Frequency of rank k is proportional to k to the power of minus s.

George Kingsley Zipf (1902-1950) showed that in language, cities, and much of human activity, a few things happen a lot and most things happen a little. Plot rank on one axis and frequency on the other and you get a power law. The exponent s is usually near 1: the second item appears about half as often as the first, the third about a third as often, and so on down a long tail.

Physical commerce is the same curve. A handful of SKUs, merchants, neighborhoods, and hours carry most of the volume. The rest is a long tail that still feeds the system - but you cannot see either end from reviews, maps, or search. You see it from bills.

That is why the company is called ZipF. The Commerce Event Graph is how the law becomes measurable in the real economy: every checkout written as rank, frequency, place, and price. Own the event stream and you can read the head of the distribution, the tail, and the way they move - which is the asset.