Every pre-registered attendee at the 1994 Machine Learning Conference and 1994 Computational Learning Theory Conference received a badge labeled with a "+" or "-".  The labeling was due to some function known only to the badge generator (Haym Hirsh), and it depended only on the attendee's name.  The goal for conference attendees was to identify the unknown function used to generate the +/- labeling.

The list of attendees is attached, along with their labels. Your task is to do the same: identify the unknown function used to generate the +/- labeling.

In doing so, think about how would you formalize it as a learning problem and what are the difficulties that arise in doing it.  You don't need to write a learning program to solve this task (for now, at least).  But think about how will you go about doing it and what may the difficulties be.

The data below is presented in the form of a +/- label followed by the person's name.  There are 294 examples, 210 positive and 84 negative.

Data