Reinforcement Learning and Trading on Noise in Limit Order Markets

This paper introduces reinforcement learning in a dynamic limit order market equilibrium to examine the effect of trading on noise. It shows that intensive noise liquidity provision (consumption) increases speculators’ liquidity consumption (provision), improving (reducing) market liquidity. Driven by uninformed chasing and informed aggressive liquidity provision, respectively, increasing noise liquidity provision and consumption improve price efficiency, generating a U-shaped price efficiency to the noise trading uncertainty on liquidity provision and consumption. Together with a hump-shaped (U-shaped) order profitability for the informed (uninformed) at a U-shaped noise trading cost in the noise trading uncertainty, this implies that, at increasing noise trading cost, intensive noise liquidity provision (consumption) makes market more (less) liquid, improves price efficiency and order profitability of informed traders, reduces the loss, even makes profit, for uninformed traders.