I'm working on a hybrid recommendation system (collaborative and content-based) for an online ordering/shopping app. So far I've managed to identify a data-source for the collaborative model (likely item-based) but I'm having trouble deciding on features and algorithms for the content-based model.

I know it's probably specific to the problem I'm working on, but if anyone could share their experience or recommendations :) on what features give the best results for a content-based system it would be really helpful. All relevant advice/opinions welcome.

  • $\begingroup$ Please clarify your specific problem or provide additional details to highlight exactly what you need. As it's currently written, it's hard to tell exactly what you're asking. $\endgroup$
    – Community Bot
    Oct 10, 2022 at 7:26

1 Answer 1


Some features that have been found to work well for content-based recommender systems include:

  1. Item category (e.g. food, clothing, electronics, etc.)

  2. Item sub-category (e.g. type of food, type of clothing, etc.)

  3. Item brand

  4. Item price

  5. Item description

  6. Item reviewer ratings

  7. Number of reviews

  8. Overall sentiment of reviews

  9. Keywords associated with the item

  10. Any other relevant metadata


You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .