The value might not be in the ability of the model to correctly classify people but in it's ability to generate discussions about the classification.
"I'm a Gemini which fits because I am X but unlike most Gemini I like Y" tells you X and Y about someone.
Saying "Gemini and Aeries shouldn't date because of..." isn't necessarily a conversation about whether any given individuals should date. It may instead actually be a conversation about whether people who conform to certain sets of traits should date.
From direct observation, people who are persuaded astrology tend to know a lot of people. You could say a sort of map to observe and predict relationships across all the people you already know and all the people you will meet is useful.
Conversely, people who are very outspoken against astrology don't have as varied, dynamic and big social circles. Hence they'd not need a "social map", and they might even lack the social intelligence to realize that other people do.
Not much of a model IMHO. You just give ultra general predictions for every sign such that everyone will go “that’s true” or “that actually happened” no matter who they are - unless they are really weird.