I have I set of 6k surveys about personal tastes (40 columns with answer number) and another set of 50M cookies about web activities (columns are all continuous). Some of these 50M can be connected to the 6k.

What I'd like to do is to "extend" all my 6k surveys questions based on my 6k cookies data to the rest of the 50M.

Which approach do you recommend? Some kind of cluster analysis or question by question prediction? Another method? One question could depend on the previous.



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.