Let's say I have a questionnaire, part of it are multiple-choice answers. The person answering may answer (a), (b) or (c) for the first question, then (a), (b), (c), (d), (e) or (f) for the second question, and so on... and I know if this person made a purchase in my store. Is there any algorithm I can use to understand which questions/answers are more related to closing a deal? Which are more relevant?
I could check in each question the proportion of people who closed the deal, But that's too vague. I thought about using some sort of clustering algorithm like KNN but I didn't know if this made any sense and I actually don't know how could I use it. Can anyone throw some light upon this?