Obviously various optimization techniques can be used essentially as poor-man's machine learners. That doesn't mean they're particularly good at it.
In this case, Genetic Programming uses trees as its representation, and so it could be used as a tree-based classifier, but the OP has already indicated that he expects enormous numbers of rules, necessitating huge trees. For Genetic Programming, this translates into a gigantic search space.
As it was my thesis work, I'm always ready to promote Genetic Programming where appropriate. This is not the place. There are better tools for this task.
I do not think that he knew thousands of if-then rules would be needed, likely his estimate.
But that aside I believe that such a search space could be handled by GP. That very problem is what I've been tackling for sometime now. Its position on my list reflects that particular bias. But there are techniques. I use EDA's like MOSES and was heavily inspired by http://www-ia.hiof.no/~rolando/ but have my own original contributions. The method is also interactive for tough problems, these really help in reducing the search space. Although I have not succeeded in a use yet, I have been thinking hard about how category theory could be used to constrain space or perform particular automatic transofrmations (https://www.cs.ox.ac.uk/jeremy.gibbons/publications/origami...., https://www.cs.ox.ac.uk/people/jeremy.gibbons/publications/a...).
In this case, Genetic Programming uses trees as its representation, and so it could be used as a tree-based classifier, but the OP has already indicated that he expects enormous numbers of rules, necessitating huge trees. For Genetic Programming, this translates into a gigantic search space.
As it was my thesis work, I'm always ready to promote Genetic Programming where appropriate. This is not the place. There are better tools for this task.