What model is "Taking Advantage of Context Features" tutorials based on?

i have a questions regarding this tutorial:

what recommendation model does this tutorial based on? is it Collaborative Filtering?
and if so why does it not use the ratings in the dataset used?
how did the model come up with the recommendation given, without the rating?

@Wei_Wei may help here

Yes, I also don’t find it clear how the rating is used.

It’s clear that the rating data is passed as the input here

But the compute_loss code in the “combined model” section doesn’t use the rating key.

It calculates some loss based on the features… I think the clue is the self.task = tfrs.tasks.Retrieval.

Retrieval and rating are often two separate steps. IIUC Retreival is “what should I even borther running the rating model on?”. So I think this model is very similar to any collaborative filtering model, except that instead of trying to predict what the rating is, it’s trying to predict “would this user have rated this movie in the first place?”.

I’ll ping the owner and see if they have any feedback.

Maciej pointed me to this paragraph:

In this tutorial, we are focusing on a retrieval system: a model that predicts a set of movies from the catalogue that the user is likely to watch. Often, implicit data is more useful here, and so we are going to treat Movielens as an implicit system. This means that every movie a user watched is a positive example, and every movie they have not seen is an implicit negative example.


1 Like

So is it correct to assume that its like kind of a deep learning Collaborative Filtering? because the tutorial that paragraph based on is a Matrix Factorization based Collaborative Filtering.