Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

I'm very new to this--I took a class last quarter and got hooked--now I'm in this competition and I don't know where to start (kind of). My problem is that I got this data that looks like a bunch of relational database tables and I don't know how to shape them into something I can try to feed into some kind of model. For example, I have users, users that are friends with other users, events, and users who are attending events. I know how to merge users and events together, convert it to floating point or integer values, and throw it into the model. Its the friends part that's has me confused. How can I bring the friends aspect into the equation?

share|improve this question
up vote 0 down vote accepted

If your framework will let you represent your data as a directed graph, that might be handy. You could use connections between users to represent a friend relationship, and use a structured machine learning algorithm for your classification. If not, you could create a binary feature vector that's the same length of all the unique visitors with which someone could be friends with, and have a 1 represent friendship, while 0 represents not friendship. Does that help?

share|improve this answer
Yeah man, thanks. That got the ball rolling again. – Brett Jan 15 '13 at 17:44
@Brett: Fantastic! – Kyle. Jan 15 '13 at 19:16

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.