FlowLOB: Efficient and Controllable Limit Order Book Generation with Flow Matching

2026-08-13

AI Summary

Existing limit order book (LOB) simulators struggle to simultaneously achieve realistic dynamics, efficient sampling, controllable generation, and cross-asset generalization. This work proposes FlowLOB, the first framework to introduce flow matching into LOB modeling, establishing a conditional flow-matching generative approach that enables multi-timescale trajectory synthesis and zero-shot transfer to unseen financial instruments. By unifying perspectives from flow matching and diffusion models—combined with tick-relative representation, a fixed-step ODE solver, and training on multi-frequency HKEX data—FlowLOB surpasses current baselines with only 10 ODE integration steps. It achieves superior performance on fine-grained distributional metrics and demonstrates high-fidelity, controllable zero-shot generation on held-out assets.

Abstract

Limit order book (LOB) simulators are most useful to practitioners when they combine realistic market dynamics, computationally efficient sampling, controllable scenario generation, and the ability to generalize beyond the instruments seen during training---properties that existing agent-based and deep generative simulators provide only partially. We present \textbf{FlowLOB}, a conditional \textbf{flow}-matching generator of \textbf{LOB} trajectories, trained on multiple Hong Kong Exchange (HKEX) symbols at three sampling frequencies ($0.1$s, $1$s, $10$s) in tick-relative representation that transfers to unseen instruments. Because flow and diffusion models admit a common formulation, we train both with identical data, architecture, and budget, and sample both through the same fixed-step ODE solvers, yielding a controlled comparison of sampling efficiency and fidelity. Flow matching attains its best quality with only $10$ ODE-solver steps, whereas diffusion needs many more function evaluations to approach the same fidelity. At this efficient operating point, FlowLOB improves realism over baselines, two learned and two agent-based models, in most distributional metrics at the two finer sampling frequencies. We evaluate counterfactual controllability with a distributional test that asks whether changing a scenario condition moves the generated statistic toward the corresponding real tail regime; FlowLOB satisfies this criterion in most tested settings. Both realism and control effects transfer zero-shot on a held-out symbol. We additionally conduct ablation studies on the network architecture and the learning rate.

Problem

• Limit Order Book
• Generative Modeling
• Market Simulation
• Controllability
• Generalization

Innovation

• flow matching
• limit order book generation
• controllable simulation
• zero-shot transfer
• sampling efficiency