Quickest detection of market shocks in agent based models of the order book

We consider how local and global decision policies interact in quickest time change detection in multi-agent models of the order book. A monopolist market maker sets two-sided prices for an asset. The market evolves through the orders of trading agents. Agents observe local individual decisions of previous agents via an order book, combine these observed decisions with their noisy private signals about the asset, selfishly optimize their expected local utility, and then make their own individual decisions (whether to buy, sell or do nothing). Given this order book information, the goal is to achieve quickest change point detection when a shock occurs to the value of the asset. We provide a Bayesian formulation of the change point problem. Some structural results are given for the optimal policy.