We present the first large-scale empirical application of reinforcement learning to the important problem of optimized trade execution in modern financial markets. Our experiments are based on 1.5 years of millisecond time-scale limit order data from NASDAQ, and demonstrate the promise of reinforcement learning methods to market microstructure problems. Our learning algorithm introduces and exploits a natural "low-impact" factorization of the state space.

We introduce and analyze a natural algorithm for multi-venue exploration from censored data, which is motivated by the Dark Pool Problem of modern quantitative finance. We prove that our algorithm converges in polynomial time to a near-optimal allocation policy; prior results for similar problems in stochastic inventory control guaranteed only asymptotic convergence and examined variants in which each venue could be treated independently. Our analysis bears a strong resemblance to that of efficient exploration/ exploitation schemes in the reinforcement learning literature. We describe an extensive experimental evaluation of our algorithm on the Dark Pool Problem using real trading data. Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, to republish, to post on servers, or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from Publications Dept., ACM, Inc., fax +1 (212) AbstractWe introduce and analyze a natural algorithm for multi-venue exploration from censored data, which is motivated by the Dark Pool Problem of modern quantitative finance. We prove that our algorithm converges in polynomial time to a near-optimal allocation policy; prior results for similar problems in stochastic inventory control guaranteed only asymptotic convergence and examined variants in which each venue could be treated independently. Our analysis bears a strong resemblance to that of efficient exploration/exploitation schemes in the reinforcement learning literature. We describe an extensive experimental evaluation of our algorithm on the Dark Pool Problem using real trading data.

Addressing the ongoing controversy over aggressive high-frequency trading practices in financial markets, we report the results of an extensive empirical study estimating the maximum possible profitability of such practices, and arrive at figures that are surprisingly modest. Our findings highlight the tension between execution costs and trading horizon confronted by high-frequency traders, and provide a controlled and large-scale empirical perspective on the high-frequency debate that has heretofore been absent. Our study employs a number of novel empirical methods, including the simulation of an "omniscient" high-frequency trader who can see the future and act accordingly.

Addressing the ongoing controversy over aggressive high-frequency trading practices in financial markets, we report the results of an extensive empirical study estimating the maximum possible profitability of such practices, and arrive at figures that are surprisingly modest. Our findings highlight the tension between execution costs and trading horizon confronted by high-frequency traders, and provide a controlled and large-scale empirical perspective on the high-frequency debate that has heretofore been absent. Our study employs a number of novel empirical methods, including the simulation of an "omniscient" high-frequency trader who can see the future and act accordingly.

No abstract