Metraipolis › archive › dc_dd1891ed9469

What Do Foundation Models for Market Microstructure Learn? A Controlled Study with Synthetic Limit Order Books — arXiv:2610.20104

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.20104
License (as archived)
CC0-1.0
Archived
2026-10-15T14:19:31.726Z
SHA-256 of the archived text
4d039367b99919d16dde726f7ab6dbaa16fe241c9a94111551d714f3f9a7c1ca
Stable URL of this page
https://metraipolis.com/documento/dc_dd1891ed9469

How to cite

What Do Foundation Models for Market Microstructure Learn? A Controlled Study with Synthetic Limit Order Books — arXiv:2610.20104 — arXiv (en), https://arxiv.org/abs/2610.20104 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dd1891ed9469 (Metraipolis archive dc_dd1891ed9469, sha256 4d039367b99919d16dde726f7ab6dbaa16fe241c9a94111551d714f3f9a7c1ca)
BibTeX
@misc{dcdd1891ed9469,
  title = {What Do Foundation Models for Market Microstructure Learn? A Controlled Study with Synthetic Limit Order Books — arXiv:2610.20104},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20104},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dd1891ed9469; sha256 4d039367b99919d16dde726f7ab6dbaa16fe241c9a94111551d714f3f9a7c1ca},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20104. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autoregressive transformers trained on limit order book (LOB) message streams are increasingly proposed as foundation models for market microstructure. Because the generative process of real markets is unknown, these models can be judged only by the realism of their output, leaving open what they actually learn. We make the question answerable by inverting the setup: we train GPT-style models on order flow from simulators whose latent parameters are known, so that the Bayes-optimal predictor, the generating state, and the exact data entropy serve as references. Measured against them, next-token pretraining on order flow implements amortized Bayesian inference over market regimes. The learned predictive matches the exact Bayes optimum to within a millinat per token and approaches the oracle floor even on a nonstationary family whose latent state drifts within an episode, a regime that requires filtering. The latent regime is linearly decodable from frozen activations, well above baselines, so a frozen-model read-out calibrates simulator parameters more accurately than windowed maximum likelihood at a fraction of the cost. In our experiments these capabilities are not produced by scale: capacity and token volume saturate early, and it is the diversity of training regimes, not the token count, that determines generalization to unseen markets. On real NASDAQ data, zero-shot transfer is set by how well the simulator prior covers real flow: an enriched mixture nearly closes the gap to an in-domain baseline, and pretraining beats from-scratch training at every budget across held-out tickers. Known ground truth turns average next-token loss, which is uninformative near the entropy floor, into an exact comparison against the Bayes-optimal and oracle predictors.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.20104 — 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 2026-10-15T13:53:35.696Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).