Censored Exploration and the Dark Pool Problem

TL;DR

This paper presents a polynomial-time algorithm for multi-venue exploration in censored data scenarios, inspired by the Dark Pool Problem in finance, with proven convergence and extensive real-data evaluation.

Contribution

Introduces a novel algorithm for censored exploration in multi-venue settings with polynomial convergence guarantees, advancing beyond prior asymptotic results.

Findings

Algorithm converges in polynomial time to near-optimal solutions

Extensive experiments demonstrate effectiveness on real trading data

Analysis aligns with reinforcement learning exploration strategies

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.