Segment Allocation

#1
Hi,

I'm a new user to this forum so apologies if i've posted in the wrong area.

My problem is to do with allocating segments to a database. A segmentation solution has been built using questionairre and lifestyle data without considering how it is to be implemented onto a database. As there isn't enough volume to identify bridging variables i have built logistic models for each segment and then allocated the customer to the segment based on maximum probabilities. I'm able to obtain a 40% allocation rate (above the 1 in 5 random)

Is there a different approach i should be considering ?

I've tried decision trees, discriminant analysis so far

Thanks,
Ian