Robustness in Sequential Decision Making under Evolving Uncertainty: Evidence from High-Frequency Market Making

2026-07-09

AI Summary

In high-frequency financial markets, dynamic uncertainty renders static trading strategies ineffective. This work proposes a state-dependent robust decision-making framework that dynamically adjusts trading policies along two dimensions: “uncertainty tolerance” and “action robustness.” Theoretical modeling, simulation experiments, and high-frequency empirical analysis demonstrate that robustness serves not merely as a safeguard against model misspecification but as a pivotal mechanism reshaping sequential decision behavior. Notably, action robustness exerts a significantly stronger influence on strategy performance than uncertainty tolerance. While moderate incorporation of action robustness enhances policy stability, excessive robustness in low-liquidity markets can suppress profitable opportunities.

Abstract

We study sequential decision making under evolving uncertainty in high-frequency financial markets, where changing market dynamics continually challenge static decision policies. We show that robustness has two economically meaningful dimensions: uncertainty tolerance, which determines how much uncertainty the decision maker allows, and action robustness, which governs how conservatively decisions respond. Robustness is not merely protection against model misspecification, but a state-dependent mechanism that reshapes sequential decision behaviors. Simulation and empirical evidence show that action robustness has a substantially larger impact than uncertainty tolerance. Moreover, excessive robustness may reduce profitability in illiquid markets by limiting execution opportunities.

Problem

• Sequential Decision Making
• Evolving Uncertainty
• Robustness
• High-Frequency Market Making
• Market Dynamics

Innovation

• robustness
• sequential decision making
• action robustness
• uncertainty tolerance
• high-frequency trading