I am not sure if there exists an answer in previous questions, but I couldn't find.

Consider I show pictures to the people and they rate that picture 1-5 if they want to make a detailed rating or if they don't want, they just select it as liked (1) and disliked (0).

At the end, recommendations will be made with respect to the historical selections.

Let's clarify it with a real example. Consider the Tinder app. You slide right if you like the picture and you slide left if you don't. In addition to it, what if there also exists a 1 to 5 rating system if the user clicks inside the profile?

What do you suggest to make a collaborative filtering as for the 0 - 1 part, 1 - 5 part and merged situation?

(I actually asked the very same question in here. I am normally more active in stackoverflow with R tag and I know the rules of asking questions. However since I don't get an answer in Data Science platform, I thought that I asked it in wrong place.)


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.