Practice Lab: Deep Learning for Content-Based Filtering what are the y_train values?

Course Q&A Machine Learning Specialization Unsupervised Learning, Recommenders, Reinforcement
1

Hello friends,
In the practice lab “Deep Learning for Content-Based Filtering”, I’m trying to understand where is the y_train data coming from?
The related CSV simply contains a list of numbers, but what are those?
What is the model (using 2 neural networks) trained against?
I get what is the input data

  • a: user ratings per genre
  • b: movie’s genre’s presented as a one-hot vector

But what is the y_train data?

Cheers

1 Like
2

The y_train data are the movie ratings given by each user.

1 Like
3

Thank you for the quick reply.
I’m not sure I follow…

The y_train data is a list of numbers. I suppose 1 rating per movie.
Would that be the average rating given by users to each item?
If so why do that number differ from the input data item_train (column “ave rating”)?

1 Like
4

If I recall correctly, y_train is a matrix of size (users x movies).
It contains the ratings from each user for each movie they have watched.

1 Like
5

Ok I see. That data has been prepared/mapped outside of the lab and simply “given” to us for the sake of the exercise.
thanks a million!

1 Like