I am reading this paper wide and deep learning recommedation system paper and haven't understood one thing.

To serve the latency, they actually first get the 100 best apps according to user query and rank them according to the probability score.

Does this mean that while buidling the model we have to build individual model for each app?

Are there any other Deep learning frameworks similar to this ?


1 Answer 1


I can only guess that since it is binary classifier based recommender model, it predicts whether a product is recommendable to a user or not with a probability score which can be set to a threshold.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.