GaetanDu

I was facing a similar issue. My dataset: - 1500 user_id - 83498 books - 167813 mapping then after training i had: `Recommendations for user 42: [b'clara callan' b'clara callan'...

My data is a pandas dataframe i didn't use tensorflow to make unique representation, here is how i preprocess: ``` unique_book_titles_df = pd.DataFrame(overall_data.book_title.unique(), columns=['book_title']) books = {key: col.values for key,...

Yes i have different recommendations and what are you giving to: ``` tfrs.tasks.Retrieval( metrics=tfrs.metrics.FactorizedTopK( candidates=books.batch(128).map(self.book_model) ) ) ``` and ``` # Create a model that takes in raw query features,...

Yes, it will be easier to debug if you share your code

Hello, are you sure it is a bad recommendation? I mean i have the same recommendations when i'm trying on new user_id are you ? I suppose this is due...