Maybe you know these, but I just came across them

• Enterprise Decision Management where I found some nice articles ..
  Is it scary to allow machines to make decisions (and related concepts of “load balancing”) which lead to an article in the Guardian on the importance of background rates when assessing the utility of tests (and hence models) It’s not so easy to predict murder - do the maths
  . Not quite the same concept, more about attributed risk, but interesting non the less is A Right Royal Statistical Fallacy
  An approach that purportedly combines a GA with a Random Forest approach The ART of (genetic) segmentation .. a paper explaining the algorithm a bit more (and it does seem to be proprietary) is at

Leveraging Randomness: The Science of Adaptive Random Trees. The approach is interesting .. maybe it merits closer study.

• Diamond Info Analytics Interesting articles on segmentation and “choice optimization”.