Metraipolis › archive › dc_3352f2bed65e
FlowLOB: Efficient and Controllable Limit Order Book Generation with Flow Matching — arXiv:2608.13096
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13096
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:27:34.182Z
- SHA-256 of the archived text
c8596ebf86a6eb383abacc0bf7c85af2e9c42a1f2816720448a566bc1e857a31- Stable URL of this page
https://metraipolis.com/documento/dc_3352f2bed65e
How to cite
FlowLOB: Efficient and Controllable Limit Order Book Generation with Flow Matching — arXiv:2608.13096 — arXiv (en), https://arxiv.org/abs/2608.13096 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3352f2bed65e (Metraipolis archive dc_3352f2bed65e, sha256 c8596ebf86a6eb383abacc0bf7c85af2e9c42a1f2816720448a566bc1e857a31)
BibTeX
@misc{dc3352f2bed65e,
title = {FlowLOB: Efficient and Controllable Limit Order Book Generation with Flow Matching — arXiv:2608.13096},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13096},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3352f2bed65e; sha256 c8596ebf86a6eb383abacc0bf7c85af2e9c42a1f2816720448a566bc1e857a31},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13096. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Computational Engineering, Finance, and Science (cs.CE); Computational Finance (q-fin.CP); Trading and Market Microstructure (q-fin.TR).
Pagina del lavoro: https://arxiv.org/abs/2608.13096 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T04:20:35.847Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).