[Question] How can I detect and prevent folding ?

Hi,

Thanks for your great library and tutorials !

In a previous blog post from Google, a phenomenon known as folding was mentioned for recommender systems that only use positive feedbacks. Reference: https://developers.google.com/machine-learning/recommendation/dnn/training?hl=en.

After training a retrieval model with only positive feedbacks, I suspect some item-to-item recommendations to encounter folding. First results seem at first glance great excepted for one item for which some results mismatch with a completely different category of items that doesn't make sense.

My first question is how can we really know we are facing this issue ? Is there a technique or a metric ?

In the blog post, they recommend to use negative feedbacks to prevent this phenomenon. Without having negative feedbacks in my dataset, is there a way to generate negative feedbacks ? Is it a good practice to include negative feedbacks in a retrieval model or should I use a ranking model ?

Thanks,
Jérémy

Start with the linked Google machine-learning recommendation article and the retrieval model setup described in the issue. Compare its folding concerns with the reported item-to-item mismatch, then document how to detect the problem and whether negative feedback or a ranking model is appropriate; done means providing a clear, evidence-based answer.