimensions of entities: users and items (items refer to products, such as movies, games, and songs). As a user, you might have preferences for certain items. Therefore, these preferences must be extracted out of the data about items, users, or ratings. This data is often represented as a utility matrix, such as a user-item pair. This type of value can represent what is known about the degree of preference that the user has for a particular item.
The entry in the matrix can come from an ordered set. For example, integers 1-5 can be used to represent the number of stars that the user gave when rating items. We have already mentioned that users might not rate items very often, so most entries...