EvoMarket: A High-Fidelity and Scalable Financial Market Simulator

2026-04-20

AI Summary

Existing financial market simulators struggle to simultaneously achieve mechanistic fidelity, microstructural realism, and large-scale scalability. This work proposes a discrete-event, multi-agent market simulator tailored for intervention experiments, supporting multi-asset, cross-day trading while incorporating realistic mechanisms such as call auctions, price limits, and T+1 settlement. A novel oracle-guided online self-calibration mechanism is introduced, which models microstructural discrepancies as missing order flows and dynamically synthesizes corrective orders, thereby avoiding opaque black-box calibration. Built upon a high-performance limit order book, hierarchical scheduling, and an asynchronous, asset-wise matching architecture, the system enables high-fidelity five-day replay on real Chinese A-share data, significantly improving depth accuracy across all price levels while supporting high-throughput order streams and cross-asset interaction analysis, demonstrating excellent scalability.

Technology Category

• Multiagent Systems: Mechanism Design
• Search and Optimization: Sampling/Simulation-based Search
• Game Theory and Economic Paradigms: Auctions and Market-Based Systems

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Search and Retrieval-Augmented AI: Agentic search
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

High-fidelity, scalable market simulation is a key instrument for mechanism evaluation, stress testing, and counterfactual policy analysis. Yet existing simulators rarely achieve \emph{mechanism fidelity} beyond single-asset intraday settings, \emph{microstructure fidelity} against historical limit order books (LOB), and \emph{computational tractability} at market scale in a single system. This paper presents \textit{EvoMarket}, a discrete-event, multi-agent financial market simulator designed for intervention-oriented experiments in multi-asset and cross-day environments. EvoMarket couples a high-throughput execution core (optimized LOB data structures, hierarchical scheduling under propagation delays, and asynchronous per-asset matching) with explicit institutional mechanisms (market calendars, opening call auctions, price limits, and T+1 settlement). To avoid expensive black-box calibration, EvoMarket introduces an Oracle-guided in-run self-calibration mechanism that interprets microstructure discrepancy as missing order flow and synthesizes corrective orders at recording checkpoints. Experiments on China A-share order-flow and LOB data show close replay alignment over five trading days, fidelity gains from budgeted in-run calibration across depth levels, broad agent order-space coverage, and scalable performance under increasing input order rates and market breadth. We further demonstrate cross-asset linkage and event-study style intervention evaluation that produces structured dependence and interpretable event-time responses.

Problem

• market simulation
• mechanism fidelity
• microstructure fidelity
• computational tractability
• financial market simulator

Innovation

• market simulation
• limit order book
• self-calibration
• multi-agent system
• microstructure fidelity