Modeling of a dynamic pricing environment to enable success in complex adaptive markets

Pricing for success in complex adaptive markets is a difficult problem. Established wisdom derives approaches from a view of market-equilibrium, and further from a number of pricing tactics that have worked in simpler, monopoly-like markets. This paper by contrast examines a pricing approach built on a hypotheses-driven, market-tree mechanism that due to its dynamic, flexible nature is arguably better suited for complex adaptive markets. Rapid pricing-rule prototyping based on hypotheses, and leveraging of algorithms and machine learning to appropriately search a live market-tree to decide in real-time the branches to be pruned versus grown, is the design proposed in this paper.