Metraipolis › archive › dc_7b06936fd607
StochLOB: Heavy-Tailed Score Matching for Robust Limit Order Book Trend Prediction — arXiv:2610.21081
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21081
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:20:09.255Z
- SHA-256 of the archived text
fecfb07a2ca8abc4ffff3c31a3f2f0d92aa625b53cc9b5b1744cdba7f4396319- Stable URL of this page
https://metraipolis.com/documento/dc_7b06936fd607
How to cite
StochLOB: Heavy-Tailed Score Matching for Robust Limit Order Book Trend Prediction — arXiv:2610.21081 — arXiv (en), https://arxiv.org/abs/2610.21081 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7b06936fd607 (Metraipolis archive dc_7b06936fd607, sha256 fecfb07a2ca8abc4ffff3c31a3f2f0d92aa625b53cc9b5b1744cdba7f4396319)
BibTeX
@misc{dc7b06936fd607,
title = {StochLOB: Heavy-Tailed Score Matching for Robust Limit Order Book Trend Prediction — arXiv:2610.21081},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21081},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7b06936fd607; sha256 fecfb07a2ca8abc4ffff3c31a3f2f0d92aa625b53cc9b5b1744cdba7f4396319},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21081. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Score-based diffusion methods usually perturb data with Brownian Gaussian noise, corresponding to a light-tailed forward stochastic differential equation (SDE). For market time series this SDE can be a poor abstraction: limit order book (LOB) order flow is heavy-tailed, bursty, and occasionally jump-like. We study STOCHLOB, a training-only score-matching framework that changes the forward diffusion corruption law while leaving the deployed predictor deterministic. Instead of Brownian-only Gaussian corruption, the noising process uses two non-Gaussian SDE-inspired alternatives: jump-Lévy noise through a compound-Poisson variance mixture, and clipped $\alpha$-stable noise through a positive-stable Gaussian scale mixture. These corruptions inject finite jumps and heavy-tailed residuals into training without requiring reverse-time diffusion sampling at inference. The resulting score target has a useful interpretation: its radial factor $h_t(r)$ is the posterior expected corruption precision, so large residuals are weighted according to the latent corruption scale that most plausibly generated them. On chronologically held-out Coinbase LOB data, the proposed variants remain competitive on uncorrupted BTC and altcoin test horizons and improve several realized tail-window stress diagnostics. An exploratory Feishu A-share transfer study further tests whether the probability outputs remain usable under transaction costs and trading-rule constraints. Code and configuration files are available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Trading and Market Microstructure (q-fin.TR); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2610.21081 — 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 2026-10-16T08:48:02.679Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).