Censored Exploration and the Dark Pool Problem

2012/05/09 by Ganchev, Kuzman, Kearns, Michael, Nevmyvaka, Yuriy +1 · 1 citation
#Computer Science and Game Theory (cs.GT) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.1205.2646

Abstract

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.

Cited by

• Regulation or Competition:Major-Minor Optimal Liquidation across Dark and Lit Pools

Related

• Optimal Allocation Strategies for the Dark Pool Problem
• Market making and incentives design in the presence of a dark pool: a deep reinforcement learning approach
• Dark-Pool Perspective of Optimal Market Making
• Machine Learning-powered Pricing of the Multidimensional Passport Option
• Deep Hedging: Continuous Reinforcement Learning for Hedging of General Portfolios across Multiple Risk Aversions