Order book regulatory impact on stock market quality: a multi-agent reinforcement learning perspective

Paper: arXiv 2302.04184

Authors: Johann Lussange, Boris Gutkin

Abstract

Recent technological developments have changed the fundamental ways stock markets function, bringing regulatory instances to assess the benefits of these developments. In parallel, the ongoing machine learning revolution and its multiple applications to trading can now be used to design a next generation of financial models, and thereby explore the systemic complexity of financial stock markets in new ways. We here follow on a previous groundwork, where we designed and calibrated a novel agent-based model stock market simulator, where each agent autonomously learns to trade by reinforcement learning. In this Paper, we now study the predictions of this model from a regulator’s perspective. In particular, we focus on how the market quality is impacted by smaller order book tick sizes, increasingly larger metaorders, and higher trading frequencies, respectively. Under our model assumptions, we find that the market quality benefits from the latter, but not from the other two trends.

Complexity vs Empirical Score

• Math Complexity: 6.5/10
• Empirical Rigor: 6.0/10
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: This paper presents an innovative application of multi-agent reinforcement learning (MARL) to model market microstructures and evaluate regulatory impacts. While it relies heavily on simulation rather than broad empirical market data, the mathematical modeling of the agent environment and systemic dynamics is strong and offers novel policy insights.

Research Flowchart

  flowchart TD
    A[Research Goal: Assess regulatory impact of tick size, metaorders, and trading frequency on market quality] --> B[Input: Limit Order Book data & Agent-Based Model calibration]
    B --> C[Methodology: Multi-Agent Reinforcement Learning LOB Simulator]
    C --> D[Simulation Experiments: Vary Tick Size, Metaorder Size, and Trading Frequencies]
    D --> E[Outcome: Higher trading frequency improves market quality]
    D --> F[Outcome: Smaller tick sizes & larger metaorders do NOT improve market quality]