Recommender_system_via_deep_RL icon indicating copy to clipboard operation
Recommender_system_via_deep_RL copied to clipboard

Published 20 hours ago • verified publisher icon backgom2357

Is it even related to the paper you have mentioned in the details.

Open kashyaprajveer opened this issue 2 years ago • 2 comments

You have divided users into test and train and not their interactions and you have trained to embedding on the whole dataset how can the training step will have all the datasets even for embedding it will make the model biased. Can you please correct me if I am wrong otherwise could you please write on the detail page that this is not the implementation of the paper as it is confusing and misleading.

kashyaprajveer avatar Nov 16 '22 15:11 kashyaprajveer

@kashyaprajveer You are totally right about it. Now, I mention it at Procedure on the README.

backgom2357 avatar Dec 13 '22 04:12 backgom2357

Great and you have divided users into test and train but in actual paper interaction of each user is divided into test and train. Which simply says this code is not related to the paper you have mentioned in the comments. Correct me if I am wrong.

kashyaprajveer avatar Dec 13 '22 15:12 kashyaprajveer