Agree overall on most most points. Re. implementation, payouts are transactions too. Currently those perform a relatively simple calculations based on shares, and those transactions would need to remain limited in computational cost. I don't think this proposal changes that much though, it just has more complicated (but still computationally simple) accounting of shares by clutser. My concern is primarily the k-means clustering; Incremental k-means variants exist, so it is probably solvable.

Also, dividing users into clusters requires a minimum number of users in each cluster, thus a minimum number of users on the site as a while. At present I doubt that is feasible as the number of users on the site is just barely reaching the point where it works at all. Ideally of course the number of users will be much larger in the future, so something like this could be phased in.