Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Generating Top-N Recommendations for the Recommendation System #1

Open
PurushothamanSrikanth opened this issue Feb 25, 2021 · 5 comments

Comments

@PurushothamanSrikanth
Copy link

@Chinmayrane16 Can we have Top-N recommendation as a new feature to the existing one?
We can generate Top-N recommendations from the rating prediction matrix.

This is a feature request 😇

@Chinmayrane16
Copy link
Owner

@PurushothamanSrikanth Yes, it is possible and fairly simple. At inference, we can get the Top-N indexes (movies) from the user's rating vector with the maximum scores.

Do you wish to proceed and make a PR? ;)

@PurushothamanSrikanth
Copy link
Author

PurushothamanSrikanth commented Feb 25, 2021

@PurushothamanSrikanth Yes, it is possible and fairly simple. At inference, we can get the Top-N indexes (movies) from the user's rating vector with the maximum scores.

Do you wish to proceed and make a PR? ;)

  • That's great. I'm trying that, but I'm not able to do it properly.

@PurushothamanSrikanth
Copy link
Author

@PurushothamanSrikanth Yes, it is possible and fairly simple. At inference, we can get the Top-N indexes (movies) from the user's rating vector with the maximum scores.
Do you wish to proceed and make a PR? ;)

  • That's great. I'm trying that, but I'm not able to do it properly.

@Chinmayrane16 Are u talking about out matrix in [Training_Deep_AE.ipynb] ?(https://github.com/Chinmayrane16/DeepRecommender/blob/master/Training_Deep_AE.ipynb)

Untitled1

@Chinmayrane16
Copy link
Owner

@PurushothamanSrikanth Yeah, you could use that. Choose a particular index (user) and take its rating vector and select Top-N maximum indexes.
Map those indexes back to Movie names. :)

@PurushothamanSrikanth
Copy link
Author

@PurushothamanSrikanth Yeah, you could use that. Choose a particular index (user) and take its rating vector and select Top-N maximum indexes.

Map those indexes back to Movie names. :)

Will give that a try

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants